To see the other types of publications on this topic, follow the link: GAN Generative Adversarial Network.
Dissertations / Theses on the topic 'GAN Generative Adversarial Network'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'GAN Generative Adversarial Network.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Aftab, Nadeem. "Disocclusion Inpainting using Generative Adversarial Networks." Thesis, Mittuniversitetet, Institutionen för informationssystem och –teknologi, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:miun:diva-40502.
Full textAbstract:
The old methods used for images inpainting of the Depth Image Based Rendering (DIBR) process are inefficient in producing high-quality virtual views from captured data. From the viewpoint of the original image, the generated data’s structure seems less distorted in the virtual view obtained by translation but when then the virtual view involves rotation, gaps and missing spaces become visible in the DIBR generated data. The typical approaches for filling the disocclusion tend to be slow, inefficient, and inaccurate. In this project, a modern technique Generative Adversarial Network (GAN) is used to fill the disocclusion. GAN consists of two or more neural networks that compete against each other and get trained. This study result shows that GAN can inpaint the disocclusion with a consistency of the structure. Additionally, another method (Filling) is used to enhance the quality of GAN and DIBR images. The statistical evaluation of results shows that GAN and filling method enhance the quality of DIBR images.
2
Yamazaki, Hiroyuki Vincent. "On Depth and Complexity of Generative Adversarial Networks." Thesis, KTH, Skolan för datavetenskap och kommunikation (CSC), 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-217293.
Full textAbstract:
Although generative adversarial networks (GANs) have achieved state-of-the-art results in generating realistic look- ing images, they are often parameterized by neural net- works with relatively few learnable weights compared to those that are used for discriminative tasks. We argue that this is suboptimal in a generative setting where data is of- ten entangled in high dimensional space and models are ex- pected to benefit from high expressive power. Additionally, in a generative setting, a model often needs to extrapo- late missing information from low dimensional latent space when generating data samples while in a typical discrimina- tive task, the model only needs to extract lower dimensional features from high dimensional space. We evaluate different architectures for GANs with varying model capacities using shortcut connections in order to study the impacts of the capacity on training stability and sample quality. We show that while training tends to oscillate and not benefit from additional capacity of naively stacked layers, GANs are ca- pable of generating samples with higher quality, specifically for images, samples of higher visual fidelity given proper regularization and careful balancing.<br>Trots att Generative Adversarial Networks (GAN) har lyckats generera realistiska bilder består de än idag av neurala nätverk som är parametriserade med relativt få tränbara vikter jämfört med neurala nätverk som används för klassificering. Vi tror att en sådan modell är suboptimal vad gäller generering av högdimensionell och komplicerad data och anser att modeller med högre kapaciteter bör ge bättre estimeringar. Dessutom, i en generativ uppgift så förväntas en modell kunna extrapolera information från lägre till högre dimensioner medan i en klassificeringsuppgift så behöver modellen endast att extrahera lågdimensionell information från högdimensionell data. Vi evaluerar ett flertal GAN med varierande kapaciteter genom att använda shortcut connections för att studera hur kapaciteten påverkar träningsstabiliteten, samt kvaliteten av de genererade datapunkterna. Resultaten visar att träningen blir mindre stabil för modeller som fått högre kapaciteter genom naivt tillsatta lager men visar samtidigt att datapunkternas kvaliteter kan öka, specifikt för bilder, bilder med hög visuell fidelitet. Detta åstadkoms med hjälp utav regularisering och noggrann balansering.
3
Eisenbeiser, Logan Ryan. "Latent Walking Techniques for Conditioning GAN-Generated Music." Thesis, Virginia Tech, 2020. http://hdl.handle.net/10919/100052.
Full textAbstract:
Artificial music generation is a rapidly developing field focused on the complex task of creating neural networks that can produce realistic-sounding music. Generating music is very difficult; components like long and short term structure present time complexity, which can be difficult for neural networks to capture. Additionally, the acoustics of musical features like harmonies and chords, as well as timbre and instrumentation require complex representations for a network to accurately generate them. Various techniques for both music representation and network architecture have been used in the past decade to address these challenges in music generation.
The focus of this thesis extends beyond generating music to the challenge of controlling and/or conditioning that generation. Conditional generation involves an additional piece or pieces of information which are input to the generator and constrain aspects of the results. Conditioning can be used to specify a tempo for the generated song, increase the density of notes, or even change the genre. Latent walking is one of the most popular techniques in conditional image generation, but its effectiveness on music-domain generation is largely unexplored. This paper focuses on latent walking techniques for conditioning the music generation network MuseGAN and examines the impact of this conditioning on the generated music.<br>Master of Science<br>Artificial music generation is a rapidly developing field focused on the complex task of creating neural networks that can produce realistic-sounding music. Beyond simply generating music lies the challenge of controlling or conditioning that generation. Conditional generation can be used to specify a tempo for the generated song, increase the density of notes, or even change the genre. Latent walking is one of the most popular techniques in conditional image generation, but its effectiveness on music-domain generation is largely unexplored, especially for generative adversarial networks (GANs). This paper focuses on latent walking techniques for conditioning the music generation network MuseGAN and examines the impact and effectiveness of this conditioning on the generated music.
4
Oskarsson, Joel. "Probabilistic Regression using Conditional Generative Adversarial Networks." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166637.
Full textAbstract:
Regression is a central problem in statistics and machine learning with applications everywhere in science and technology. In probabilistic regression the relationship between a set of features and a real-valued target variable is modelled as a conditional probability distribution. There are cases where this distribution is very complex and not properly captured by simple approximations, such as assuming a normal distribution. This thesis investigates how conditional Generative Adversarial Networks (GANs) can be used to properly capture more complex conditional distributions. GANs have seen great success in generating complex high-dimensional data, but less work has been done on their use for regression problems. This thesis presents experiments to better understand how conditional GANs can be used in probabilistic regression. Different versions of GANs are extended to the conditional case and evaluated on synthetic and real datasets. It is shown that conditional GANs can learn to estimate a wide range of different distributions and be competitive with existing probabilistic regression models.
5
Rinnarv, Jonathan. "GANChat : A Generative Adversarial Network approach for chat bot learning." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-278143.
Full textAbstract:
Recently a new method for training generative neural networks called Generative Adversarial Networks (GAN) has shown great results in the computer vision domain and shown potential in other generative machine learning tasks as well. GAN training is an adversarial training method where two neural networks compete and attempt to outperform each other, and in the process they both learn. In this thesis the effectiveness of GAN training is tested on conversational agents also called chat bots. To test this, current state-of-the-art training methods such as Maximum Likelihood Estimation (MLE) models are compared with GAN method trained models. Model performance was measured by closeness of the model distribution from the target distribution after training. This thesis shows that the GAN method performs worse the MLE in some scenarios but can outperform MLE in some cases.<br>Nyligen har en ny metod för att träna generativa neurala nätverk kallad Generative Adversarial Networks (GAN) visat bra resultat inom datorseendedomänen och visat potential inom andra maskininlärningsområden också GAN-träning är en träningsmetod där två neurala nätverk tävlar och försöker överträffa varandra, och i processen lär sig båda. I detta examensarbete har effektiviteten av GAN-träning testats på konversationsagenter, som också kallas Chat bots. För att testa det här jämfördes modeller tränade med nuvarande state-of- the-art träningsmetoder, så som Maximum likelihood-metoden (ML), med GAN-tränade modeller. Modellernas prestation mättes genom distans från modelldistribution till måldistribution efter träning. Det här examensarbetet visar att GAN-metoden presterar sämre än ML-metoden i vissa scenarier men kan överträffa ML i vissa fall.
6
Ljung, Mikael. "Synthetic Data Generation for the Financial Industry Using Generative Adversarial Networks." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301307.
Full textAbstract:
Following the introduction of new laws and regulations to ensure data protection in GDPR and PIPEDA, interests in technologies to protect data privacy have increased. A promising research trajectory in this area is found in Generative Adversarial Networks (GAN), an architecture trained to produce data that reflects the statistical properties of its underlying dataset without compromising the integrity of the data subjects. Despite the technology’s young age, prior research has made significant progress in the generation process of so-called synthetic data, and the current models can generate images with high-quality. Due to the architecture’s success with images, it has been adapted to new domains, and this study examines its potential to synthesize financial tabular data. The study investigates a state-of-the-art model within tabular GANs, called CTGAN, together with two proposed ideas to enhance its generative ability. The results indicate that a modified training dynamic and a novel early stopping strategy improve the architecture’s capacity to synthesize data. The generated data presents realistic features with clear influences from its underlying dataset, and the inferred conclusions on subsequent analyses are similar to those based on the original data. Thus, the conclusion is that GANs has great potential to generate tabular data that can be considered a substitute for sensitive data, which could enable organizations to have more generous data sharing policies.<br>Med striktare förhållningsregler till hur data ska hanteras genom GDPR och PIPEDA har intresset för anonymiseringsmetoder för att censurera känslig data aktualliserats. En lovande teknik inom området återfinns i Generativa Motstridande Nätverk, en arkitektur som syftar till att generera data som återspeglar de statiska egenskaperna i dess underliggande dataset utan att äventyra datasubjektens integritet. Trots forskningsfältet unga ålder har man gjort stora framsteg i genereringsprocessen av så kallad syntetisk data, och numera finns det modeller som kan generera bilder av hög realistisk karaktär. Som ett steg framåt i forskningen har arkitekturen adopterats till nya domäner, och den här studien syftar till att undersöka dess förmåga att syntatisera finansiell tabelldata. I studien undersöks en framträdande modell inom forskningsfältet, CTGAN, tillsammans med två föreslagna idéer i syfte att förbättra dess generativa förmåga. Resultaten indikerar att en förändrad träningsdynamik och en ny optimeringsstrategi förbättrar arkitekturens förmåga att generera syntetisk data. Den genererade datan håller i sin tur hög kvalité med tydliga influenser från dess underliggande dataset, och resultat på efterföljande analyser mellan datakällorna är av jämförbar karaktär. Slutsatsen är således att GANs har stor potential att generera tabulär data som kan betrakatas som substitut till känslig data, vilket möjliggör för en mer frikostig delningspolitik av data inom organisationer.
7
Sargent, Garrett Craig. "A Conditional Generative Adversarial Network Demosaicing Strategy for Division of Focal Plane Polarimeters." University of Dayton / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1606050550958383.
Full text
8
Zou, Xiaozhou. "Improve the Convergence Speed and Stability of Generative Adversarial Networks." Digital WPI, 2018. https://digitalcommons.wpi.edu/etd-theses/1309.
Full textAbstract:
In this thesis, we address two major problems in Generative Adversarial Networks (GAN), an important sub-field in deep learning. The first problem that we address is the instability in the training process that happens in many real-world problems and the second problem that we address is the lack of a good evaluation metric for the performance of GAN algorithms. To understand and address the first problem, three approaches are developed. Namely, we introduce randomness to the training process; we investigate various normalization methods; most importantly we develop a better parameter initialization strategy to help stabilize training. In the randomness techniques part of the thesis, we developed two randomness approaches, namely the addition of gradient noise and the batch random flipping of the results from the discrimination section of a GAN. In the normalization part of the thesis, we compared the performances of the z-score transform, the min-max normalization, affine transformations and batch normalization. In the most novel and important part of this thesis, we developed techniques to initialize the GAN generator section with parameters that can produce a uniform distribution on the range of the training data. As far as we are aware, this seemingly simple idea has not yet appeared in the extant literature, and the empirical results we obtain on 2-dimensional synthetic data show marked improvement. As to better evaluation metrics, we demonstrate a simple yet effective way to evaluate the effectiveness of the generator using a novel "overlap loss".
