Log in

Relevant bibliographies by topics / Convolution Neural Networks(CNN's) / Journal articles

To see the other types of publications on this topic, follow the link: Convolution Neural Networks(CNN's).

Journal articles on the topic 'Convolution Neural Networks(CNN's)'

Author: Grafiati

Published: 4 June 2021

Last updated: 14 February 2022

Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles

Select a source type:

Consult the top 50 journal articles for your research on the topic 'Convolution Neural Networks(CNN's).'

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 journal articles on a wide variety of disciplines and organise your bibliography correctly.

1

Sarabu, Ashok, and Ajit Kumar Santra. "Human Action Recognition in Videos using Convolution Long Short-Term Memory Network with Spatio-Temporal Networks." Emerging Science Journal 5, no. 1 (2021): 25–33. http://dx.doi.org/10.28991/esj-2021-01254.

Full text

Abstract:

Two-stream convolutional networks plays an essential role as a powerful feature extractor in human action recognition in videos. Recent studies have shown the importance of two-stream Convolutional Neural Networks (CNN) to recognize human action recognition. Recurrent Neural Networks (RNN) has achieved the best performance in video activity recognition combining CNN. Encouraged by CNN's results with RNN, we present a two-stream network with two CNNs and Convolution Long-Short Term Memory (CLSTM). First, we extricate Spatio-temporal features using two CNNs using pre-trained ImageNet models. Sec

APA, Harvard, Vancouver, ISO, and other styles

2

Kim, HyunJin. "AresB-Net: accurate residual binarized neural networks using shortcut concatenation and shuffled grouped convolution." PeerJ Computer Science 7 (March 26, 2021): e454. http://dx.doi.org/10.7717/peerj-cs.454.

Full text

Abstract:

This article proposes a novel network model to achieve better accurate residual binarized convolutional neural networks (CNNs), denoted as AresB-Net. Even though residual CNNs enhance the classification accuracy of binarized neural networks with increasing feature resolution, the degraded classification accuracy is still the primary concern compared with real-valued residual CNNs. AresB-Net consists of novel basic blocks to amortize the severe error from the binarization, suggesting a well-balanced pyramid structure without downsampling convolution. In each basic block, the shortcut is added t

APA, Harvard, Vancouver, ISO, and other styles

3

Cho, Hyungmin. "RiSA: A Reinforced Systolic Array for Depthwise Convolutions and Embedded Tensor Reshaping." ACM Transactions on Embedded Computing Systems 20, no. 5s (2021): 1–20. http://dx.doi.org/10.1145/3476984.

Full text

Abstract:

Depthwise convolutions are widely used in convolutional neural networks (CNNs) targeting mobile and embedded systems. Depthwise convolution layers reduce the computation loads and the number of parameters compared to the conventional convolution layers. Many deep neural network (DNN) accelerators adopt an architecture that exploits the high data-reuse factor of DNN computations, such as a systolic array. However, depthwise convolutions have low data-reuse factor and under-utilize the processing elements (PEs) in systolic arrays. In this paper, we present a DNN accelerator design called RiSA, w

APA, Harvard, Vancouver, ISO, and other styles

4

Park, Sang-Soo, and Ki-Seok Chung. "CENNA: Cost-Effective Neural Network Accelerator." Electronics 9, no. 1 (2020): 134. http://dx.doi.org/10.3390/electronics9010134.

Full text

Abstract:

Convolutional neural networks (CNNs) are widely adopted in various applications. State-of-the-art CNN models deliver excellent classification performance, but they require a large amount of computation and data exchange because they typically employ many processing layers. Among these processing layers, convolution layers, which carry out many multiplications and additions, account for a major portion of computation and memory access. Therefore, reducing the amount of computation and memory access is the key for high-performance CNNs. In this study, we propose a cost-effective neural network a

APA, Harvard, Vancouver, ISO, and other styles

5

Yin, Wenpeng, and Hinrich Schütze. "Attentive Convolution: Equipping CNNs with RNN-style Attention Mechanisms." Transactions of the Association for Computational Linguistics 6 (December 2018): 687–702. http://dx.doi.org/10.1162/tacl_a_00249.

Full text

Abstract:

In NLP, convolutional neural networks (CNNs) have benefited less than recurrent neural networks (RNNs) from attention mechanisms. We hypothesize that this is because the attention in CNNs has been mainly implemented as attentive pooling (i.e., it is applied to pooling) rather than as attentive convolution (i.e., it is integrated into convolution). Convolution is the differentiator of CNNs in that it can powerfully model the higher-level representation of a word by taking into account its local fixed-size context in the input text t x. In this work, we propose an attentive convolution network,

APA, Harvard, Vancouver, ISO, and other styles

6

Srinivas, K., B. Kavitha Rani, M. Varaprasad Rao, G. Madhukar, and B. Venkata Ramana. "Convolution Neural Networks for Binary Classification." Journal of Computational and Theoretical Nanoscience 16, no. 11 (2019): 4877–82. http://dx.doi.org/10.1166/jctn.2019.8399.

