Bibliografie tematiche / Robust Representations / Articoli di riviste

Segui questo link per vedere altri tipi di pubblicazioni sul tema: Robust Representations.

Articoli di riviste sul tema "Robust Representations"

Autore: Grafiati

Pubblicato: 1 giugno 2024

Ultima modifica: 19 luglio 2025

Cita una fonte nei formati APA, MLA, Chicago, Harvard e in molti altri stili

Scegli il tipo di fonte:

Vedi i top-50 articoli di riviste per l'attività di ricerca sul tema "Robust Representations".

Accanto a ogni fonte nell'elenco di riferimenti c'è un pulsante "Aggiungi alla bibliografia". Premilo e genereremo automaticamente la citazione bibliografica dell'opera scelta nello stile citazionale di cui hai bisogno: APA, MLA, Harvard, Chicago, Vancouver ecc.

Puoi anche scaricare il testo completo della pubblicazione scientifica nel formato .pdf e leggere online l'abstract (il sommario) dell'opera se è presente nei metadati.

Vedi gli articoli di riviste di molte aree scientifiche e compila una bibliografia corretta.

Yang, Shuo, Tianyu Guo, Yunhe Wang, and Chang Xu. "Adversarial Robustness through Disentangled Representations." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 4 (2021): 3145–53. http://dx.doi.org/10.1609/aaai.v35i4.16424.

Testo completo

Abstract (sommario):

Despite the remarkable empirical performance of deep learning models, their vulnerability to adversarial examples has been revealed in many studies. They are prone to make a susceptible prediction to the input with imperceptible adversarial perturbation. Although recent works have remarkably improved the model's robustness under the adversarial training strategy, an evident gap between the natural accuracy and adversarial robustness inevitably exists. In order to mitigate this problem, in this paper, we assume that the robust and non-robust representations are two basic ingredients entangled in the integral representation. For achieving adversarial robustness, the robust representations of natural and adversarial examples should be disentangled from the non-robust part and the alignment of the robust representations can bridge the gap between accuracy and robustness. Inspired by this motivation, we propose a novel defense method called Deep Robust Representation Disentanglement Network (DRRDN). Specifically, DRRDN employs a disentangler to extract and align the robust representations from both adversarial and natural examples. Theoretical analysis guarantees the mitigation of the trade-off between robustness and accuracy with good disentanglement and alignment performance. Experimental results on benchmark datasets finally demonstrate the empirical superiority of our method.

Gli stili APA, Harvard, Vancouver, ISO e altri

Kuo, Yen-Ling. "Learning Representations for Robust Human-Robot Interaction." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 20 (2024): 22673. http://dx.doi.org/10.1609/aaai.v38i20.30289.

Testo completo

Abstract (sommario):

For robots to robustly and flexibly interact with humans, they need to acquire skills to use across scenarios. One way to enable the generalization of skills is to learn representations that are useful for downstream tasks. Learning a representation for interactions requires an understanding of what (e.g., objects) as well as how (e.g., actions, controls, and manners) to interact with. However, most existing language or visual representations mainly focus on objects. To enable robust human-robot interactions, we need a representation that is not just grounded at the object level but to reason at the action level. The ability to reason about an agent’s own actions and other’s actions will be crucial for long-tail interactions. My research focuses on leveraging the compositional nature of language and reward functions to learn representations that generalize to novel scenarios. Together with the information from multiple modalities, the learned representation can reason about task progress, future behaviors, and the goals/beliefs of an agent. The above ideas have been demonstrated in my research on building robots to understand language and engage in social interactions.

Gli stili APA, Harvard, Vancouver, ISO e altri

Iddianozie, Chidubem, and Gavin McArdle. "Towards Robust Representations of Spatial Networks Using Graph Neural Networks." Applied Sciences 11, no. 15 (2021): 6918. http://dx.doi.org/10.3390/app11156918.

Testo completo

Abstract (sommario):

The effectiveness of a machine learning model is impacted by the data representation used. Consequently, it is crucial to investigate robust representations for efficient machine learning methods. In this paper, we explore the link between data representations and model performance for inference tasks on spatial networks. We argue that representations which explicitly encode the relations between spatial entities would improve model performance. Specifically, we consider homogeneous and heterogeneous representations of spatial networks. We recognise that the expressive nature of the heterogeneous representation may benefit spatial networks and could improve model performance on certain tasks. Thus, we carry out an empirical study using Graph Neural Network models for two inference tasks on spatial networks. Our results demonstrate that heterogeneous representations improves model performance for down-stream inference tasks on spatial networks.

Gli stili APA, Harvard, Vancouver, ISO e altri

Chateauneuf, Alain, Xiangyu Qu, Caroline Ventura та Vassili Vergopoulos. "Robust α-maxmin representations". Journal of Mathematical Economics 114 (жовтень 2024): 103045. http://dx.doi.org/10.1016/j.jmateco.2024.103045.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Vu, Hung, Tu Dinh Nguyen, Trung Le, Wei Luo, and Dinh Phung. "Robust Anomaly Detection in Videos Using Multilevel Representations." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 5216–23. http://dx.doi.org/10.1609/aaai.v33i01.33015216.