9
Waldow, Walter E. "An Adversarial Framework for Deep 3D Target Template Generation." Wright State University / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=wright1597334881614898.
Full text
10
Birgersson, Anna, and Klara Hellgren. "Texture Enhancement in 3D Maps using Generative Adversarial Networks." Thesis, Linköpings universitet, Datorseende, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-162446.
Full textAbstract:
In this thesis we investigate the use of GANs for texture enhancement. To achievethis, we have studied if synthetic satellite images generated by GANs will improvethe texture in satellite-based 3D maps. We investigate two GANs; SRGAN and pix2pix. SRGAN increases the pixelresolution of the satellite images by generating upsampled images from low resolutionimages. As for pip2pix, the GAN performs image-to-image translation bytranslating a source image to a target image, without changing the pixel resolution. We trained the GANs in two different approaches, named SAT-to-AER andSAT-to-AER-3D, where SAT, AER and AER-3D are different datasets provided bythe company Vricon. In the first approach, aerial images were used as groundtruth and in the second approach, rendered images from an aerial-based 3D mapwere used as ground truth. The procedure of enhancing the texture in a satellite-based 3D map was dividedin two steps; the generation of synthetic satellite images and the re-texturingof the 3D map. Synthetic satellite images generated by two SRGAN models andone pix2pix model were used for the re-texturing. The best results were presentedusing SRGAN in the SAT-to-AER approach, in where the re-textured 3Dmap had enhanced structures and an increased perceived quality. SRGAN alsopresented a good result in the SAT-to-AER-3D approach, where the re-textured3D map had changed color distribution and the road markers were easier to distinguishfrom the ground. The images generated by the pix2pix model presentedthe worst result. As for the SAT-to-AER approach, even though the syntheticsatellite images generated by pix2pix were somewhat enhanced and containedless noise, they had no significant impact in the re-texturing. In the SAT-to-AER-3D approach, none of the investigated models based on the pix2pix frameworkpresented any successful results. We concluded that GANs can be used as a texture enhancer using both aerialimages and images rendered from an aerial-based 3D map as ground truth. Theuse of GANs as a texture enhancer have great potential and have several interestingareas for future works.
11
Karlsson, Anton, and Torbjörn Sjöberg. "Synthesis of Tabular Financial Data using Generative Adversarial Networks." Thesis, KTH, Matematisk statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-273633.
Full textAbstract:
Digitalization has led to tons of available customer data and possibilities for data-driven innovation. However, the data needs to be handled carefully to protect the privacy of the customers. Generative Adversarial Networks (GANs) are a promising recent development in generative modeling. They can be used to create synthetic data which facilitate analysis while ensuring that customer privacy is maintained. Prior research on GANs has shown impressive results on image data. In this thesis, we investigate the viability of using GANs within the financial industry. We investigate two state-of-the-art GAN models for synthesizing tabular data, TGAN and CTGAN, along with a simpler GAN model that we call WGAN. A comprehensive evaluation framework is developed to facilitate comparison of the synthetic datasets. The results indicate that GANs are able to generate quality synthetic datasets that preserve the statistical properties of the underlying data and enable a viable and reproducible subsequent analysis. It was however found that all of the investigated models had problems with reproducing numerical data.<br>Digitaliseringen har fört med sig stora mängder tillgänglig kunddata och skapat möjligheter för datadriven innovation. För att skydda kundernas integritet måste dock uppgifterna hanteras varsamt. Generativa Motstidande Nätverk (GANs) är en ny lovande utveckling inom generativ modellering. De kan användas till att syntetisera data som underlättar dataanalys samt bevarar kundernas integritet. Tidigare forskning på GANs har visat lovande resultat på bilddata. I det här examensarbetet undersöker vi gångbarheten av GANs inom finansbranchen. Vi undersöker två framstående GANs designade för att syntetisera tabelldata, TGAN och CTGAN, samt en enklare GAN modell som vi kallar för WGAN. Ett omfattande ramverk för att utvärdera syntetiska dataset utvecklas för att möjliggöra jämförelse mellan olika GANs. Resultaten indikerar att GANs klarar av att syntetisera högkvalitativa dataset som bevarar de statistiska egenskaperna hos det underliggande datat, vilket möjliggör en gångbar och reproducerbar efterföljande analys. Alla modellerna som testades uppvisade dock problem med att återskapa numerisk data.
12
Evholt, David, and Oscar Larsson. "Generative Adversarial Networks and Natural Language Processing for Macroeconomic Forecasting." Thesis, KTH, Matematisk statistik, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-273422.
Full textAbstract:
Macroeconomic forecasting is a classic problem, today most often modeled using time series analysis. Few attempts have been made using machine learning methods, and even fewer incorporating unconventional data, such as that from social media. In this thesis, a Generative Adversarial Network (GAN) is used to predict U.S. unemployment, beating the ARIMA benchmark on all horizons. Furthermore, attempts at using Twitter data and the Natural Language Processing (NLP) model DistilBERT are performed. While these attempts do not beat the benchmark, they do show promising results with predictive power. The models are also tested at predicting the U.S. stock index S&P 500. For these models, the Twitter data does improve the accuracy and shows the potential of social media data when predicting a more erratic index with less seasonality that is more responsive to current trends in public discourse. The results also show that Twitter data can be used to predict trends in both unemployment and the S&P 500 index. This sets the stage for further research into NLP-GAN models for macroeconomic predictions using social media data.<br>Makroekonomiska prognoser är sedan länge en svår utmaning. Idag löses de oftast med tidsserieanalys och få försök har gjorts med maskininlärning. I denna uppsats används ett generativt motstridande nätverk (GAN) för att förutspå amerikansk arbetslöshet, med resultat som slår samtliga riktmärken satta av en ARIMA. Ett försök görs också till att använda data från Twitter och den datorlingvistiska (NLP) modellen DistilBERT. Dessa modeller slår inte riktmärkena men visar lovande resultat. Modellerna testas vidare på det amerikanska börsindexet S&P 500. För dessa modeller förbättrade Twitterdata resultaten vilket visar på den potential data från sociala medier har när de appliceras på mer oregelbunda index, utan tydligt säsongsberoende och som är mer känsliga för trender i det offentliga samtalet. Resultaten visar på att Twitterdata kan användas för att hitta trender i både amerikansk arbetslöshet och S&P 500 indexet. Detta lägger grunden för fortsatt forskning inom NLP-GAN modeller för makroekonomiska prognoser baserade på data från sociala medier.
13
Jonsson, Jacob. "Cooperative versus Adversarial Learning: Generating Political Text." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-241440.
Full textAbstract:
This thesis aims to evaluate the current state of the art for unconditional text generation and compare established models with novel approaches in the task of generating texts, after being trained on texts written by political parties from the Swedish Riksdag. First, the progression of language modeling from n-gram models and statistical models to neural network models is presented. This is followed by theoretical arguments for the development of adversarial training methods,where a generator neural network tries to fool a discriminator network, trained to distinguish between real and generated sentences. One of the methods in the research frontier diverges from the adversarial idea and instead uses cooperative training, where a mediator network is trained instead of a discriminator. The mediator is then used to estimate a symmetric divergence measure between the true distribution and the generator’s distribution, which is to be minimized in training. A set of experiments evaluates the performance of cooperative training and adversarial training, and finds that they both have advantages and disadvantages. In the experiments, the adversarial training increases the quality of generated texts, while the cooperative training increases the diversity. The findings are in line with the theoretical expectation.<br>Denna uppsats utvärderar några nyligen föreslagna metoder för obetingad textgenerering, baserade på s.k. “Generative Adversarial Networks” (GANs). Den jämför etablerade modeller med nya metoder för att generera text, efter att ha tränats på texter från de svenska Riksdagspartierna. Utvecklingen av språkmodellering från n-gram-modeller och statistiska modeller till modeller av neurala nätverk presenteras. Detta följs upp av teoretiska argument för utvecklingen av GANs, för vilka ett generatornätverk försöker överlista ett diskriminatornätverk, som tränas skilja mellan riktiga och genererade meningar. En av de senaste metoderna avviker från detta angreppssätt och introducerar istället kooperativ träning, där ett mediatornätverk tränas istället för en diskriminator. Mediatorn används sedan till att uppskatta ett symmetriskt divergensmått mellan den sanna distributionen och generatorns distribution, vilket träningen syftar till att minimera. En serie experiment utvärderar hur GANs och kooperativ träning presterar i förhållande till varandra, och finner att de båda har för- och nackdelar. I experimenten ökar GANs kvaliteten på texterna som genereras, medan kooperativ träning ökar mångfalden. Resultaten motsvarar vad som kan förväntas teoretiskt.
14
Gustafsson, Fredrik. "Unsupervised Image Enhancement Using Generative Adversarial Networks : An attempt at real-time video enhancement." Thesis, Uppsala universitet, Avdelningen för visuell information och interaktion, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:uu:diva-446698.
Full textAbstract:
As the world has become more connected meetings have moved online. However, since few have access to studio lighting and uses the embedded webcam the video quality can be far from good. Hence, there is an interest in using a software solution to enhance the video quality in real time. This thesis investigates the feasibility to train a machine learning model to automatically enhance the quality of images. The model must learn without using paired images, since it is difficult to capture images with the exact same content but different quality. Furthermore, the model has to process at least 30 images per second which is a common frequency for videos. Therefore, this thesis investigates the possibility to train a model without paired images and whether such a model can be used in real-time. To answer these questions several sizes of the same model was trained. These were evaluated using six different measures during in order to determine if training without paired data is possible. The models image enhancement capabilities and inference speed were investigated followed by attempts at improving the speed. Finally, different combinations of datasets were investigated to test how well the model generalised to new data. The results show that it is possible to train models for image enhancement without paired data. However, to use such a model in real time a graphics card is needed to reach above 30 images per second.
15
Berglöf, Olle, and Adam Jacobs. "Effects of Transfer Learning on Data Augmentation with Generative Adversarial Networks." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-259485.
Full textAbstract:
Data augmentation is a technique that acquires more training data by augmenting available samples, where the training data is used to fit model parameters. Data augmentation is utilized due to a shortage of training data in certain domains and to reduce overfitting. Augmenting a training dataset for image classification with a Generative Adversarial Network (GAN) has been shown to increase classification accuracy. This report investigates if transfer learning within a GAN can further increase classification accuracy when utilizing the augmented training dataset. The method section describes a specific GAN architecture for the experiments that includes a label condition. When using transfer learning within the specific GAN architecture, a statistical analysis shows a statistically significant increase in classification accuracy for a classification problem with the EMNIST dataset, which consists of images of handwritten alphanumeric characters. In the discussion section, the authors analyze the results and motivates other use cases for the proposed GAN architecture.<br>Datautökning är en metod som skapar mer träningsdata genom att utöka befintlig träningsdata, där träningsdatan används för att anpassa modellers parametrar. Datautökning används på grund av en brist på träningsdata inom vissa områden samt för att minska overfitting. Att utöka ett träningsdataset för att genomföra bildklassificering med ett generativt adversarialt nätverk (GAN) har visats kunna öka precisionen av klassificering av bilder. Denna rapport undersöker om transferlärande inom en GAN kan vidare öka klassificeringsprecisionen när ett utökat träningsdataset används. Metoden beskriver en specific GANarkitektur som innehåller ett etikettvillkor. När transferlärande används inom den utvalda GAN-arkitekturen visar en statistisk analys en statistiskt säkerställd ökning av klassificeringsprecisionen för ett klassificeringsproblem med EMNIST datasetet, som innehåller bilder på handskrivna bokstäver och siffror. I diskussionen diskuteras orsakerna bakom resultaten och fler användningsområden nämns.