Full text

Abstract:

Convolutional neural networks (CNNs) are similar to “ordinary” neural networks in the sense that they are made up of hidden layers consisting of neurons with “learnable” parameters. These neurons receive inputs, perform a dot product, and then follows it with a non-linearity. The whole network expresses the mapping between raw image pixels and their class scores. Conventionally, the Softmax function is the classifier used at the last layer of this network. However, there have been studies conducted to challenge this norm. Empirical data has shown that the CNN model was able to achieve a test a

APA, Harvard, Vancouver, ISO, and other styles

7

Fuhl, Wolfgang, Gjergji Kasneci, Wolfgang Rosenstiel, and Enkeljda Kasneci. "Training Decision Trees as Replacement for Convolution Layers." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 3882–89. http://dx.doi.org/10.1609/aaai.v34i04.5801.

Full text

Abstract:

We present an alternative layer to convolution layers in convolutional neural networks (CNNs). Our approach reduces the complexity of convolutions by replacing it with binary decisions. Those binary decisions are used as indexes to conditional distributions where each weight represents a leaf in a decision tree. This means that only the indices to the weights need to be determined once, thus reducing the complexity of convolutions by the depth of the output tensor. Index computation is performed by simple binary decisions that require fewer cycles compared to conventionally used multiplication

APA, Harvard, Vancouver, ISO, and other styles

8

Wang, Aili, Minhui Wang, Kaiyuan Jiang, Mengqing Cao, and Yuji Iwahori. "A Dual Neural Architecture Combined SqueezeNet with OctConv for LiDAR Data Classification." Sensors 19, no. 22 (2019): 4927. http://dx.doi.org/10.3390/s19224927.

Full text

Abstract:

Light detection and ranging (LiDAR) is a frequently used technique of data acquisition and it is widely used in diverse practical applications. In recent years, deep convolutional neural networks (CNNs) have shown their effectiveness for LiDAR-derived rasterized digital surface models (LiDAR-DSM) data classification. However, many excellent CNNs have too many parameters due to depth and complexity. Meanwhile, traditional CNNs have spatial redundancy because different convolution kernels scan and store information independently. SqueezeNet replaces a part of 3 × 3 convolution kernels in CNNs wi

APA, Harvard, Vancouver, ISO, and other styles

9

He, Chu, Zishan Shi, Tao Qu, Dingwen Wang, and Mingsheng Liao. "Lifting Scheme-Based Deep Neural Network for Remote Sensing Scene Classification." Remote Sensing 11, no. 22 (2019): 2648. http://dx.doi.org/10.3390/rs11222648.

Full text

Abstract:

Recently, convolutional neural networks (CNNs) achieve impressive results on remote sensing scene classification, which is a fundamental problem for scene semantic understanding. However, convolution, the most essential operation in CNNs, restricts the development of CNN-based methods for scene classification. Convolution is not efficient enough for high-resolution remote sensing images and limited in extracting discriminative features due to its linearity. Thus, there has been growing interest in improving the convolutional layer. The hardware implementation of the JPEG2000 standard relies on

APA, Harvard, Vancouver, ISO, and other styles

10

Dong, Hongwei, Lamei Zhang, and Bin Zou. "PolSAR Image Classification with Lightweight 3D Convolutional Networks." Remote Sensing 12, no. 3 (2020): 396. http://dx.doi.org/10.3390/rs12030396.

Full text

Abstract:

Convolutional neural networks (CNNs) have become the state-of-the-art in optical image processing. Recently, CNNs have been used in polarimetric synthetic aperture radar (PolSAR) image classification and obtained promising results. Unlike optical images, the unique phase information of PolSAR data expresses the structure information of objects. This special data representation makes 3D convolution which explicitly modeling the relationship between polarimetric channels perform better in the task of PolSAR image classification. However, the development of deep 3D-CNNs will cause a huge number o

APA, Harvard, Vancouver, ISO, and other styles

11

Zeng, Guozhao, Xiao Hu, and Yueyue Chen. "Optimizing Convolution Neural Network on the TI C6678 multicore DSP." MATEC Web of Conferences 246 (2018): 03044. http://dx.doi.org/10.1051/matecconf/201824603044.