Testo completo

Abstract (sommario):

Detecting anomalies in surveillance videos has long been an important but unsolved problem. In particular, many existing solutions are overly sensitive to (often ephemeral) visual artifacts in the raw video data, resulting in false positives and fragmented detection regions. To overcome such sensitivity and to capture true anomalies with semantic significance, one natural idea is to seek validation from abstract representations of the videos. This paper introduces a framework of robust anomaly detection using multilevel representations of both intensity and motion data. The framework consists of three main components: 1) representation learning using Denoising Autoencoders, 2) level-wise representation generation using Conditional Generative Adversarial Networks, and 3) consolidating anomalous regions detected at each representation level. Our proposed multilevel detector shows a significant improvement in pixel-level Equal Error Rate, namely 11.35%, 12.32% and 4.31% improvement in UCSD Ped 1, UCSD Ped 2 and Avenue datasets respectively. In addition, the model allowed us to detect mislabeled anomalies in the UCDS Ped 1.

Gli stili APA, Harvard, Vancouver, ISO e altri

Ho, Edward Kei Shiu, and Lai Wan Chan. "Analyzing Holistic Parsers: Implications for Robust Parsing and Systematicity." Neural Computation 13, no. 5 (2001): 1137–70. http://dx.doi.org/10.1162/08997660151134361.

Testo completo

Abstract (sommario):

Holistic parsers offer a viable alternative to traditional algorithmic parsers. They have good generalization performance and are robust inherently. In a holistic parser, parsing is achieved by mapping the connectionist representation of the input sentence to the connectionist representation of the target parse tree directly. Little prior knowledge of the underlying parsing mechanism thus needs to be assumed. However, it also makes holistic parsing difficult to understand. In this article, an analysis is presented for studying the operations of the confluent pre-order parser (CPP). In the analysis, the CPP is viewed as a dynamical system, and holistic parsing is perceived as a sequence of state transitions through its state-space. The seemingly one-shot parsing mechanism can thus be elucidated as a step-by-step inference process, with the intermediate parsing decisions being reflected by the states visited during parsing. The study serves two purposes. First, it improves our understanding of how grammatical errors are corrected by the CPP. The occurrence of an error in a sentence will cause the CPP to deviate from the normal track that is followed when the original sentence is parsed. But as the remaining terminals are read, the two trajectories will gradually converge until finally the correct parse tree is produced. Second, it reveals that having systematic parse tree representations alone cannot guarantee good generalization performance in holistic parsing. More important, they need to be distributed in certain useful locations of the representational space. Sentences with similar trailing terminals should have their corresponding parse tree representations mapped to nearby locations in the representational space. The study provides concrete evidence that encoding the linearized parse trees as obtained via preorder traversal can satisfy such a requirement.

Gli stili APA, Harvard, Vancouver, ISO e altri

Yang, Qing, Jun Chen, and Najla Al-Nabhan. "Data representation using robust nonnegative matrix factorization for edge computing." Mathematical Biosciences and Engineering 19, no. 2 (2021): 2147–78. http://dx.doi.org/10.3934/mbe.2022100.

Testo completo

Abstract (sommario):

<abstract> <p>As a popular data representation technique, Nonnegative matrix factorization (NMF) has been widely applied in edge computing, information retrieval and pattern recognition. Although it can learn parts-based data representations, existing NMF-based algorithms fail to integrate local and global structures of data to steer matrix factorization. Meanwhile, semi-supervised ones ignore the important role of instances from different classes in learning the representation. To solve such an issue, we propose a novel semi-supervised NMF approach via joint graph regularization and constraint propagation for edge computing, called robust constrained nonnegative matrix factorization (RCNMF), which learns robust discriminative representations by leveraging the power of both L2, 1-norm NMF and constraint propagation. Specifically, RCNMF explicitly exploits global and local structures of data to make latent representations of instances involved by the same class closer and those of instances involved by different classes farther. Furthermore, RCNMF introduces the L2, 1-norm cost function for addressing the problems of noise and outliers. Moreover, L2, 1-norm constraints on the factorial matrix are used to ensure the new representation sparse in rows. Finally, we exploit an optimization algorithm to solve the proposed framework. The convergence of such an optimization algorithm has been proven theoretically and empirically. Empirical experiments show that the proposed RCNMF is superior to other state-of-the-art algorithms.</p> </abstract>

Gli stili APA, Harvard, Vancouver, ISO e altri

Parlett, Beresford N., and Inderjit S. Dhillon. "Relatively robust representations of symmetric tridiagonals." Linear Algebra and its Applications 309, no. 1-3 (2000): 121–51. http://dx.doi.org/10.1016/s0024-3795(99)00262-1.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Medina, Josep R., and Carlos R. Sanchez‐Carratala. "Robust AR Representations of Ocean Spectra." Journal of Engineering Mechanics 117, no. 12 (1991): 2926–30. http://dx.doi.org/10.1061/(asce)0733-9399(1991)117:12(2926).

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Higashi, Masatake, Fuyuki Torihara, Nobuhiro Takeuchi, Toshio Sata, Tsuyoshi Saitoh, and Mamoru Hosaka. "Robust algorithms for face-based representations." Computer-Aided Design 29, no. 2 (1997): 135–46. http://dx.doi.org/10.1016/s0010-4485(96)00042-5.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Rostami, Mohammad. "Internal Robust Representations for Domain Generalization." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 13 (2023): 15451. http://dx.doi.org/10.1609/aaai.v37i13.26818.

Testo completo

Abstract (sommario):

Model generalization under distributional changes remains a significant challenge for machine learning. We present consolidating the internal representation of the training data in a model as a strategy of improving model generalization.