16
Adhikari, Aakriti. "Skin Cancer Detection using Generative Adversarial Networkand an Ensemble of deep Convolutional Neural Networks." University of Toledo / OhioLINK, 2019. http://rave.ohiolink.edu/etdc/view?acc_num=toledo1574383625473665.
Full text
17
Bak, Adam. "Simulace projevu kožního onemocnění s využitím GAN." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2021. http://www.nusl.cz/ntk/nusl-445569.
Full textAbstract:
Cieľom tejto diplomovej práce je vygenerovanie datasetu syntetických snímkov odtlačkov prstov, ktoré vykazujú známky kožných ochorení. Práca sa zaoberá poškodením spôsobeným kožnými ochoreniami v odtlačkoch prstov a generovaním syntetických odtlačkov prstov. Odtlačky prstov s prejavom kožných ochorení boli generované s využitím modelu založeného na Wasserstein GAN s penalizáciou gradientu. Na trénovanie GAN modelu bola použitá unikátna databáza odtlačkov prstov s prejavom kožných ochorení vytvorená na FIT VUT. Daný model bol trénovaný na troch typoch kožných ochorení: atopický ekzém, psoriáza a dyshidrotický ekzém. Sieť generátoru z natrénovaného WGAN-GP modelu bola použitá na vygenerovanie datasetov syntetických odtlačkov prstov. Tieto syntetické odtlačky boli porovnané s reálnymi odtlačkami s využitím NFIQ a FiQiVi nástrojov na určenie kvality spoločne s porovnaním rozložení lokácií a orientácii markantov v snímkoch odtlačkov prstov.
18
Albertazzi, Riccardo. "A study on the application of generative adversarial networks to industrial OCR." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2018.
Find full textAbstract:
High performance and nearly perfect accuracy are the standards required by OCR algorithms for industrial applications. In the last years research on Deep Learning has proven that Convolutional Neural Networks (CNNs) are a very powerful and robust tool for image analysis and classification; when applied to OCR tasks, CNNs are able to perform much better than previously adopted techniques and reach easily 99% accuracy.
However, Deep Learning models' effectiveness relies on the quality of the data used to train them; this can become a problem since OCR tools can run for months without interruption, and during this period unpredictable variations (printer errors, background modifications, light conditions) could affect the accuracy of the trained system. We cannot expect that the final user who trains the tool will take thousands of training pictures under different conditions until all imaginable variations have been captured; we then have to be able to generate these variations programmatically.
Generative Adversarial Networks (GANs) are a recent breakthrough in machine learning; these networks are able to learn the distribution of the input data and therefore generate realistic samples belonging to that distribution. This thesis' objective is learning how GANs work in detail and perform experiments on generative models that allow to create unseen variations of OCR training characters, thus allowing the whole OCR system to be more robust to future character variations.
19
Gehlin, Nils, and Martin Antonsson. "Detecting Non-Natural Objects in a Natural Environment using Generative Adversarial Networks with Stereo Data." Thesis, Linköpings universitet, Datorseende, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166619.
Full textAbstract:
This thesis investigates the use of Generative Adversarial Networks (GANs) for detecting images containing non-natural objects in natural environments and if the introduction of stereo data can improve the performance. The state-of-the-art GAN-based anomaly detection method presented by A. Berget al. in [5] (BergGAN) was the base of this thesis. By modifiying BergGAN to not only accept three channel input, but also four and six channel input, it was possible to investigate the effect of introducing stereo data in the method. The input to the four channel network was an RGB image and its corresponding disparity map, and the input to the six channel network was a stereo pair consistingof two RGB images. The three datasets used in the thesis were constructed froma dataset of aerial video sequences provided by SAAB Dynamics, where the scene was mostly wooded areas. The datasets were divided into training and validation data, where the latter was used for the performance evaluation of the respective network. The evaluation method suggested in [5] was used in the thesis, where each sample was scored on the likelihood of it containing anomalies, Receiver Operating Characteristics (ROC) analysis was then applied and the area under the ROC-curve was calculated. The results showed that BergGAN was successfully able to detect images containing non-natural objects in natural environments using the dataset provided by SAAB Dynamics. The adaption of BergGAN to also accept four and six input channels increased the performance of the method, showing that there is information in stereo data that is relevant for GAN-based anomaly detection. There was however no substantial performance difference between the network trained with two RGB images versus the one trained with an RGB image and its corresponding disparity map.
20
Marriott, Richard. "Data-augmentation with synthetic identities for robust facial recognition." Thesis, Lyon, 2020. http://www.theses.fr/2020LYSEC048.
Full textAbstract:
En 2014, l'utilisation des réseaux neuronaux profonds (RNP) a révolutionné la reconnaissance faciale (RF). Les RNP sont capables d'apprendre à extraire des images des représentations basées sur des caractéristiques qui sont discriminantes et robustes aux détails non pertinents. On peut dire que l'un des facteurs les plus importants qui limitent aujourd'hui les performances des algorithmes de RF sont les données utilisées pour les entraîner. Les ensembles de données d'images de haute qualité qui sont représentatives des conditions de test du monde réel peuvent être difficiles à collecter. Une solution possible est d'augmenter les ensembles de données avec des images synthétiques. Cette option est récemment devenue plus viable suite au développement des « generative adversarial networks » (GAN) qui permettent de générer des échantillons de données synthétiques très réalistes. Cette thèse étudie l'utilisation des GAN pour augmenter les ensembles de données FR. Elle examine la capacité des GAN à générer de nouvelles identités, et leur capacité à démêler l'identité des autres formes de variation des images. Enfin, un GAN intégrant un modèle 3D est proposé afin de démêler complètement la pose de l'identité. Il est démontré que les images synthétisées à l'aide du GAN 3D améliorent la reconnaissance des visages aux poses larges et une précision état de l'art est démontrée pour l'ensemble de données d'évaluation ``Cross-Pose LFW''.Le dernier chapitre de la thèse évalue l'une des utilisations plus néfastes des images synthétiques : l'attaque par morphing du visage. Ces attaques exploitent l'imprécision des systèmes de RF en manipulant les images de manière à ce qu'il puisse être faussement vérifié qu'elles appartiennent à plus d'une personne. Une évaluation des attaques par morphing de visage basées sur le GAN est fournie. Une nouvelle méthode de morphing basée sur le GAN est également présentée, qui minimise la distance entre l'image transformée et les identités originales dans un espace de caractéristiques biométriques. Une contre-mesure potentielle à ces attaques par morphing consiste à entraîner les réseaux FR en utilisant des identités synthétiques supplémentaires. Dans cette veine, l'effet de l'entraînement utilisant des données synthétiques GAN 3D sur le succès des attaques simulées de morphing facial est évalué<br>In 2014, use of deep neural networks (DNNs) revolutionised facial recognition (FR). DNNs are capable of learning to extract feature-based representations from images that are discriminative and robust to extraneous detail. Arguably, one of the most important factors now limiting the performance of FR algorithms is the data used to train them. High-quality image datasets that are representative of real-world test conditions can be difficult to collect. One potential solution is to augment datasets with synthetic images. This option recently became increasingly viable following the development of generative adversarial networks (GANs) which allow generation of highly realistic, synthetic data samples. This thesis investigates the use of GANs for augmentation of FR datasets. It looks at the ability of GANs to generate new identities, and their ability to disentangle identity from other forms of variation in images. Ultimately, a GAN integrating a 3D model is proposed in order to fully disentangle pose from identity. Images synthesised using the 3D GAN are shown to improve large-pose FR and a state-of-the-art accuracy is demonstrated for the challenging Cross-Pose LFW evaluation dataset.The final chapter of the thesis evaluates one of the more nefarious uses of synthetic images: the face-morphing attack. Such attacks exploit imprecision in FR systems by manipulating images such that they might be falsely verified as belonging to more than one person. An evaluation of GAN-based face-morphing attacks is provided. Also introduced is a novel, GAN-based morphing method that minimises the distance of the morphed image from the original identities in a biometric feature-space. A potential counter measure to such morphing attacks is to train FR networks using additional, synthetic identities. In this vein, the effect of training using synthetic, 3D GAN data on the success of simulated face-morphing attacks is evaluated
21
Käll, Viktor, and Erik Piscator. "Particle Filter Bridge Interpolation in GANs." Thesis, KTH, Matematisk statistik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301733.
Full textAbstract:
Generative adversarial networks (GANs), a type of generative modeling framework, has received much attention in the past few years since they were discovered for their capacity to recover complex high-dimensional data distributions. These provide a compressed representation of the data where all but the essential features of a sample is extracted, subsequently inducing a similarity measure on the space of data. This similarity measure gives rise to the possibility of interpolating in the data which has been done successfully in the past. Herein we propose a new stochastic interpolation method for GANs where the interpolation is forced to adhere to the data distribution by implementing a sequential Monte Carlo algorithm for data sampling. The results show that the new method outperforms previously known interpolation methods for the data set LINES; compared to the results of other interpolation methods there was a significant improvement measured through quantitative and qualitative evaluations. The developed interpolation method has met its expectations and shown promise, however it needs to be tested on a more complex data set in order to verify that it also scales well.<br>Generative adversarial networks (GANs) är ett slags generativ modell som har fått mycket uppmärksamhet de senaste åren sedan de upptäcktes för sin potential att återskapa komplexa högdimensionella datafördelningar. Dessa förser en komprimerad representation av datan där enbart de karaktäriserande egenskaperna är bevarade, vilket följdaktligen inducerar ett avståndsmått på datarummet. Detta avståndsmått möjliggör interpolering inom datan vilket har åstadkommits med framgång tidigare. Häri föreslår vi en ny stokastisk interpoleringsmetod för GANs där interpolationen tvingas följa datafördelningen genom att implementera en sekventiell Monte Carlo algoritm för dragning av datapunkter. Resultaten för studien visar att metoden ger bättre interpolationer för datamängden LINES som användes; jämfört med resultaten av tidigare kända interpolationsmetoder syntes en märkbar förbättring genom kvalitativa och kvantitativa utvärderingar. Den framtagna interpolationsmetoden har alltså mött förväntningarna och är lovande, emellertid fordras att den testas på en mer komplex datamängd för att bekräfta att den fungerar väl även under mer generella förhållanden.
22
Šagát, Martin. "Návrh generativní kompetitivní neuronové sítě pro generování umělých EKG záznamů." Master's thesis, Vysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií, 2020. http://www.nusl.cz/ntk/nusl-413114.