Full text

Abstract:

Convolutional Neural Networks (CNNs) have become the most advanced algorithms for deep learning. They are widely used in image processing, object detection and automatic translation. As the demand for CNNs continues to increase, the platforms on which they are deployed continue to expand. As an excellent low-power, high-performance, embedded solution, Digital Signal Processor (DSP) is used frequently in many key areas. This paper attempts to deploy the CNN to Texas Instruments (TI)’s TMS320C6678 multi-core DSP and optimize the main operations (convolution) to accommodate the DSP structure. The

APA, Harvard, Vancouver, ISO, and other styles

12

Ding, Enjie, Yuhao Cheng, Chengcheng Xiao, Zhongyu Liu, and Wanli Yu. "Efficient Attention Mechanism for Dynamic Convolution in Lightweight Neural Network." Applied Sciences 11, no. 7 (2021): 3111. http://dx.doi.org/10.3390/app11073111.

Full text

Abstract:

Light-weight convolutional neural networks (CNNs) suffer limited feature representation capabilities due to low computational budgets, resulting in degradation in performance. To make CNNs more efficient, dynamic neural networks (DyNet) have been proposed to increase the complexity of the model by using the Squeeze-and-Excitation (SE) module to adaptively obtain the importance of each convolution kernel through the attention mechanism. However, the attention mechanism in the SE network (SENet) selects all channel information for calculations, which brings essential challenges: (a) interference

APA, Harvard, Vancouver, ISO, and other styles

13

Zhao, Yunping, Jianzhuang Lu, and Xiaowen Chen. "An Accelerator Design Using a MTCA Decomposition Algorithm for CNNs." Sensors 20, no. 19 (2020): 5558. http://dx.doi.org/10.3390/s20195558.

Full text

Abstract:

Due to the high throughput and high computing capability of convolutional neural networks (CNNs), researchers are paying increasing attention to the design of CNNs hardware accelerator architecture. Accordingly, in this paper, we propose a block parallel computing algorithm based on the matrix transformation computing algorithm (MTCA) to realize the convolution expansion and resolve the block problem of the intermediate matrix. It enables high parallel implementation on hardware. Moreover, we also provide a specific calculation method for the optimal partition of matrix multiplication to optim

APA, Harvard, Vancouver, ISO, and other styles

14

Lin, Wenxiang, Yan Ding, Hua-Liang Wei, Xinglin Pan, and Yutong Zhang. "LdsConv: Learned Depthwise Separable Convolutions by Group Pruning." Sensors 20, no. 15 (2020): 4349. http://dx.doi.org/10.3390/s20154349.

Full text

Abstract:

Standard convolutional filters usually capture unnecessary overlap of features resulting in a waste of computational cost. In this paper, we aim to solve this problem by proposing a novel Learned Depthwise Separable Convolution (LdsConv) operation that is smart but has a strong capacity for learning. It integrates the pruning technique into the design of convolutional filters, formulated as a generic convolutional unit that can be used as a direct replacement of convolutions without any adjustments of the architecture. To show the effectiveness of the proposed method, experiments are carried o

APA, Harvard, Vancouver, ISO, and other styles

15

Kanai, Sekitoshi, Yasutoshi Ida, Yasuhiro Fujiwara, Masanori Yamada, and Shuichi Adachi. "Absum: Simple Regularization Method for Reducing Structural Sensitivity of Convolutional Neural Networks." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 4394–403. http://dx.doi.org/10.1609/aaai.v34i04.5865.

Full text

Abstract:

We propose Absum, which is a regularization method for improving adversarial robustness of convolutional neural networks (CNNs). Although CNNs can accurately recognize images, recent studies have shown that the convolution operations in CNNs commonly have structural sensitivity to specific noise composed of Fourier basis functions. By exploiting this sensitivity, they proposed a simple black-box adversarial attack: Single Fourier attack. To reduce structural sensitivity, we can use regularization of convolution filter weights since the sensitivity of linear transform can be assessed by the nor

APA, Harvard, Vancouver, ISO, and other styles

16

Leong, Mei Chee, Dilip K. Prasad, Yong Tsui Lee, and Feng Lin. "Semi-CNN Architecture for Effective Spatio-Temporal Learning in Action Recognition." Applied Sciences 10, no. 2 (2020): 557. http://dx.doi.org/10.3390/app10020557.