Gli stili APA, Harvard, Vancouver, ISO e altri

Shi, Weipeng, Wenhu Qin, and Allshine Chen. "Towards Robust Semantic Segmentation of Land Covers in Foggy Conditions." Remote Sensing 14, no. 18 (2022): 4551. http://dx.doi.org/10.3390/rs14184551.

Testo completo

Abstract (sommario):

When conducting land cover classification, it is inevitable to encounter foggy conditions, which degrades the performance by a large margin. Robustness may be reduced by a number of factors, such as aerial images of low quality and ineffective fusion of multimodal representations. Hence, it is crucial to establish a reliable framework that can robustly understand remote sensing image scenes. Based on multimodal fusion and attention mechanisms, we leverage HRNet to extract underlying features, followed by the Spectral and Spatial Representation Learning Module to extract spectral-spatial representations. A Multimodal Representation Fusion Module is proposed to bridge the gap between heterogeneous modalities which can be fused in a complementary manner. A comprehensive evaluation study of the fog-corrupted Potsdam and Vaihingen test sets demonstrates that the proposed method achieves a mean F1score exceeding 73%, indicating a promising performance compared to State-Of-The-Art methods in terms of robustness.

Gli stili APA, Harvard, Vancouver, ISO e altri

Rezayi, Saed. "Learning Better Representations Using Auxiliary Knowledge." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 13 (2023): 16133–34. http://dx.doi.org/10.1609/aaai.v37i13.26927.

Testo completo

Abstract (sommario):

Representation Learning is the core of Machine Learning and Artificial Intelligence as it summarizes input data points into low dimensional vectors. This low dimensional vectors should be accurate portrayals of the input data, thus it is crucial to find the most effective and robust representation possible for given input as the performance of the ML task is dependent on the resulting representations. In this summary, we discuss an approach to augment representation learning which relies on external knowledge. We briefly describe the shortcoming of the existing techniques and describe how an auxiliary knowledge source could result in obtaining improved representations.

Gli stili APA, Harvard, Vancouver, ISO e altri

Klatzky, Roberta L., and Nicholas A. Giudice. "The planar mosaic fails to account for spatially directed action." Behavioral and Brain Sciences 36, no. 5 (2013): 554–55. http://dx.doi.org/10.1017/s0140525x13000435.

Testo completo

Abstract (sommario):

AbstractHumans' spatial representations enable navigation and reaching to targets above the ground plane, even without direct perceptual support. Such abilities are inconsistent with an impoverished representation of the third dimension. Features that differentiate humans from most terrestrial animals, including raised eye height and arms dedicated to manipulation rather than locomotion, have led to robust metric representations of volumetric space.

Gli stili APA, Harvard, Vancouver, ISO e altri

Benda, Natalie C., and Ann M. Bisantz. "Prototypical Work Situations: A Robust, Flexible Means for Representing Activity in a Work Domain." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 63, no. 1 (2019): 337–41. http://dx.doi.org/10.1177/1071181319631089.

Testo completo

Abstract (sommario):

Representing the results is a key component in the analysis of cognitive work. Many structures have been developed for representing the results of Cognitive Work Analysis, but the representation of activity through “prototypical work situations” is less commonly utilized. Prototypical work situations, initially described by Rasmussen, convey summaries of actual activities that represent the key properties of work in a domain. This study illustrates the utility of prototypical work situation representations through a demonstrative case example. Specifically, representations of prototypical work situations were utilized to summarize and compare communication with patients in the emergency department across multiple situations. Via the case example, we demonstrate how representations of prototypical work situations can be leveraged to summarize results, elicit feedback, and design and test new tools to support cognitive, collaborative work. We also provide a revised structure for creating prototypical representations of work that can be adapted and utilized in future studies.

Gli stili APA, Harvard, Vancouver, ISO e altri

Mehrmann, V., and P. Van Dooren. "Optimal robustness of passive discrete-time systems." IMA Journal of Mathematical Control and Information 37, no. 4 (2020): 1248–69. http://dx.doi.org/10.1093/imamci/dnaa013.

Testo completo

Abstract (sommario):

Abstract We study different representations of a given rational transfer function that represents a passive (or positive real) discrete-time system. When the system is subject to perturbations, passivity or stability may be lost. To make the system robust, we use the freedom in the representation to characterize and construct optimally robust representations in the sense that the distance to non-passivity is maximized with respect to an appropriate matrix norm. We link this construction to the solution set of certain linear matrix inequalities defining passivity of the transfer function. We present an algorithm to compute a nearly optimal representation using an eigenvalue optimization technique. We also briefly consider the problem of finding the nearest passive system to a given non-passive one.

Gli stili APA, Harvard, Vancouver, ISO e altri

Giese, Martin A. "Mirror representations innate versus determined by experience: A viewpoint from learning theory." Behavioral and Brain Sciences 37, no. 2 (2014): 201–2. http://dx.doi.org/10.1017/s0140525x13002306.

Testo completo

Abstract (sommario):

AbstractFrom the viewpoint of pattern recognition and computational learning, mirror neurons form an interesting multimodal representation that links action perception and planning. While it seems unlikely that all details of such representations are specified by the genetic code, robust learning of such complex representations likely requires an appropriate interplay between plasticity, generalization, and anatomical constraints of the underlying neural architecture.