Full textAbstract:
The work deals with the generation of ECG signals using generative adversarial networks (GAN). It examines in detail the basics of artificial neural networks and the principles of their operation. It theoretically describes the use and operation and the most common types of failures of generative adversarial networks. In this work, a general procedure of signal preprocessing suitable for GAN training was derived, which was used to compile a database. In this work, a total of 3 different GAN models were designed and implemented. The results of the models were visually displayed and analyzed in detail. Finally, the work comments on the achieved results and suggests further research direction of methods dealing with the generation of ECG signals.
23
Schilling, Lennart. "Generating synthetic brain MR images using a hybrid combination of Noise-to-Image and Image-to-Image GANs." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166034.
Full textAbstract:
Generative Adversarial Networks (GANs) have attracted much attention because of their ability to learn high-dimensional, realistic data distributions. In the field of medical imaging, they can be used to augment the often small image sets available. In this way, for example, the training of image classification or segmentation models can be improved to support clinical decision making. GANs can be distinguished according to their input. While Noise-to-Image GANs synthesize new images from a random noise vector, Image-To-Image GANs translate a given image into another domain. In this study, it is investigated if the performance of a Noise-To-Image GAN, defined by its generated output quality and diversity, can be improved by using elements of a previously trained Image-To-Image GAN within its training. The data used consists of paired T1- and T2-weighted MR brain images. With the objective of generating additional T1-weighted images, a hybrid model (Hybrid GAN) is implemented that combines elements of a Deep Convolutional GAN (DCGAN) as a Noise-To-Image GAN and a Pix2Pix as an Image-To-Image GAN. Thereby, starting from the dependency of an input image, the model is gradually converted into a Noise-to-Image GAN. Performance is evaluated by the use of an independent classifier that estimates the divergence between the generative output distribution and the real data distribution. When comparing the Hybrid GAN performance with the DCGAN baseline, no improvement, neither in the quality nor in the diversity of the generated images, could be observed. Consequently, it could not be shown that the performance of a Noise-To-Image GAN is improved by using elements of a previously trained Image-To-Image GAN within its training.
24
Chowdhury, Muhammad Iqbal Hasan. "Question-answering on image/video content." Thesis, Queensland University of Technology, 2020. https://eprints.qut.edu.au/205096/1/Muhammad%20Iqbal%20Hasan_Chowdhury_Thesis.pdf.
Full textAbstract:
This thesis explores a computer's ability to understand multimodal data where the correspondence between image/video content and natural language text are utilised to answer open-ended natural language questions through question-answering tasks. Static image data consisting of both indoor and outdoor scenes, where complex textual questions are arbitrarily posed to a machine to generate correct answers, was examined. Dynamic videos consisting of both single-camera and multi-camera settings for the exploration of more challenging and unconstrained question-answering tasks were also considered. In exploring these challenges, new deep learning processes were developed to improve a computer's ability to understand and consider multimodal data.
25
Xu, Libo. "GAN-based Automatic Segmentation of Thoracic Aorta from Non-contrast-Enhanced CT Images." Thesis, KTH, Skolan för kemi, bioteknologi och hälsa (CBH), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-295428.
Full textAbstract:
The deep learning-based automatic segmentation methods have developed rapidly in recent years to give a promising performance in the medical image segmentation tasks, which provide clinical medicine with an accurate and fast computer-aided diagnosis method. Generative adversarial networks and their extended frameworks have achieved encouraging results on image-to-image translation problems. In this report, the proposed hybrid network combined cycle-consistent adversarial networks, which transformed contrast-enhanced images from computed tomography angiography to the conventional low-contrast CT scans, with the segmentation network and trained them simultaneously in an end-to-end manner. The trained segmentation network was tested on the non-contrast-enhanced CT images. The synthetic process and the segmentation process were also implemented in a two-stage manner. The two-stage process achieved a higher Dice similarity coefficient than the baseline U-Net did on test data, but the proposed hybrid network did not outperform the baseline due to the field of view difference between the two training data sets.
26
Hermansson, Adam, and Stefan Generalao. "Interpretable Superhuman Machine Learning Systems: An explorative study focusing on interpretability and detecting Unknown Knowns using GAN." Thesis, Malmö universitet, Fakulteten för teknik och samhälle (TS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20857.
Full textAbstract:
I en framtid där förutsägelser och beslut som tas av maskininlärningssystem överträffar människors förmåga behöver systemen att vara tolkbara för att vi skall kunna lita på och förstå dem. Vår studie utforskar världen av tolkbar maskininlärning genom att designa och undersöka artefakter. Vi genomför experiment för att utforska förklarbarhet, tolkbarhet samt tekniska utmaningar att skapa maskininlärningsmodeller för att identifiera liknande men unika objekt. Slutligen genomför vi ett användartest för att utvärdera toppmoderna förklaringsverktyg i ett direkt mänskligt sammanhang. Med insikter från dessa experiment diskuterar vi den potentiella framtiden för detta fält<br>In a future where predictions and decisions made by machine learning systems outperform humans we need the systems to be interpretable in order for us to trust and understand them. Our study explore the realm of interpretable machine learning through designing artifacts. We conduct experiments to explore explainability, interpretability as well as technical challenges of creating machine learning models to identify objects that appear similar to humans. Lastly, we conduct a user test to evaluate current state-of-the-art visual explanatory tools in a human setting. From these insights, we discuss the potential future of this field.
27
Pakdaman, Hesam. "Updating the generator in PPGN-h with gradients flowing through the encoder." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-224867.
Full textAbstract:
The Generative Adversarial Network framework has shown success in implicitly modeling data distributions and is able to generate realistic samples. Its architecture is comprised of a generator, which produces fake data that superficially seem to belong to the real data distribution, and a discriminator which is to distinguish fake from genuine samples. The Noiseless Joint Plug & Play model offers an extension to the framework by simultaneously training autoencoders. This model uses a pre-trained encoder as a feature extractor, feeding the generator with global information. Using the Plug & Play network as baseline, we design a new model by adding discriminators to the Plug & Play architecture. These additional discriminators are trained to discern real and fake latent codes, which are the output of the encoder using genuine and generated inputs, respectively. We proceed to investigate whether this approach is viable. Experiments conducted for the MNIST manifold show that this indeed is the case.<br>Generative Adversarial Network är ett ramverk vilket implicit modellerar en datamängds sannolikhetsfördelning och är kapabel till att producera realistisk exempel. Dess arkitektur utgörs av en generator, vilken kan fabricera datapunkter liggandes nära den verkliga sannolikhetsfördelning, och en diskriminator vars syfte är att urskilja oäkta punkter från genuina. Noiseless Joint Plug & Play modellen är en vidareutveckling av ramverket som samtidigt tränar autoencoders. Denna modell använder sig utav en inlärd enkoder som förser generatorn med data. Genom att använda Plug & Play modellen som referens, skapar vi en ny modell genom att addera diskriminatorer till Plug & Play architekturen. Dessa diskriminatorer är tränade att särskilja genuina och falska latenta koder, vilka har producerats av enkodern genom att ha använt genuina och oäkta datapunkter som inputs. Vi undersöker huruvida denna metod är gynnsam. Experiment utförda för MNIST datamängden visar att så är fallet.
28
Lai, Matteo. "Conditional MR image synthesis with Auxiliary Progressive Growing GANs." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2022.
Find full textAbstract:
L'addestramento di algotritmi di deep learning (DL) richiede una grande quantità di dati, che però spesso non sono disponibili in ambito medico. In questa tesi viene proposto un modello per la generazione di dataset sintetici etichettati nell'ambito dell'imaging medico ad alta risoluzione. Dopo aver presentato vantaggi e limiti dell'uso delle tecniche di DL in radiologia, vengono proposte le Generative Adversarial Networks (GANs) come possibile soluzione per superare tali limiti. Illustrando lo stato dell'arte relativo alle GAN, viene focalizzata l'attenzione sulle Progressive Growing GAN, capaci di generare immagini ad alta risoluzione, e sulle Auxiliary Classifier GAN (ACGAN), capaci di generare immagini target.
Sulla base di questi modelli, vengono proposte le innovative Progressive ACGAN (PACGAN), progettate per generare immagini target ad elevata risoluzione. L'obiettivo di questo lavoro di tesi è sfruttare la capacità delle GAN di creare una rappresentazione nello spazio latente dei dati del training set, sia per generare immagini target ad alta risoluzione (256 x 256), che per effettuare una classificazione. Il modello proposto viene testato su un dataset contenente 200 immagini di risonanza magnetica (RM) cerebrale di soggetti sani e pazienti con malattia di Alzheimer.
I risultati del modello sono molto promettenti.
La qualità delle immagini generate è stata valutata sia visivamente che quantitativamente, tramite FID (Fréchet Inception Distance) e MS-SSIM (Multi-Scale Structural Similarity Index), evidenziando una maggiore capacità delle PACGAN di rappresentare immagini target ad alta risoluzione rispetto alle ACGAN. Le performance di classificazione risultano ottime nel training set, con discreta capacità di generalizzare su nuovi dati.
Il modello proposto consente quindi di generare immagini target ad alta risoluzione che possono essere usate per ottenere dataset sintetici.
29
Karlík, Pavol. "Odstraňování šumu pomocí neuronových sítí s cyklickou konzistencí." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2020. http://www.nusl.cz/ntk/nusl-417289.
Full textAbstract:
Hlboké neurónové siete sa bežne používajú v oblasti odstraňovania šumu. Trénovací proces neurónovej siete je možné rožšíriť využitím druhej neurónovej siete, ktorej cieľom je vložiť šum do čistej rečovej nahrávky. Tieto dve siete sa môžu spolu využiť k rekonštrukcii pôvodných čistých a zašumených nahrávok. Táto práca skúma efektivitu tejto techniky, zvanej cyklická konzistencia. Cyklická konzistencia zlepšuje robustnosť neurónovej siete bez toho, aby sa daná sieť akokoľvek modifikovala, nakoľko vystavuje sieť na odstraňovanie šumu rôznorodejšiemu množstvu zašumených dát. Avšak, táto technika vyžaduje trénovacie dáta skladajúce sa z párov vstupných a referenčných nahrávok. Tieto dáta niesu vždy dostupné. Na trénovanie modelov s nepárovanými dátami využívame generatívne neurónové siete s cyklickou konzistenciou. V tejto práci sme vykonali veľké množstvo experimentov s modelmi trénovanými na párovaných a nepárovaných dátach. Naše výsledky ukazujú, že využitie cyklickej konzistencie výrazne zlepšuje výkonnosť modelov.
30
Nilsson, Alexander, and Martin Thönners. "A Framework for Generative Product Design Powered by Deep Learning and Artificial Intelligence : Applied on Everyday Products." Thesis, Linköpings universitet, Maskinkonstruktion, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-149454.
Full textAbstract:
In this master’s thesis we explore the idea of using artificial intelligence in the product design process and seek to develop a conceptual framework for how it can be incorporated to make user customized products more accessible and affordable for everyone. We show how generative deep learning models such as Variational Auto Encoders and Generative Adversarial Networks can be implemented to generate design variations of windows and clarify the general implementation process along with insights from recent research in the field. The proposed framework consists of three parts: (1) A morphological matrix connecting several identified possibilities of implementation to specific parts of the product design process. (2) A general step-by-step process on how to incorporate generative deep learning. (3) A description of common challenges, strategies andsolutions related to the implementation process. Together with the framework we also provide a system for automatic gathering and cleaning of image data as well as a dataset containing 4564 images of windows in a front view perspective.