Full text

Abstract:

This paper introduces a fusion convolutional architecture for efficient learning of spatio-temporal features in video action recognition. Unlike 2D convolutional neural networks (CNNs), 3D CNNs can be applied directly on consecutive frames to extract spatio-temporal features. The aim of this work is to fuse the convolution layers from 2D and 3D CNNs to allow temporal encoding with fewer parameters than 3D CNNs. We adopt transfer learning from pre-trained 2D CNNs for spatial extraction, followed by temporal encoding, before connecting to 3D convolution layers at the top of the architecture. We

APA, Harvard, Vancouver, ISO, and other styles

17

Wu, Di, Jianpei Zhang, and Qingchao Zhao. "A Text Emotion Analysis Method Using the Dual-Channel Convolution Neural Network in Social Networks." Mathematical Problems in Engineering 2020 (October 3, 2020): 1–10. http://dx.doi.org/10.1155/2020/6182876.

Full text

Abstract:

In order to solve the problem that the existing deep learning method has insufficient ability in feature extraction in the text emotion classification task, this paper proposes a text emotion analysis using the dual-channel convolution neural network in the social network. First, a double-channel convolutional neural network is constructed. Combined with emotion words, parts of speech, degree adverbs, negative words, punctuation, and other word features that affect the text’s emotional tendency, an extended text feature is formed. Then, using the CNN’s multichannel mechanism, the extended text

APA, Harvard, Vancouver, ISO, and other styles

18

Gifford, Nadia, Rafiq Ahmad, and Mario Soriano Morales. "Text Recognition and Machine Learning: For Impaired Robots and Humans." Alberta Academic Review 2, no. 2 (2019): 31–32. http://dx.doi.org/10.29173/aar42.

Full text

Abstract:

As robots and machines become more reliable, developing tools that utilize their potential in manufacturing and beyond is an important step being addressed by many, including the LIMDA team at the University of Alberta. A common and effective means to improve artificial performance is through optical character recognition methods. Within the category of artificial intelligence under classification machine learning, research has focussed on the benefits of convolutional neural networks (CNN) and the improvement provided compared to its parent method, neural networks. Neural networks serious fla

APA, Harvard, Vancouver, ISO, and other styles

19

Huang, Di, Xishan Zhang, Rui Zhang, et al. "DWM: A Decomposable Winograd Method for Convolution Acceleration." Proceedings of the AAAI Conference on Artificial Intelligence 34, no. 04 (2020): 4174–81. http://dx.doi.org/10.1609/aaai.v34i04.5838.

Full text

Abstract:

Winograd's minimal filtering algorithm has been widely used in Convolutional Neural Networks (CNNs) to reduce the number of multiplications for faster processing. However, it is only effective on convolutions with kernel size as 3x3 and stride as 1, because it suffers from significantly increased FLOPs and numerical accuracy problem for kernel size larger than 3x3 and fails on convolution with stride larger than 1. In this paper, we propose a novel Decomposable Winograd Method (DWM), which breaks through the limitation of original Winograd's minimal filtering algorithm to a wide and general co

APA, Harvard, Vancouver, ISO, and other styles

20

Shi, Cuiping, Xin Zhao, and Liguo Wang. "A Multi-Branch Feature Fusion Strategy Based on an Attention Mechanism for Remote Sensing Image Scene Classification." Remote Sensing 13, no. 10 (2021): 1950. http://dx.doi.org/10.3390/rs13101950.

Full text

Abstract:

In recent years, with the rapid development of computer vision, increasing attention has been paid to remote sensing image scene classification. To improve the classification performance, many studies have increased the depth of convolutional neural networks (CNNs) and expanded the width of the network to extract more deep features, thereby increasing the complexity of the model. To solve this problem, in this paper, we propose a lightweight convolutional neural network based on attention-oriented multi-branch feature fusion (AMB-CNN) for remote sensing image scene classification. Firstly, we

APA, Harvard, Vancouver, ISO, and other styles

21

Chen, Guangsheng, Chao Li, Wei Wei, et al. "Fully Convolutional Neural Network with Augmented Atrous Spatial Pyramid Pool and Fully Connected Fusion Path for High Resolution Remote Sensing Image Segmentation." Applied Sciences 9, no. 9 (2019): 1816. http://dx.doi.org/10.3390/app9091816.

Full text

Abstract:

Recent developments in Convolutional Neural Networks (CNNs) have allowed for the achievement of solid advances in semantic segmentation of high-resolution remote sensing (HRRS) images. Nevertheless, the problems of poor classification of small objects and unclear boundaries caused by the characteristics of the HRRS image data have not been fully considered by previous works. To tackle these challenging problems, we propose an improved semantic segmentation neural network, which adopts dilated convolution, a fully connected (FC) fusion path and pre-trained encoder for the semantic segmentation

APA, Harvard, Vancouver, ISO, and other styles

22

Yan, Zhenguo, and Yue Wu. "A Neural N-Gram Network for Text Classification." Journal of Advanced Computational Intelligence and Intelligent Informatics 22, no. 3 (2018): 380–86. http://dx.doi.org/10.20965/jaciii.2018.p0380.