Gli stili APA, Harvard, Vancouver, ISO e altri

Liu, Qiyuan, Qi Zhou, Rui Yang, and Jie Wang. "Robust Representation Learning by Clustering with Bisimulation Metrics for Visual Reinforcement Learning with Distractions." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 7 (2023): 8843–51. http://dx.doi.org/10.1609/aaai.v37i7.26063.

Testo completo

Abstract (sommario):

Recent work has shown that representation learning plays a critical role in sample-efficient reinforcement learning (RL) from pixels. Unfortunately, in real-world scenarios, representation learning is usually fragile to task-irrelevant distractions such as variations in background or viewpoint. To tackle this problem, we propose a novel clustering-based approach, namely Clustering with Bisimulation Metrics (CBM), which learns robust representations by grouping visual observations in the latent space. Specifically, CBM alternates between two steps: (1) grouping observations by measuring their bisimulation distances to the learned prototypes; (2) learning a set of prototypes according to the current cluster assignments. Computing cluster assignments with bisimulation metrics enables CBM to capture task-relevant information, as bisimulation metrics quantify the behavioral similarity between observations. Moreover, CBM encourages the consistency of representations within each group, which facilitates filtering out task-irrelevant information and thus induces robust representations against distractions. An appealing feature is that CBM can achieve sample-efficient representation learning even if multiple distractions exist simultaneously. Experiments demonstrate that CBM significantly improves the sample efficiency of popular visual RL algorithms and achieves state-of-the-art performance on both multiple and single distraction settings. The code is available at https://github.com/MIRALab-USTC/RL-CBM.

Gli stili APA, Harvard, Vancouver, ISO e altri

Kikumoto, Atsushi, and Ulrich Mayr. "Conjunctive representations that integrate stimuli, responses, and rules are critical for action selection." Proceedings of the National Academy of Sciences 117, no. 19 (2020): 10603–8. http://dx.doi.org/10.1073/pnas.1922166117.

Testo completo

Abstract (sommario):

People can use abstract rules to flexibly configure and select actions for specific situations, yet how exactly rules shape actions toward specific sensory and/or motor requirements remains unclear. Both research from animal models and human-level theories of action control point to the role of highly integrated, conjunctive representations, sometimes referred to as event files. These representations are thought to combine rules with other, goal-relevant sensory and motor features in a nonlinear manner and represent a necessary condition for action selection. However, so far, no methods exist to track such representations in humans during action selection with adequate temporal resolution. Here, we applied time-resolved representational similarity analysis to the spectral-temporal profiles of electroencephalography signals while participants performed a cued, rule-based action selection task. In two experiments, we found that conjunctive representations were active throughout the entire selection period and were functionally dissociable from the representation of constituent features. Specifically, the strength of conjunctions was a highly robust predictor of trial-by-trial variability in response times and was selectively related to an important behavioral indicator of conjunctive representations, the so-called partial-overlap priming pattern. These results provide direct evidence for conjunctive representations as critical precursors of action selection in humans.

Gli stili APA, Harvard, Vancouver, ISO e altri

Zhang, Binghui, Sayedeh Leila Noorbakhsh, Yun Dong, Yuan Hong, and Binghui Wang. "Learning Robust and Privacy-Preserving Representations via Information Theory." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 21 (2025): 22363–71. https://doi.org/10.1609/aaai.v39i21.34392.

Testo completo

Abstract (sommario):

Machine learning models are vulnerable to both security attacks (e.g., adversarial examples) and privacy attacks (e.g., private attribute inference). We take the first step to mitigate both the security and privacy attacks, and maintain task utility as well. Particularly, we propose an information-theoretic framework to achieve the goals through the lens of representation learning, i.e., learning representations that are robust to both adversarial examples and attribute inference adversaries. We also derive novel theoretical results under our framework, e.g., the inherent trade-off between adversarial robustness/utility and attribute privacy, and guaranteed attribute privacy leakage against attribute inference adversaries.

Gli stili APA, Harvard, Vancouver, ISO e altri

Yue, Zhihan, Yujing Wang, Juanyong Duan, et al. "TS2Vec: Towards Universal Representation of Time Series." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 8 (2022): 8980–87. http://dx.doi.org/10.1609/aaai.v36i8.20881.

Testo completo

Abstract (sommario):

This paper presents TS2Vec, a universal framework for learning representations of time series in an arbitrary semantic level. Unlike existing methods, TS2Vec performs contrastive learning in a hierarchical way over augmented context views, which enables a robust contextual representation for each timestamp. Furthermore, to obtain the representation of an arbitrary sub-sequence in the time series, we can apply a simple aggregation over the representations of corresponding timestamps. We conduct extensive experiments on time series classification tasks to evaluate the quality of time series representations. As a result, TS2Vec achieves significant improvement over existing SOTAs of unsupervised time series representation on 125 UCR datasets and 29 UEA datasets. The learned timestamp-level representations also achieve superior results in time series forecasting and anomaly detection tasks. A linear regression trained on top of the learned representations outperforms previous SOTAs of time series forecasting. Furthermore, we present a simple way to apply the learned representations for unsupervised anomaly detection, which establishes SOTA results in the literature. The source code is publicly available at https://github.com/yuezhihan/ts2vec.