31
Kola, Ramya Sree. "Generation of synthetic plant images using deep learning architecture." Thesis, Blekinge Tekniska Högskola, Institutionen för datavetenskap, 2019. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-18450.
Full textAbstract:
Background: Generative Adversarial Networks (Goodfellow et al., 2014) (GANs)are the current state of the art machine learning data generating systems. Designed with two neural networks in the initial architecture proposal, generator and discriminator. These neural networks compete in a zero-sum game technique, to generate data having realistic properties inseparable to that of original datasets. GANs have interesting applications in various domains like Image synthesis, 3D object generation in gaming industry, fake music generation(Dong et al.), text to image synthesis and many more. Despite having a widespread application domains, GANs are popular for image data synthesis. Various architectures have been developed for image synthesis evolving from fuzzy images of digits to photorealistic images. Objectives: In this research work, we study various literature on different GAN architectures. To understand significant works done essentially to improve the GAN architectures. The primary objective of this research work is synthesis of plant images using Style GAN (Karras, Laine and Aila, 2018) variant of GAN using style transfer. The research also focuses on identifying various machine learning performance evaluation metrics that can be used to measure Style GAN model for the generated image datasets. Methods: A mixed method approach is used in this research. We review various literature work on GANs and elaborate in detail how each GAN networks are designed and how they evolved over the base architecture. We then study the style GAN (Karras, Laine and Aila, 2018a) design details. We then study related literature works on GAN model performance evaluation and measure the quality of generated image datasets. We conduct an experiment to implement the Style based GAN on leaf dataset(Kumar et al., 2012) to generate leaf images that are similar to the ground truth. We describe in detail various steps in the experiment like data collection, preprocessing, training and configuration. Also, we evaluate the performance of Style GAN training model on the leaf dataset. Results: We present the results of literature review and the conducted experiment to address the research questions. We review and elaborate various GAN architecture and their key contributions. We also review numerous qualitative and quantitative evaluation metrics to measure the performance of a GAN architecture. We then present the generated synthetic data samples from the Style based GAN learning model at various training GPU hours and the latest synthetic data sample after training for around ~8 GPU days on leafsnap dataset (Kumar et al., 2012). The results we present have a decent quality to expand the dataset for most of the tested samples. We then visualize the model performance by tensorboard graphs and an overall computational graph for the learning model. We calculate the Fréchet Inception Distance score for our leaf Style GAN and is observed to be 26.4268 (the lower the better). Conclusion: We conclude the research work with an overall review of sections in the paper. The generated fake samples are much similar to the input ground truth and appear to be convincingly realistic for a human visual judgement. However, the calculated FID score to measure the performance of the leaf StyleGAN accumulates a large value compared to that of Style GANs original celebrity HD faces image data set. We attempted to analyze the reasons for this large score.
32
Nilsson, Mårten. "Augmenting High-Dimensional Data with Deep Generative Models." Thesis, KTH, Robotik, perception och lärande, RPL, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-233969.
Full textAbstract:
Data augmentation is a technique that can be performed in various ways to improve the training of discriminative models. The recent developments in deep generative models offer new ways of augmenting existing data sets. In this thesis, a framework for augmenting annotated data sets with deep generative models is proposed together with a method for quantitatively evaluating the quality of the generated data sets. Using this framework, two data sets for pupil localization was generated with different generative models, including both well-established models and a novel model proposed for this purpose. The unique model was shown both qualitatively and quantitatively to generate the best data sets. A set of smaller experiments on standard data sets also revealed cases where this generative model could improve the performance of an existing discriminative model. The results indicate that generative models can be used to augment or replace existing data sets when training discriminative models.<br>Dataaugmentering är en teknik som kan utföras på flera sätt för att förbättra träningen av diskriminativa modeller. De senaste framgångarna inom djupa generativa modeller har öppnat upp nya sätt att augmentera existerande dataset. I detta arbete har ett ramverk för augmentering av annoterade dataset med hjälp av djupa generativa modeller föreslagits. Utöver detta så har en metod för kvantitativ evaulering av kvaliteten hos genererade data set tagits fram. Med hjälp av detta ramverk har två dataset för pupillokalisering genererats med olika generativa modeller. Både väletablerade modeller och en ny modell utvecklad för detta syfte har testats. Den unika modellen visades både kvalitativt och kvantitativt att den genererade de bästa dataseten. Ett antal mindre experiment på standardiserade dataset visade exempel på fall där denna generativa modell kunde förbättra prestandan hos en existerande diskriminativ modell. Resultaten indikerar att generativa modeller kan användas för att augmentera eller ersätta existerande dataset vid träning av diskriminativa modeller.
33
Rana, Aakanksha. "Analyse d'images haute gamme dynamique." Electronic Thesis or Diss., Paris, ENST, 2018. http://www.theses.fr/2018ENST0015.
Full textAbstract:
L'imagerie HDR (High Dynamic Range) permet de capturer une gamme dynamique plus larges, nous permettant ainsi de tirer parti de détails subtils, mais différenciés, présents à la fois dans les zones extrêmement sombres et lumineuses d'une scène. Ces propriétés présentent un intérêt potentiel pour les algorithmes de vision par ordinateur où la performance peut se dégrader considérablement en présence de changements d’illumination lorsque les scènes acquises sont à l'aide d'images traditionnelles à faible gamme dynamique (LDR). Dans cette thèse, nous présentons des aspects quantitatifs et qualitatifs de l'analyse d'images HDR pour des algorithmes de vision par ordinateur.Cette thèse débute par l'identification des questions les plus importantes concernant l'utilisation de contenus HDR pour la tâche d'extraction des caractéristiques de bas niveau, qui est d'une importance fondamentale pour de nombreuses applications. En réalisant une évaluation de la performance, nous démontrons comment les différentes techniques basées sur le HDR améliorent la performance par rapport au LDR. Cependant, nous constatons qu'aucune ne peut le faire de manière optimale pour toutes les scènes. Pour étudier cette question, nous examinons l'importance des objectifs propres à chaque tâche, et concevons des opérateurs de mise en correspondance tonale (tone mapping operator-TMO) spécifiques.Dans cette thèse, nous proposons trois méthodologies basées sur l'apprentissage visant le TMO optimal du contenu HDR pour améliorer l'efficacité de l'extraction des caractéristiques locales à chaqueétape, à savoir détection, description et appariement final<br>High Dynamic Range (HDR) imaging enables to capture a wider dynamic range and color gamut, thus enabling us to draw on subtle, yet discriminating details present both in the extremely dark and bright areas of a scene. Such property is of potential interest for computer vision algorithms where performance degrades substantially when the scenes are captured using traditional low dynamic range (LDR) imagery. While such algorithms have been exhaustively designed using traditional LDR images, little work has been done so far in contex of HDR content. In this thesis, we present the quantitative and qualitative analysis of HDR imagery for such task-specific algorithms. This thesis begins by identifying the most natural and important questions of using HDR content for low-level feature extraction task, which is of fundamental importance for many high-level applications such as stereo vision, localization, matching and retrieval. By conducting a performance evaluation study, we demonstrate how different HDR-based modalities enhance algorithms performance with respect to LDR on a proposed dataset. However, we observe that none of them can optimally to do so across all the scenes. To examine this sub-optimality, we investigate the importance of task-specific objectives for designing optimal modalities through an experimental study. Based on the insights, we attempt to surpass this sub-optimality by designing task-specific HDR tone-mapping operators (TMOs). In this thesis, we propose three learning based methodologies aimed at optimal mapping of HDR content to enhance the efficiency of local features extraction at each stage namely, detection, description and final matching
34
Shahid, Mustafizur Rahman. "Deep learning for Internet of Things (IoT) network security." Electronic Thesis or Diss., Institut polytechnique de Paris, 2021. http://www.theses.fr/2021IPPAS003.
Full textAbstract:
L’internet des objets (IoT) introduit de nouveaux défis pour la sécurité des réseaux. La plupart des objets IoT sont vulnérables en raison d'un manque de sensibilisation à la sécurité des fabricants d'appareils et des utilisateurs. En conséquence, ces objets sont devenus des cibles privilégiées pour les développeurs de malware qui veulent les transformer en bots. Contrairement à un ordinateur de bureau, un objet IoT est conçu pour accomplir des tâches spécifiques. Son comportement réseau est donc très stable et prévisible, ce qui le rend bien adapté aux techniques d'analyse de données. Ainsi, la première partie de cette thèse tire profit des algorithmes de deep learning pour développer des outils de surveillance des réseaux IoT. Deux types d'outils sont explorés: les systèmes de reconnaissance de type d’objets IoT et les systèmes de détection d'intrusion réseau IoT. Pour la reconnaissance des types d’objets IoT, des algorithmes d'apprentissage supervisé sont entrainés pour classifier le trafic réseau et déterminer à quel objet IoT le trafic appartient. Le système de détection d'intrusion consiste en un ensemble d'autoencoders, chacun étant entrainé pour un type d’objet IoT différent. Les autoencoders apprennent le profil du comportement réseau légitime et détectent tout écart par rapport à celui-ci. Les résultats expérimentaux en utilisant des données réseau produites par une maison connectée montrent que les modèles proposés atteignent des performances élevées. Malgré des résultats préliminaires prometteurs, l’entraînement et l'évaluation des modèles basés sur le machine learning nécessitent une quantité importante de données réseau IoT. Or, très peu de jeux de données de trafic réseau IoT sont accessibles au public. Le déploiement physique de milliers d’objets IoT réels peut être très coûteux et peut poser problème quant au respect de la vie privée. Ainsi, dans la deuxième partie de cette thèse, nous proposons d'exploiter des GAN (Generative Adversarial Networks) pour générer des flux bidirectionnels qui ressemblent à ceux produits par un véritable objet IoT. Un flux bidirectionnel est représenté par la séquence des tailles de paquets ainsi que de la durée du flux. Par conséquent, en plus de générer des caractéristiques au niveau des paquets, tel que la taille de chaque paquet, notre générateur apprend implicitement à se conformer aux caractéristiques au niveau du flux, comme le nombre total de paquets et d'octets dans un flux ou sa durée totale. Des résultats expérimentaux utilisant des données produites par un haut-parleur intelligent montrent que notre méthode permet de générer des flux bidirectionnels synthétiques réalistes et de haute qualité<br>The growing Internet of Things (IoT) introduces new security challenges for network activity monitoring. Most IoT devices are vulnerable because of a lack of security awareness from device manufacturers and end users. As a consequence, they have become prime targets for malware developers who want to turn them into bots. Contrary to general-purpose devices, an IoT device is designed to perform very specific tasks. Hence, its networking behavior is very stable and predictable making it well suited for data analysis techniques. Therefore, the first part of this thesis focuses on leveraging recent advances in the field of deep learning to develop network monitoring tools for the IoT. Two types of network monitoring tools are explored: IoT device type recognition systems and IoT network Intrusion Detection Systems (NIDS). For IoT device type recognition, supervised machine learning algorithms are trained to perform network traffic classification and determine what IoT device the traffic belongs to. The IoT NIDS consists of a set of autoencoders, each trained for a different IoT device type. The autoencoders learn the legitimate networking behavior profile and detect any deviation from it. Experiments using network traffic data produced by a smart home show that the proposed models achieve high performance.Despite yielding promising results, training and testing machine learning based network monitoring systems requires tremendous amount of IoT network traffic data. But, very few IoT network traffic datasets are publicly available. Physically operating thousands of real IoT devices can be very costly and can rise privacy concerns. In the second part of this thesis, we propose to leverage Generative Adversarial Networks (GAN) to generate bidirectional flows that look like they were produced by a real IoT device. A bidirectional flow consists of the sequence of the sizes of individual packets along with a duration. Hence, in addition to generating packet-level features which are the sizes of individual packets, our developed generator implicitly learns to comply with flow-level characteristics, such as the total number of packets and bytes in a bidirectional flow or the total duration of the flow. Experimental results using data produced by a smart speaker show that our method allows us to generate high quality and realistic looking synthetic bidirectional flows
35
Gruneau, Joar. "Investigation of deep learning approaches for overhead imagery analysis." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-232208.