Gli stili APA, Harvard, Vancouver, ISO e altri

James, M. R., M. C. Smith, and G. Vinnicombe. "Gap Metrics, Representations, and Nonlinear Robust Stability." SIAM Journal on Control and Optimization 43, no. 5 (2005): 1535–82. http://dx.doi.org/10.1137/s0363012901393067.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Martins, P., P. Carvalho, and C. Gatta. "Context-aware features and robust image representations." Journal of Visual Communication and Image Representation 25, no. 2 (2014): 339–48. http://dx.doi.org/10.1016/j.jvcir.2013.10.006.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Skočaj, Danijel, Aleš Leonardis, and Horst Bischof. "Weighted and robust learning of subspace representations." Pattern Recognition 40, no. 5 (2007): 1556–69. http://dx.doi.org/10.1016/j.patcog.2006.09.019.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Beattie, Christopher A., Volker Mehrmann, and Paul Van Dooren. "Robust port-Hamiltonian representations of passive systems." Automatica 100 (February 2019): 182–86. http://dx.doi.org/10.1016/j.automatica.2018.11.013.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Hu, Chun-Yi, Nicholas M. Patrikalakis, and Xiuzi Ye. "Robust interval solid modelling Part I: representations." Computer-Aided Design 28, no. 10 (1996): 807–17. http://dx.doi.org/10.1016/0010-4485(96)00013-9.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Skočaj, Danijel, and Aleš Leonardis. "Incremental and robust learning of subspace representations." Image and Vision Computing 26, no. 1 (2008): 27–38. http://dx.doi.org/10.1016/j.imavis.2005.07.028.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Roschewitz, Mélanie, Fabio De Sousa Ribeiro, Tian Xia, Galvin Khara, and Ben Glocker. "Robust image representations with counterfactual contrastive learning." Medical Image Analysis 105 (October 2025): 103668. https://doi.org/10.1016/j.media.2025.103668.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Kountzakis, Christos E., and Damiano Rossello. "Risk Measures’ Duality on Ordered Linear Spaces." Mathematics 12, no. 8 (2024): 1165. http://dx.doi.org/10.3390/math12081165.

Testo completo

Abstract (sommario):

The aim of this paper is to provide a dual representation of convex and coherent risk measures in partially ordered linear spaces with respect to the algebraic dual space. An algebraic robust representation is deduced by weak separation of convex sets by functionals, which are assumed to be only linear; thus, our framework does not require any topological structure of the underlying spaces, and our robust representations are found without any continuity requirement for the risk measures. We also use such extensions to the representation of acceptability indices.

Gli stili APA, Harvard, Vancouver, ISO e altri

Silva, Samuel Henrique, Arun Das, Adel Aladdini, and Peyman Najafirad. "Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purification on Social Networks." Proceedings of the International AAAI Conference on Web and Social Media 16 (May 31, 2022): 968–79. http://dx.doi.org/10.1609/icwsm.v16i1.19350.

Testo completo

Abstract (sommario):

Advances in Artificial Intelligence (AI) have made it possible to automate human-level visual search and perception tasks on the massive sets of image data shared on social media on a daily basis. However, AI-based automated filters are highly susceptible to deliberate image attacks that can lead to content misclassification of cyberbulling, child sexual abuse material (CSAM), adult content, and deepfakes. One of the most effective methods to defend against such disturbances is adversarial training, but this comes at the cost of generalization for unseen attacks and transferability across models. In this article, we propose a robust defense against adversarial image attacks, which is model agnostic and generalizable to unseen adversaries. We begin with a baseline model, extracting the latent representations for each class and adaptively clustering the latent representations that share a semantic similarity. Next, we obtain the distributions for these clustered latent representations along with their originating images. We then learn semantic reconstruction dictionaries (SRD). We adversarially train a new model constraining the latent space representation to minimize the distance between the adversarial latent representation and the true cluster distribution. To purify the image, we decompose the input into low and high-frequency components. The high-frequency component is reconstructed based on the best SRD from the clean dataset. In order to evaluate the best SRD, we rely on the distance between the robust latent representations and semantic cluster distributions. The output is a purified image with no perturbations. Evaluations using comprehensive datasets including image benchmarks and social media images demonstrate that our proposed purification approach guards and enhances the accuracy of AI-based image filters for unlawful and harmful perturbed images considerably.

Gli stili APA, Harvard, Vancouver, ISO e altri

Wahutu, J. Siguru. "‘In the case of Africa in general, there is a tendency to exaggerate’: representing mass atrocity in Africa." Media, Culture & Society 39, no. 6 (2017): 919–29. http://dx.doi.org/10.1177/0163443717692737.

Testo completo

Abstract (sommario):

Based on an analysis of print media and journalists’ interviews, this article examines the representation of atrocity and mass violence in Africa. It specifically focuses on the atrocities in Darfur and Rwanda and compares African and Western coverage of them. It argues that since representations (just as the knowledge that anchors them) are highly dependent on one’s social location, it is necessary to understand multiple representations of the same atrocity. Although the literature on representation of Africa has been critical of Western representations of Africa, this article argues that including African representations of the same provides for a more nuanced understanding. It uses interview data from Kenya and South Africa, both of which have had peacekeeping engagements in Sudan. Kenya and South Africa also have media fields that are more robust and freer than many other countries in the continent.

Gli stili APA, Harvard, Vancouver, ISO e altri

Gao, Hang, Jiangmeng Li, Wenwen Qiang, et al. "Robust Causal Graph Representation Learning against Confounding Effects." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 6 (2023): 7624–32. http://dx.doi.org/10.1609/aaai.v37i6.25925.

Testo completo

Abstract (sommario):

The prevailing graph neural network models have achieved significant progress in graph representation learning. However, in this paper, we uncover an ever-overlooked phenomenon: the pre-trained graph representation learning model tested with full graphs underperforms the model tested with well-pruned graphs. This observation reveals that there exist confounders in graphs, which may interfere with the model learning semantic information, and current graph representation learning methods have not eliminated their influence. To tackle this issue, we propose Robust Causal Graph Representation Learning (RCGRL) to learn robust graph representations against confounding effects. RCGRL introduces an active approach to generate instrumental variables under unconditional moment restrictions, which empowers the graph representation learning model to eliminate confounders, thereby capturing discriminative information that is causally related to downstream predictions. We offer theorems and proofs to guarantee the theoretical effectiveness of the proposed approach. Empirically, we conduct extensive experiments on a synthetic dataset and multiple benchmark datasets. Experimental results demonstrate the effectiveness and generalization ability of RCGRL. Our codes are available at https://github.com/hang53/RCGRL.

Gli stili APA, Harvard, Vancouver, ISO e altri

Espinosa Zarlenga, Mateo, Pietro Barbiero, Zohreh Shams, et al. "Towards Robust Metrics for Concept Representation Evaluation." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 10 (2023): 11791–99. http://dx.doi.org/10.1609/aaai.v37i10.26392.

Testo completo

Abstract (sommario):

Recent work on interpretability has focused on concept-based explanations, where deep learning models are explained in terms of high-level units of information, referred to as concepts. Concept learning models, however, have been shown to be prone to encoding impurities in their representations, failing to fully capture meaningful features of their inputs. While concept learning lacks metrics to measure such phenomena, the field of disentanglement learning has explored the related notion of underlying factors of variation in the data, with plenty of metrics to measure the purity of such factors. In this paper, we show that such metrics are not appropriate for concept learning and propose novel metrics for evaluating the purity of concept representations in both approaches. We show the advantage of these metrics over existing ones and demonstrate their utility in evaluating the robustness of concept representations and interventions performed on them. In addition, we show their utility for benchmarking state-of-the-art methods from both families and find that, contrary to common assumptions, supervision alone may not be sufficient for pure concept representations.

Gli stili APA, Harvard, Vancouver, ISO e altri

Chen, Feiqiong, Guopeng Li, Shuaihui Wang, and Zhisong Pan. "Multiview Clustering via Robust Neighboring Constraint Nonnegative Matrix Factorization." Mathematical Problems in Engineering 2019 (November 23, 2019): 1–10. http://dx.doi.org/10.1155/2019/6084382.

Testo completo

Abstract (sommario):

Many real-world datasets are described by multiple views, which can provide complementary information to each other. Synthesizing multiview features for data representation can lead to more comprehensive data description for clustering task. However, it is often difficult to preserve the locally real structure in each view and reconcile the noises and outliers among views. In this paper, instead of seeking for the common representation among views, a novel robust neighboring constraint nonnegative matrix factorization (rNNMF) is proposed to learn the neighbor structure representation in each view, and L2,1-norm-based loss function is designed to improve its robustness against noises and outliers. Then, a final comprehensive representation of data was integrated with those representations of multiviews. Finally, a neighboring similarity graph was learned and the graph cut method was used to partition data into its underlying clusters. Experimental results on several real-world datasets have shown that our model achieves more accurate performance in multiview clustering compared to existing state-of-the-art methods.

Gli stili APA, Harvard, Vancouver, ISO e altri

Bowman, Sean, Kostas Daniilidis, and George Pappas. "Robust Object-Level Semantic Visual SLAM Using Semantic Keypoints." Field Robotics 2, no. 1 (2022): 513–24. http://dx.doi.org/10.55417/fr.2022018.

Testo completo

Abstract (sommario):

Simultaneous Localization and Mapping (SLAM) has traditionally relied on representing the environment as low-level, geometric features, such as points, lines, and planes. Recent advances in object recognition capabilities, however, as well as demand for environment representations that facilitate higher-level autonomy, have motivated an object-based Semantic SLAM. We present a Semantic SLAM algorithm that directly incorporates a sparse representation of objects into a factor-graph SLAM optimization, resulting in a system that is efficient, robust to varying object shapes and environments, and easy to incorporate into an existing SLAM pipeline. Our keypoint-based representation facilitates robust detection in varying conditions and intraclass shape variation, as well as computational efficiency. We demonstrate the performance of our algorithm in two different SLAM systems and in varying environments.

Gli stili APA, Harvard, Vancouver, ISO e altri

Nguyễn, Tuấn, Nguyen Hai Hao, Dang Le Dinh Trang, Nguyen Van Tuan, and Cao Van Loi. "Robust anomaly detection methods for contamination network data." Journal of Military Science and Technology, no. 79 (May 19, 2022): 41–51. http://dx.doi.org/10.54939/1859-1043.j.mst.79.2022.41-51.

Testo completo

Abstract (sommario):

Recently, latent representation models, such as Shrink Autoencoder (SAE), have been demonstrated as robust feature representations for one-class learning-based network anomaly detection. In these studies, benchmark network datasets that are processed in laboratory environments to make them completely clean are often employed for constructing and evaluating such models. In real-world scenarios, however, we can not guarantee 100% to collect pure normal data for constructing latent representation models. Therefore, this work aims to investigate the characteristics of the latent representation of SAE in learning normal data under some contamination scenarios. This attempts to find out wherever the latent feature space of SAE is robust to contamination or not, and which contamination scenarios it prefers. We design a set of experiments using normal data contaminated with different anomaly types and different proportions of anomalies for the investigation. Other latent representation methods such as Denoising Autoencoder (DAE) and Principal component analysis (PCA) are also used for comparison with the performance of SAE. The experimental results on four CTU13 scenarios show that the latent representation of SAE often out-performs and are less sensitive to contamination than the others.