Full textAbstract:
Analysis of overhead imagery has a great potential to produce real-time data cost-effectively. This can be an important foundation for decision-making for businesses and politics. Every day a massive amount of new satellite imagery is produced. To fully take advantage of these data volumes a computationally efficient pipeline is required for the analysis. This thesis proposes a pipeline which outperforms the Segment Before you Detect network [6] and different types of fast region based convolutional neural networks [61] with a large margin in a fraction of the time. The model obtains a prediction error for counting cars of 1.67% on the Potsdam dataset and increases the vehiclewise F1 score on the VEDAI dataset from 0.305 reported by [61] to 0.542. This thesis also shows that it is possible to outperform the Segment Before you Detect network in less than 1% of the time on car counting and vehicle detection while also using less than half of the resolution. This makes the proposed model a viable solution for large-scale satellite imagery analysis.<br>Analys av flyg- och satellitbilder har stor potential att kostnadseffektivt producera data i realtid för beslutsfattande för företag och politik. Varje dag produceras massiva mängder nya satellitbilder. För att fullt kunna utnyttja dessa datamängder krävs ett beräkningseffektivt nätverk för analysen. Denna avhandling föreslår ett nätverk som överträffar Segment Before you Detect-nätverket [6] och olika typer av snabbt regionsbaserade faltningsnätverk [61] med en stor marginal på en bråkdel av tiden. Den föreslagna modellen erhåller ett prediktionsfel för att räkna bilar på 1,67% på Potsdam-datasetet och ökar F1- poängen for fordons detektion på VEDAI-datasetet från 0.305 rapporterat av [61] till 0.542. Denna avhandling visar också att det är möjligt att överträffa Segment Before you Detect-nätverket på mindre än 1% av tiden på bilräkning och fordonsdetektering samtidigt som den föreslagna modellen använder mindre än hälften av upplösningen. Detta gör den föreslagna modellen till en attraktiv lösning för storskalig satellitbildanalys.
36
Antipov, Grigory. "Apprentissage profond pour la description sémantique des traits visuels humains." Thesis, Paris, ENST, 2017. http://www.theses.fr/2017ENST0071/document.
Full textAbstract:
Les progrès récents des réseaux de neurones artificiels (plus connus sous le nom d'apprentissage profond) ont permis d'améliorer l’état de l’art dans plusieurs domaines de la vision par ordinateur. Dans cette thèse, nous étudions des techniques d'apprentissage profond dans le cadre de l’analyse du genre et de l’âge à partir du visage humain. En particulier, deux problèmes complémentaires sont considérés : (1) la prédiction du genre et de l’âge, et (2) la synthèse et l’édition du genre et de l’âge.D’abord, nous effectuons une étude détaillée qui permet d’établir une liste de principes pour la conception et l’apprentissage des réseaux de neurones convolutifs (CNNs) pour la classification du genre et l’estimation de l’âge. Ainsi, nous obtenons les CNNs les plus performants de l’état de l’art. De plus, ces modèles nous ont permis de remporter une compétition internationale sur l’estimation de l’âge apparent. Nos meilleurs CNNs obtiennent une précision moyenne de 98.7% pour la classification du genre et une erreur moyenne de 4.26 ans pour l’estimation de l’âge sur un corpus interne particulièrement difficile.Ensuite, afin d’adresser le problème de la synthèse et de l’édition d’images de visages, nous concevons un modèle nommé GA-cGAN : le premier réseau de neurones génératif adversaire (GAN) qui produit des visages synthétiques réalistes avec le genre et l’âge souhaités. Enfin, nous proposons une nouvelle méthode permettant d’employer GA-cGAN pour le changement du genre et de l’âge tout en préservant l’identité dans les images synthétiques. Cette méthode permet d'améliorer la précision d’un logiciel sur étagère de vérification faciale en présence d’écarts d’âges importants<br>The recent progress in artificial neural networks (rebranded as deep learning) has significantly boosted the state-of-the-art in numerous domains of computer vision. In this PhD study, we explore how deep learning techniques can help in the analysis of gender and age from a human face. In particular, two complementary problem settings are considered: (1) gender/age prediction from given face images, and (2) synthesis and editing of human faces with the required gender/age attributes.Firstly, we conduct a comprehensive study which results in an empirical formulation of a set of principles for optimal design and training of gender recognition and age estimation Convolutional Neural Networks (CNNs). As a result, we obtain the state-of-the-art CNNs for gender/age prediction according to the three most popular benchmarks, and win an international competition on apparent age estimation. On a very challenging internal dataset, our best models reach 98.7% of gender classification accuracy and an average age estimation error of 4.26 years.In order to address the problem of synthesis and editing of human faces, we design and train GA-cGAN, the first Generative Adversarial Network (GAN) which can generate synthetic faces of high visual fidelity within required gender and age categories. Moreover, we propose a novel method which allows employing GA-cGAN for gender swapping and aging/rejuvenation without losing the original identity in synthetic faces. Finally, in order to show the practical interest of the designed face editing method, we apply it to improve the accuracy of an off-the-shelf face verification software in a cross-age evaluation scenario
37
Daley, Jr John. "Generating Synthetic Schematics with Generative Adversarial Networks." Thesis, Högskolan Kristianstad, Fakulteten för naturvetenskap, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:hkr:diva-20901.
Full textAbstract:
This study investigates synthetic schematic generation using conditional generative adversarial networks, specifically the Pix2Pix algorithm was implemented for the experimental phase of the study. With the increase in deep neural network’s capabilities and availability, there is a demand for verbose datasets. This in combination with increased privacy concerns, has led to synthetic data generation utilization. Analysis of synthetic images was completed using a survey. Blueprint images were generated and were successful in passing as genuine images with an accuracy of 40%. This study confirms the ability of generative neural networks ability to produce synthetic blueprint images.
38
Tang, Hao. "Learning to Generate Things and Stuff: Guided Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes." Doctoral thesis, Università degli studi di Trento, 2021. http://hdl.handle.net/11572/306790.
Full textAbstract:
In this thesis, we mainly focus on image generation. However, one can still observe unsatisfying results produced by existing state-of-the-art methods. To address this limitation and further improve the quality of generated images, we propose a few novel models. The image generation task can be roughly divided into three subtasks, i.e., person image generation, scene image generation, and cross-modal translation. Person image generation can be further divided into three subtasks, namely, hand gesture generation, facial expression generation, and person pose generation. Meanwhile, scene image generation can be further divided into two subtasks, i.e., cross-view image translation and semantic image synthesis. For each task, we have proposed the corresponding solution. Specifically, for hand gesture generation, we have proposed the GestureGAN framework. For facial expression generation, we have proposed the Cycle-in-Cycle GAN (C2GAN) framework. For person pose generation, we have proposed the XingGAN and BiGraphGAN frameworks. For cross-view image translation, we have proposed the SelectionGAN framework. For semantic image synthesis, we have proposed the Local and Global GAN (LGGAN), EdgeGAN, and Dual Attention GAN (DAGAN) frameworks. Although each method was originally proposed for a certain task, we later discovered that each method is universal and can be used to solve different tasks. For instance, GestureGAN can be used to solve both hand gesture generation and cross-view image translation tasks. C2GAN can be used to solve facial expression generation, person pose generation, hand gesture generation, and cross-view image translation. SelectionGAN can be used to solve cross-view image translation, facial expression generation, person pose generation, hand gesture generation, and semantic image synthesis. Moreover, we explore cross-modal translation and propose a novel DanceGAN for audio-to-video translation.
39
Tang, Hao. "Learning to Generate Things and Stuff: Guided Generative Adversarial Networks for Generating Human Faces, Hands, Bodies, and Natural Scenes." Doctoral thesis, Università degli studi di Trento, 2021. http://hdl.handle.net/11572/306790.
Full textAbstract:
In this thesis, we mainly focus on image generation. However, one can still observe unsatisfying results produced by existing state-of-the-art methods. To address this limitation and further improve the quality of generated images, we propose a few novel models. The image generation task can be roughly divided into three subtasks, i.e., person image generation, scene image generation, and cross-modal translation.
Person image generation can be further divided into three subtasks, namely, hand gesture generation, facial expression generation, and person pose generation. Meanwhile, scene image generation can be further divided into two subtasks, i.e., cross-view image translation and semantic image synthesis. For each task, we have proposed the corresponding solution. Specifically, for hand gesture generation, we have proposed the GestureGAN framework. For facial expression generation, we have proposed the Cycle-in-Cycle GAN (C2GAN) framework. For person pose generation, we have proposed the XingGAN and BiGraphGAN frameworks. For cross-view image translation, we have proposed the SelectionGAN framework. For semantic image synthesis, we have proposed the Local and Global GAN (LGGAN), EdgeGAN, and Dual Attention GAN (DAGAN) frameworks. Although each method was originally proposed for a certain task, we later discovered that each method is universal and can be used to solve different tasks. For instance, GestureGAN can be used to solve both hand gesture generation and cross-view image translation tasks. C2GAN can be used to solve facial expression generation, person pose generation, hand gesture generation, and cross-view image translation. SelectionGAN can be used to solve cross-view image translation, facial expression generation, person pose generation, hand gesture generation, and semantic image synthesis. Moreover, we explore cross-modal translation and propose a novel DanceGAN for audio-to-video translation.
40
Marek, Jan. "Rekonstrukce chybějících části obličeje pomocí neuronové sítě." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2020. http://www.nusl.cz/ntk/nusl-433506.
Full textAbstract:
Cílem této práce je vytvořit neuronovou síť která bude schopna rekonstruovat obličeje z fotografií na kterých je část obličeje překrytá maskou. Jsou prezentovány koncepty využívané při vývoji konvolučních neuronových sítí a generativních kompetitivních sítí. Dále jsou popsány koncepty používané v neuronových sítích specificky pro rekonstrukci fotografií obličejů. Je představen model generativní kompetitivní sítě využívající kombinaci hrazených konvolučních vrstev a víceškálových bloků schopný realisticky doplnit oblasti obličeje zakryté maskou.
41
Li, Yuchuan. "Dual-Attention Generative Adversarial Network and Flame and Smoke Analysis." Thesis, Université d'Ottawa / University of Ottawa, 2021. http://hdl.handle.net/10393/42774.
Full textAbstract:
Flame and smoke image processing and analysis could improve performance to detect smoke or fire and identify many complicated fire hazards, eventually to help firefighters to fight fires safely. Deep Learning applied to image processing has been prevailing in recent years among image-related research fields. Fire safety researchers also brought it into their studies due to its leading performance in image-related tasks and statistical analysis. From the perspective of input data type, traditional fire research is based on simple mathematical regressions or empirical correlations relying on sensor data, such as temperature. However, data from advanced vision devices or sensors can be analyzed by applying deep learning beyond auxiliary methods in data processing and analysis. Deep Learning has a bigger capacity in non-linear problems, especially in high-dimensional spaces, such as flame and smoke image processing. We propose a video-based real-time smoke and flame analysis system with deep learning networks and fire safety knowledge. It takes videos of fire as input and produces analysis and prediction for flashover of fire.
Our system consists of four modules. The Color2IR Conversion module is made by deep neural networks to convert RGB video frames into InfraRed (IR) frames, which could provide important thermal information of fire. Thermal information is critically important for fire hazard detection. For example, 600 °C marks the start of a flashover. As RGB cameras cannot capture thermal information, we propose an image conversion module from RGB to IR images. The core of this conversion is a new network that we innovatively proposed: Dual-Attention Generative Adversarial Network (DAGAN), and it is trained using a pair of RGB and IR images.
Next, Video Semantic Segmentation Module helps extract flame and smoke areas from the scene in the RGB video frames. We innovated to use synthetic RGB video data generated and captured from 3D modeling software for data augmentation.
After that, a Video Prediction Module takes the RGB video frames and IR frames as input and produces predictions of the subsequent frames of their scenes.
Finally, a Fire Knowledge Analysis Module predicts if flashover is coming or not, based on fire knowledge criteria such as thermal information extracted from IR images, temperature increase rate, the flashover occurrence temperature, and increase rate of lowest temperature.
For our contributions and innovations, we introduce a novel network, DAGAN, by applying foreground and background attention mechanisms in the image conversion module to help reduce the hardware device requirement for flashover prediction. Besides, we also make use of combination of thermal information from IR images and segmentation information from RGB images in our system for flame and smoke analysis. We also apply a hybrid design of deep neural networks and a knowledge-based system to achieve high accuracy. Moreover, data augmentation is also applied on the Video Semantic Segmentation Module by introducing synthetic video data for training.
The test results of flashover prediction show that our system has leading places quantitative and qualitative in terms of various metrics compared with other existing approaches. It can give a flashover prediction as early as 51 seconds with 94.5% accuracy before it happens.
42
Cabezas, Rodríguez Juan Pablo. "Generative adversarial network based model for multi-domain fault diagnosis." Tesis, Universidad de Chile, 2019. http://repositorio.uchile.cl/handle/2250/170996.
Full textAbstract:
Memoria para optar al título de Ingeniero Civil Mecánico<br>Con el uso de las redes neuronal profundas ganando terreno en el área de PHM, los sensores
disminuyendo progresivamente su precio y mejores algoritmos, la falta de datos se ha vuelto
un problema principal para los modelos enfocados en datos. Los datos etiquetados y aplicables
a escenarios específicos son, en el mejor de los casos, escasos.
El objetivo de este trabajo es desarrollar un método para diagnosticas el estado de un rodamiento
en situaciones con datos limitados.
Hoy en día la mayoría de las técnicas se enfocan en mejorar la precisión del diagnóstico y
en estimar la vida útil remanente en componentes bien documentados. En el presente, los
métodos actuales son ineficiente en escenarios con datos limitados.
Se desarrolló un método en el cual las señales vibratorias son usadas para crear escalogramas
y espectrogramas, los cuales a su vez se usan para entrenar redes neuronales generativas y
de clasificación, en función de diagnosticar un set de datos parcial o totalmente desconocido,
en base a uno conocido.
Los resultados se comparan con un método más sencillo en el cual la red para clasificación
es entrenada con el set de datos conocidos y usada directamente para diagnosticar el set de
datos desconocido.
El Case Western Reserve University Bearing Dataset y el Machine Failure Prevention Technology
Bearing Dataset fueron usados como datos de entrada. Ambos sets se usaron como
conocidos tanto como desconocidos.
Para la clasificación una red neuronal convolucional (CNN por sus siglas en inglés) fue diseñada.
Una red adversaria generativa (GAN por sus siglas en inglés) fue usada como red
generativa. Esta red fue basada en una introducida en el paper StarGAN: Unified Generative
Adversarial Networks for Multi-Domain Image-to-Image Translation.
Los resultados fueron favorables para la red CNN mientras que fueron -en general- desfavorables
para la red GAN.
El análisis de resultados sugiere que la función de costo es inapropiada para el problema
propuesto.
Las conclusiones dictaminan que la traducción imagen-a-imagen basada en la función ciclo
no funciona correctamente en señal vibratorias para diagnóstico de rodamientos.
With the use of deep neural networks gaining notoriety on the prognostics & health management field, sensors getting progressively cheaper and improved algorithms, the lack of data
has become a major issue for data-driven models. Data which is labelled and applicable for
specific scenarios is scarce at best.
The purpose of this works is to develop a method to diagnose the health state of a bearing
on limited data situations.
Now a days most techniques focus on improving accuracy for diagnosis and estimating remaining useful life on well documented components. As it stands, current methods are
ineffective on limited data scenarios.
A method was developed were in vibration signals are used to create scalograms and spectrograms, which in turn are used to train generative and classification neural networks with
the goal of diagnosing a partially or totally unknown dataset based on a fully labelled one.
Results were compared to a simpler method in which a classification network is trained on
the labelled dataset to diagnose the unknown dataset.
As inputs the Case Western Reserve University Bearing Dataset (CWR) and the Society for
Machine Failure Prevention Technology Bearing Dataset. Both datasets are used as labelled
and unknown.
For classification a Convolutional Neural Network (CNN) is designed. A Generative Adversarial Network (GAN) is used as generative model. The generative model is based of a
previous paper called StarGAN: Unified Generative Adversarial Networks for Multi-Domain
Image-to-Image Translation.
Results were favourable for the CNN network whilst generally negative for the GAN network.
Result analysis suggests that the cost function is unsuitable for the proposed problem.
Conclusions state that cycle based image-to-image translation does not work correctly on
vibration signals for bearing diagnosis.
43
Zeid, Baker Mousa. "Generation of Synthetic Images with Generative Adversarial Networks." Thesis, Blekinge Tekniska Högskola, Institutionen för datalogi och datorsystemteknik, 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-15866.
Full textAbstract:
Machine Learning is a fast growing area that revolutionizes computer programs by providing systems with the ability to automatically learn and improve from experience. In most cases, the training process begins with extracting patterns from data. The data is a key factor for machine learning algorithms, without data the algorithms will not work. Thus, having sufficient and relevant data is crucial for the performance. In this thesis, the researcher tackles the problem of not having a sufficient dataset, in terms of the number of training examples, for an image classification task. The idea is to use Generative Adversarial Networks to generate synthetic images similar to the ground truth, and in this way expand a dataset. Two types of experiments were conducted: the first was used to fine-tune a Deep Convolutional Generative Adversarial Network for a specific dataset, while the second experiment was used to analyze how synthetic data examples affect the accuracy of a Convolutional Neural Network in a classification task. Three well known datasets were used in the first experiment, namely MNIST, Fashion-MNIST and Flower photos, while two datasets were used in the second experiment: MNIST and Fashion-MNIST. The results of the generated images of MNIST and Fashion-MNIST had good overall quality. Some classes had clear visual errors while others were indistinguishable from ground truth examples. When it comes to the Flower photos, the generated images suffered from poor visual quality. One can easily tell the synthetic images from the real ones. One reason for the bad performance is due to the large quantity of noise in the Flower photos dataset. This made it difficult for the model to spot the important features of the flowers. The results from the second experiment show that the accuracy does not increase when the two datasets, MNIST and Fashion-MNIST, are expanded with synthetic images. This is not because the generated images had bad visual quality, but because the accuracy turned out to not be highly dependent on the number of training examples. It can be concluded that Deep Convolutional Generative Adversarial Networks are capable of generating synthetic images similar to the ground truth and thus can be used to expand a dataset. However, this approach does not completely solve the initial problem of not having adequate datasets because Deep Convolutional Generative Adversarial Networks may themselves require, depending on the dataset, a large quantity of training examples.
44
Desentz, Derek. "Partial Facial Re-imaging Using Generative Adversarial Networks." Wright State University / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=wright1622122813797895.
Full text
45
Antipov, Grigory. "Apprentissage profond pour la description sémantique des traits visuels humains." Electronic Thesis or Diss., Paris, ENST, 2017. http://www.theses.fr/2017ENST0071.
Full textAbstract:
Les progrès récents des réseaux de neurones artificiels (plus connus sous le nom d'apprentissage profond) ont permis d'améliorer l’état de l’art dans plusieurs domaines de la vision par ordinateur. Dans cette thèse, nous étudions des techniques d'apprentissage profond dans le cadre de l’analyse du genre et de l’âge à partir du visage humain. En particulier, deux problèmes complémentaires sont considérés : (1) la prédiction du genre et de l’âge, et (2) la synthèse et l’édition du genre et de l’âge.D’abord, nous effectuons une étude détaillée qui permet d’établir une liste de principes pour la conception et l’apprentissage des réseaux de neurones convolutifs (CNNs) pour la classification du genre et l’estimation de l’âge. Ainsi, nous obtenons les CNNs les plus performants de l’état de l’art. De plus, ces modèles nous ont permis de remporter une compétition internationale sur l’estimation de l’âge apparent. Nos meilleurs CNNs obtiennent une précision moyenne de 98.7% pour la classification du genre et une erreur moyenne de 4.26 ans pour l’estimation de l’âge sur un corpus interne particulièrement difficile.Ensuite, afin d’adresser le problème de la synthèse et de l’édition d’images de visages, nous concevons un modèle nommé GA-cGAN : le premier réseau de neurones génératif adversaire (GAN) qui produit des visages synthétiques réalistes avec le genre et l’âge souhaités. Enfin, nous proposons une nouvelle méthode permettant d’employer GA-cGAN pour le changement du genre et de l’âge tout en préservant l’identité dans les images synthétiques. Cette méthode permet d'améliorer la précision d’un logiciel sur étagère de vérification faciale en présence d’écarts d’âges importants<br>The recent progress in artificial neural networks (rebranded as deep learning) has significantly boosted the state-of-the-art in numerous domains of computer vision. In this PhD study, we explore how deep learning techniques can help in the analysis of gender and age from a human face. In particular, two complementary problem settings are considered: (1) gender/age prediction from given face images, and (2) synthesis and editing of human faces with the required gender/age attributes.Firstly, we conduct a comprehensive study which results in an empirical formulation of a set of principles for optimal design and training of gender recognition and age estimation Convolutional Neural Networks (CNNs). As a result, we obtain the state-of-the-art CNNs for gender/age prediction according to the three most popular benchmarks, and win an international competition on apparent age estimation. On a very challenging internal dataset, our best models reach 98.7% of gender classification accuracy and an average age estimation error of 4.26 years.In order to address the problem of synthesis and editing of human faces, we design and train GA-cGAN, the first Generative Adversarial Network (GAN) which can generate synthetic faces of high visual fidelity within required gender and age categories. Moreover, we propose a novel method which allows employing GA-cGAN for gender swapping and aging/rejuvenation without losing the original identity in synthetic faces. Finally, in order to show the practical interest of the designed face editing method, we apply it to improve the accuracy of an off-the-shelf face verification software in a cross-age evaluation scenario
46
Vanhainen, Erik, and Johan Adamsson. "Generating Realistic Neuronal Morphologies in 3D using a Generative Adversarial Network." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-301788.