Gli stili APA, Harvard, Vancouver, ISO e altri

Cook, Svetlana V., and Kira Gor. "Lexical access in L2." Mental Lexicon 10, no. 2 (2015): 247–70. http://dx.doi.org/10.1075/ml.10.2.04coo.

Testo completo

Abstract (sommario):

Previous research on phonological priming in a Lexical Decision Task (LDT) has demonstrated that second language (L2) learners do not show inhibition typical for native (L1) speakers that results from lexical competition, but rather a reversed effect – facilitation (Gor, Cook, & Jackson, 2010). The present study investigates the source of the reversed priming effect and addresses two possible causes: a deficit in lexical representations and a processing constraint. Twenty-three advanced learners of Russian participated in two experiments. The monolingual Russian LDT task with priming addressed the processing constraint by manipulating the interstimulus interval (ISI, 350 ms and 500 ms). The translation task evaluated the robustness of lexical representations at both the phonolexical level (whole-word phonological representation) and the level of form-to-meaning mapping, thereby addressing the lexical deficit. L2 learners did not benefit from an increased ISI, indicating lack of support for the processing constraint. However, the study, found evidence for the representational deficit: when L2 familiarity with the words is controlled and L2 representations are robust, L2 learners demonstrate native-like processing accompanied by inhibition; however, when the words have fragmented (or fuzzy) representations, L2 lexical access is unfaithful and is accompanied by reduced lexical competition leading to facilitation effects.

Gli stili APA, Harvard, Vancouver, ISO e altri

Choi, Jaewoong, Daeha Kim, and Byung Cheol Song. "Style-Guided and Disentangled Representation for Robust Image-to-Image Translation." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 1 (2022): 463–71. http://dx.doi.org/10.1609/aaai.v36i1.19924.

Testo completo

Abstract (sommario):

Recently, various image-to-image translation (I2I) methods have improved mode diversity and visual quality in terms of neural networks or regularization terms. However, conventional I2I methods relies on a static decision boundary and the encoded representations in those methods are entangled with each other, so they often face with ‘mode collapse’ phenomenon. To mitigate mode collapse, 1) we design a so-called style-guided discriminator that guides an input image to the target image style based on the strategy of flexible decision boundary. 2) Also, we make the encoded representations include independent domain attributes. Based on two ideas, this paper proposes Style-Guided and Disentangled Representation for Robust Image-to-Image Translation (SRIT). SRIT showed outstanding FID by 8%, 22.8%, and 10.1% for CelebA-HQ, AFHQ, and Yosemite datasets, respectively. The translated images of SRIT reflect the styles of target domain successfully. This indicates that SRIT shows better mode diversity than previous works.

Gli stili APA, Harvard, Vancouver, ISO e altri

Apostolico, A., and A. Fraenkel. "Robust transmission of unbounded strings using Fibonacci representations." IEEE Transactions on Information Theory 33, no. 2 (1987): 238–45. http://dx.doi.org/10.1109/tit.1987.1057284.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Tong, Frank, and Ken Nakayama. "Robust representations for faces: Evidence from visual search." Journal of Experimental Psychology: Human Perception and Performance 25, no. 4 (1999): 1016–35. http://dx.doi.org/10.1037/0096-1523.25.4.1016.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Mancini, Massimiliano, Samuel Rota Bulo, Elisa Ricci, and Barbara Caputo. "Learning Deep NBNN Representations for Robust Place Categorization." IEEE Robotics and Automation Letters 2, no. 3 (2017): 1794–801. http://dx.doi.org/10.1109/lra.2017.2705282.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Hu, Xing, Shiqiang Hu, Jinhua Xie, and Shiyou Zheng. "Robust and efficient anomaly detection using heterogeneous representations." Journal of Electronic Imaging 24, no. 3 (2015): 033021. http://dx.doi.org/10.1117/1.jei.24.3.033021.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Sheng, Bin, Bowen Liu, Ping Li, Hongbo Fu, Lizhuang Ma, and Enhua Wu. "Accelerated robust Boolean operations based on hybrid representations." Computer Aided Geometric Design 62 (May 2018): 133–53. http://dx.doi.org/10.1016/j.cagd.2018.03.021.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Wong, Alexander, and Jeff Orchard. "Robust Multimodal Registration Using Local Phase-Coherence Representations." Journal of Signal Processing Systems 54, no. 1-3 (2008): 89–100. http://dx.doi.org/10.1007/s11265-008-0202-x.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Liu, J., B. C. Vemuri, and J. L. Marroquin. "Local frequency representations for robust multimodal image registration." IEEE Transactions on Medical Imaging 21, no. 5 (2002): 462–69. http://dx.doi.org/10.1109/tmi.2002.1009382.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Schwarz, Baruch. "Why Can Intermediate Abstractions Help Acquire Robust Representations?" Interactive Learning Environments 5, no. 1 (1998): 181–203. http://dx.doi.org/10.1080/1049482980050112.

Testo completo

Gli stili APA, Harvard, Vancouver, ISO e altri

Li, Siyuan, Xun Wang, Rongchang Zuo, et al. "Robust Visual Imitation Learning with Inverse Dynamics Representations." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 12 (2024): 13609–18. http://dx.doi.org/10.1609/aaai.v38i12.29265.