Full textAbstract:
Neuronal morphology is primarily responsible for the structure of the connectivity among the neurons and is an important determinant for neuronal activity. This raises questions about the relationship between neuron shape and neuron function. To further investigate the structure-function relationship in neurons, extensive modelling with more morphological data is key. Digitally reconstructing neurons is tedious and requires a lot of manual labour and hence several generative methods have been proposed. However these generative models utilizes the current understanding of neuronal morphology, often by imposing a priori constraints, and thus may be biased or do not capture reality fully. We present an alternative technique using a Generative Adversarial Network that generates neurons without being constrained by current human understanding. The model was trained on digital reconstructions of pyramidal cells from rats and mice in a voxelized representation with dimensionality 1283. The results show that the model can generate objects that exhibit realistic neuronal features with a wide variety of shapes. Even though realistic feature are present in the generated objects they are often easily distinguishable from real neurons because of small discontinuous parts and noise in the complex arborizations. Nevertheless, this work can be seen as a proof of concept for generating realistic three dimensional morphologies in an unbiased manner.<br>Neuroners morfologier är primärt ansvariga för strukturen hos kopplingarna mellan neuroner och är en avgörande faktor för neuronaktivitet. Detta väcker frågor om sambandet mellan neuroners form och funktionalitet. För att undersöka detta samband är omfattande modellering med mycket morfologidata viktigt. Digital rekonstruktion av neuroner är omfattande och kräver mycket manuellt arbete. Av den anledning har flera generativa metoder föreslagits, dock bygger dessa metoder på vår nuvarande förståelse om neuroners morfologi som kan vara felaktig eller ofullständig. Vi föreslår en alternativ metod som med ett Generative Adversarial Network genererar neuroner utan att begränsas av vår nuvarande förståelse om neuroner. Modellen tränades på digitala rekonstruktioner av pyramidalceller från råttor och möss där varje neuron är representerad med 1283 voxlar. Resultaten visar att modellen kan generera objekt med realistiska neuronala särdrag och former. Även fast genererade objekt har realistiska former går de lätt att urskilja från riktiga neuroner på grund av små diskontinuerliga delar och brus i komplexa förgreningar. Detta arbete kan icke desto mindre ses som en grund till framtida arbete inom generering av tredimensionella nervceller utan mänsklig bias.
47
Hermoza, Aragonés Renato. "3D Reconstruction of Incomplete Archaeological Objects Using a Generative Adversarial Network." Master's thesis, Pontificia Universidad Católica del Perú, 2018. http://tesis.pucp.edu.pe/repositorio/handle/123456789/12263.
Full textAbstract:
We introduce a data-driven approach to aid the repairing and conservation of archaeological objects: ORGAN, an object reconstruction generative adversarial network (GAN). By using an encoder-decoder 3D deep neural network on a GAN architecture, and combining two loss objectives: a completion loss and an Improved Wasserstein GAN loss, we can train a network to effectively predict the missing geometry of damaged objects. As archaeological objects can greatly differ between them, the network is conditioned on a variable, which can be a culture, a region or any metadata of the object. In our results, we show that our method can recover most of the information from damaged objects, even in cases where more than half of the voxels are missing, without producing many errors.<br>Tesis
48
Ankaräng, Fredrik. "Generative Adversarial Networks for Cross-Lingual Voice Conversion." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-299560.
Full textAbstract:
Speech synthesis is a technology that increasingly influences our daily lives, in the form of smart assistants, advanced translation systems and similar applications. In this thesis, the phenomenon of making one’s voice sound like the voice of someone else is explored. This topic is called voice conversion and needs to be done without altering the linguistic content of speech. More specifically, a Cycle-Consistent Adversarial Network that has proven to work well in a monolingual setting, is evaluated in a multilingual environment. The model is trained to convert voices between native speakers from the Nordic countries. In the experiments no parallel, transcribed or aligned speech data is being used, forcing the model to focus on the raw audio signal. The goal of the thesis is to evaluate if performance is degraded in a multilingual environment, in comparison to monolingual voice conversion, and to measure the impact of the potential performance drop. In the study, performance is measured in terms of naturalness and speaker similarity between the generated speech and the target voice. For evaluation, listening tests are conducted, as well as objective comparisons of the synthesized speech. The results show that voice conversion between a Swedish and Norwegian speaker is possible and also that it can be performed without performance degradation in comparison to Swedish-to-Swedish conversion. Furthermore, conversion between Finnish and Swedish speakers, as well as Danish and Swedish speakers show a performance drop for the generated speech. However, despite the performance decrease, the model produces fluent and clearly articulated converted speech in all experiments. These results are noteworthy, especially since the network is trained on less than 15 minutes of nonparallel speaker data for each speaker. This thesis opens up for further areas of research, for instance investigating more languages, more recent Generative Adversarial Network architectures and devoting more resources to tweaking the hyperparameters to further optimize the model for multilingual voice conversion.<br>Talsyntes är ett område som allt mer influerar vår vardag, exempelvis genom smarta assistenter, avancerade översättningssystem och liknande användningsområden. I det här examensarbetet utforskas fenomenet röstkonvertering, som innebär att man får en talare att låta som någon annan, utan att det som sades förändras. Mer specifikt undersöks ett Cycle-Consistent Adversarial Network som fungerat väl för röstkonvertering inom ett enskilt språk för röstkonvertering mellan olika språk. Det neurala nätverket tränas för konvertering mellan röster från olika modersmålstalare från de nordiska länderna. I experimenten används ingen parallell eller transkriberad data, vilket tvingar modellen att endast använda sig av ljudsignalen. Målet med examensarbetet är att utvärdera om modellens prestanda försämras i en flerspråkig kontext, jämfört med en enkelspråkig sådan, samt mäta hur stor försämringen i sådant fall är. I studien mäts prestanda i termer av kvalitet och talarlikhet för det genererade talet och rösten som efterliknas. För att utvärdera detta genomförs lyssningstester, samt objektiva analyser av det genererade talet. Resultaten visar att röstkonvertering mellan en svensk och norsk talare är möjlig utan att modellens prestanda försämras, jämfört med konvertering mellan svenska talare. För konvertering mellan finska och svenska talare, samt danska och svenska talare försämrades däremot kvaliteten av det genererade talet. Trots denna försämring producerade modellen tydligt och sammanhängande tal i samtliga experiment. Det här är anmärkningsvärt eftersom modellen tränades på mindre än 15 minuter icke-parallel data för varje talare. Detta examensarbete öppnar upp för nya framtida studier, exempelvis skulle fler språk kunna inkluderas eller nyare varianter av typen Generative Adversarial Network utvärderas. Mer resurser skulle även kunna läggas på att optimera hyperparametrarna för att ytterligare optimera den undersökta modellen för flerspråkig röstkonvertering.
49
Radhakrishnan, Saieshwar. "Domain Adaptation of IMU sensors using Generative Adversarial Networks." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-286821.
Full textAbstract:
Autonomous vehicles rely on sensors for a clear understanding of the environment and in a heavy duty truck, the sensors are placed at multiple locations like the cabin, chassis and the trailer in order to increase the field of view and reduce the blind spot area. Usually, these sensors perform best when they are stationary relative to the ground, hence large and fast movements, which are quite common in a truck, may lead to performance reduction, erroneous data or in the worst case, a sensor failure. This enforces a need to validate the sensors before using them for making life-critical decisions. This thesis proposes Domain Adaptation as one of the strategies to co-validate Inertial Measurement Unit (IMU) sensors. The proposed Generative Adversarial Network (GAN) based framework predicts the data of one IMU using other IMUs in the truck by implicitly learning the internal dynamics. This prediction model along with other sensor fusion strategies would be used by the supervising system to validate the IMUs in real-time. Through data collected from real-world experiments, it is shown that the proposed framework is able to accurately transform raw IMU sequences across domains. A further comparison is made between Long Short Term Memory (LSTM) and WaveNet based architectures to show the superiority of WaveNets in terms of performance and computational efficiency.<br>Autonoma fordon förlitar sig på sensorer för att skapa en bild av omgivningen. På en tung lastbil placeras sensorerna på multipla ställen, till exempel på hytten, chassiet och på trailern för att öka siktfältet och för att minska blinda områden. Vanligtvis presterar sensorerna som bäst när de är stationära i förhållande till marken, därför kan stora och snabba rörelser, som är vanliga på en lastbil, leda till nedsatt prestanda, felaktig data och i värsta fall fallerande sensorer. På grund av detta så finns det ett stort behov av att validera sensordata innan det används för kritiskt beslutsfattande. Den här avhandlingen föreslår domänadaption som en av de strategier för att samvalidera Tröghetsmätningssensorer (IMU-sensorer). Det föreslagna Generative Adversarial Network (GAN) baserade ramverket förutspår en Tröghetssensors data genom att implicit lära sig den interna dynamiken från andra Tröghetssensorer som är monterade på lastbilen. Den här prediktionsmodellen kombinerat med andra sensorfusionsstrategier kan användas av kontrollsystemet för att i realtid validera Tröghetssensorerna. Med hjälp av data insamlat från verkliga experiment visas det att det föreslagna ramverket klarar av att med hög noggrannhet konvertera obehandlade Tröghetssensor-sekvenser mellan domäner. Ytterligare en undersökning mellan Long Short Term Memory (LSTM) och WaveNet-baserade arkitekturer görs för att visa överlägsenheten i WaveNets när det gäller prestanda och beräkningseffektivitet.
50
Delacruz, Gian P. "Using Generative Adversarial Networks to Classify Structural Damage Caused by Earthquakes." DigitalCommons@CalPoly, 2020. https://digitalcommons.calpoly.edu/theses/2158.
Full textAbstract:
The amount of structural damage image data produced in the aftermath of an earthquake can be staggering. It is challenging for a few human volunteers to efficiently filter and tag these images with meaningful damage information. There are several solution to automate post-earthquake reconnaissance image tagging using Machine Learning (ML) solutions to classify each occurrence of damage per building material and structural member type. ML algorithms are data driven; improving with increased training data. Thanks to the vast amount of data available and advances in computer architectures, ML and in particular Deep Learning (DL) has become one of the most popular image classification algorithms producing results comparable to and in some cases superior to human experts. These kind of algorithms need the input images used for the training to be labeled, and even if there is a large amount of images most of them are not labeled and it takes structural engineers a large amount of time to do it. The current data earthquakes image data bases do not contain the label information or is incomplete slowing significantly the advance of a solution and are incredible difficult to search. To be able to train a ML algorithm to classify one of the structural damages it took the architecture school an entire year to gather 200 images of the specific damage. That number is clearly not enough to avoid overfitting so for this thesis we decided to generate synthetic images for the specific structural damage. In particular we attempt to use Generative Adversarial Neural Networks (GANs) to generate the synthetic images and enable the fast classification of rail and road damage caused by earthquakes. Fast classification of rail and road damage can allow for the safety of people and to better prepare the reconnaissance teams that manage recovery tasks. GANs combine classification neural networks with generative neural networks. For this thesis we will be combining a convolutional neural network (CNN) with a generative neural network. By taking a classifier trained in a GAN and modifying it to classify other images the classifier can take advantage of the GAN training without having to find more training data. The classifier trained in this way was able to achieve an 88\% accuracy score when classifying images of structural damage caused by earthquakes.