Testo completo

Abstract (sommario):

Imitation learning (IL) has achieved considerable success in solving complex sequential decision-making problems. However, current IL methods mainly assume that the environment for learning policies is the same as the environment for collecting expert datasets. Therefore, these methods may fail to work when there are slight differences between the learning and expert environments, especially for challenging problems with high-dimensional image observations. However, in real-world scenarios, it is rare to have the chance to collect expert trajectories precisely in the target learning environment. To address this challenge, we propose a novel robust imitation learning approach, where we develop an inverse dynamics state representation learning objective to align the expert environment and the learning environment. With the abstract state representation, we design an effective reward function, which thoroughly measures the similarity between behavior data and expert data not only element-wise, but also from the trajectory level. We conduct extensive experiments to evaluate the proposed approach under various visual perturbations and in diverse visual control tasks. Our approach can achieve a near-expert performance in most environments, and significantly outperforms the state-of-the-art visual IL methods and robust IL methods.

Gli stili APA, Harvard, Vancouver, ISO e altri

Dai, Wengui, and Yujun Wang. "Web Semantic-Based Robust Graph Contrastive Learning for Recommendation via Invariant Learning." International Journal on Semantic Web and Information Systems 20, no. 1 (2024): 1–15. http://dx.doi.org/10.4018/ijswis.337962.

Testo completo

Abstract (sommario):

The use of contrastive learning (CL) in recommendation has advanced significantly. Recently, some works use perturbations in the embedding space to obtain enhanced views of nodes. This makes the representation distribution of nodes more even and then improve recommendation effectiveness. In this article, the authors provide an explanation on the role of added noises in the embedding space from the perspective of invariant learning and feature selection. Guided by this thinking, the authors devise a more reasonable method for generating random noises and put forward web semantic based robust graph contrastive learning for recommendation via invariant learning, a novel graph CL-based recommendation model, named RobustGCL. RobustGCL, randomly zeros the values of certain dimensions in the noise vectors at a fixed ratio. In this way, RobustGCL can identify invariant and variant features and then learn invariant and variant representations. Tests on publicly available datasets show that our proposed approach can learn invariant representations and achieve better performance.

Gli stili APA, Harvard, Vancouver, ISO e altri

Hu, Dou, Lingwei Wei, Wei Zhou, and Songlin Hu. "An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 16 (2025): 17276–86. https://doi.org/10.1609/aaai.v39i16.33899.

Testo completo

Abstract (sommario):

This paper proposes a new principled multi-task representation learning framework (InfoMTL) to extract noise-invariant sufficient representations for all tasks. It ensures sufficiency of shared representations for all tasks and mitigates the negative effect of redundant features, which can enhance language understanding of pre-trained language models (PLMs) under the multi-task paradigm. Firstly, a shared information maximization principle is proposed to learn more sufficient shared representations for all target tasks. It can avoid the insufficiency issue arising from representation compression in the multi-task paradigm. Secondly, a task-specific information minimization principle is designed to mitigate the negative effect of potential redundant features in the input for each task. It can compress task-irrelevant redundant information and preserve necessary information relevant to the target for multi-task prediction. Experiments on six classification benchmarks show that our method outperforms 12 comparative multi-task methods under the same multi-task settings, especially in data-constrained and noisy scenarios. Extensive experiments demonstrate that the learned representations are more sufficient, data-efficient, and robust.

Gli stili APA, Harvard, Vancouver, ISO e altri

Wang, Leilei, Si Shi, Fei Ma, Fei Richard Yu, Pengteng Li, and Ying Tiffany He. "Subgraph Invariant Learning Towards Large-Scale Graph Node Classification." Proceedings of the AAAI Conference on Artificial Intelligence 39, no. 20 (2025): 21144–52. https://doi.org/10.1609/aaai.v39i20.35412.

Testo completo

Abstract (sommario):

Graph Neural Networks (GNNs) have shown efficacy in graph node classification, but face computational challenges on large-scale graphs. Although existing graph reduction methods address these issues, they still require high computational resources and fail to prioritize robust performance on out-of-distribution data. To tackle these challenges, we introduce the subgraph invariant learning paradigm, inspired by the small-world phenomenon. This approach enables models trained on specific subgraphs to generalize across diverse subgraphs, reducing computational demands, and enhancing scalability. To promote generalization, we maximize the invariance log-likelihood by deriving a theoretical lower bound of it and formulating the InVar loss. This loss minimizes the discrepancy between node representations and their corresponding invariance representations while maximizing the entropy of the node representation. In response to InVar loss, we propose the Invariance Facilitation Model (IFM), comprising the Invariance Representation Encoder (IRE) and Node Representation Encoder (NRE). IRE, capturing the invariance representations, utilizes Invariance ATTention (InvarATT) to compress long-range dependencies, while NRE learns the node representation, by integrating invariance representations via Telematic ATTention (TeleATT) and exchanging local information within each subgraph through GNNs. Evaluations on four large-scale graph datasets demonstrate the effectiveness, computational efficiency, and interpretability of IFM for large-scale graph node classification.

Gli stili APA, Harvard, Vancouver, ISO e altri

Offriamo sconti su tutti i piani premium per gli autori le cui opere sono incluse in raccolte letterarie tematiche. Contattaci per ottenere un codice promozionale unico!