Full text

Abstract:

Convolutional Neural Networks (CNNs) effectively extract local features from input data. However, CNN based on word embedding and convolution layers displays poor performance in text classification tasks when compared with traditional baseline methods. We address this problem and propose a model named NNGN that simplifies the convolution layer in the CNN by replacing it with a pooling layer that extracts n-gram embedding in a simpler way and obtains document representations via linear computation. We implement two settings in our model to extract n-gram features. In the first setting, which we

APA, Harvard, Vancouver, ISO, and other styles

23

Sledevič, Tomyslav, and Artūras Serackis. "mNet2FPGA: A Design Flow for Mapping a Fixed-Point CNN to Zynq SoC FPGA." Electronics 9, no. 11 (2020): 1823. http://dx.doi.org/10.3390/electronics9111823.

Full text

Abstract:

The convolutional neural networks (CNNs) are a computation and memory demanding class of deep neural networks. The field-programmable gate arrays (FPGAs) are often used to accelerate the networks deployed in embedded platforms due to the high computational complexity of CNNs. In most cases, the CNNs are trained with existing deep learning frameworks and then mapped to FPGAs with specialized toolflows. In this paper, we propose a CNN core architecture called mNet2FPGA that places a trained CNN on a SoC FPGA. The processing system (PS) is responsible for convolution and fully connected core conf

APA, Harvard, Vancouver, ISO, and other styles

24

Hoang, Hong Hai, and Hoang Hieu Trinh. "Improvement for Convolutional Neural Networks in Image Classification Using Long Skip Connection." Applied Sciences 11, no. 5 (2021): 2092. http://dx.doi.org/10.3390/app11052092.

Full text

Abstract:

In this paper, we examine and research the effect of long skip connection on convolutional neural networks (CNNs) for the tasks of image (surface defect) classification. The standard popular models only apply short skip connection inside blocks (layers with the same size). We apply the long version of residual connection on several proposed models, which aims to reuse the lost spatial knowledge from the layers close to input. For some models, Depthwise Separable Convolution is used rather than traditional convolution in order to reduce both count of parameters and floating-point operations per

APA, Harvard, Vancouver, ISO, and other styles

25

Huang, Hongmin, Zihao Liu, Taosheng Chen, Xianghong Hu, Qiming Zhang, and Xiaoming Xiong. "Design Space Exploration for YOLO Neural Network Accelerator." Electronics 9, no. 11 (2020): 1921. http://dx.doi.org/10.3390/electronics9111921.

Full text

Abstract:

The You Only Look Once (YOLO) neural network has great advantages and extensive applications in computer vision. The convolutional layers are the most important part of the neural network and take up most of the computation time. Improving the efficiency of the convolution operations can greatly increase the speed of the neural network. Field programmable gate arrays (FPGAs) have been widely used in accelerators for convolutional neural networks (CNNs) thanks to their configurability and parallel computing. This paper proposes a design space exploration for the YOLO neural network based on FPG

APA, Harvard, Vancouver, ISO, and other styles

26

Ren, Yun, Changren Zhu, and Shunping Xiao. "Deformable Faster R-CNN with Aggregating Multi-Layer Features for Partially Occluded Object Detection in Optical Remote Sensing Images." Remote Sensing 10, no. 9 (2018): 1470. http://dx.doi.org/10.3390/rs10091470.

Full text

Abstract:

The region-based convolutional networks have shown their remarkable ability for object detection in optical remote sensing images. However, the standard CNNs are inherently limited to model geometric transformations due to the fixed geometric structures in its building modules. To address this, we introduce a new module named deformable convolution that is integrated into the prevailing Faster R-CNN. By adding 2D offsets to the regular sampling grid in the standard convolution, it learns the augmenting spatial sampling locations in the modules from target tasks without additional supervision.

APA, Harvard, Vancouver, ISO, and other styles

27

Sineglazov, Victor, and Anatoly Kot. "Design of hybrid neural networks of the ensemble structure." Eastern-European Journal of Enterprise Technologies 1, no. 4 (109) (2021): 31–45. http://dx.doi.org/10.15587/1729-4061.2021.225301.

Full text

Abstract:

This paper considers the structural-parametric synthesis (SPS) of neural networks (NNs) of deep learning, in particular convolutional neural networks (CNNs), which are used in image processing. It has been shown that modern neural networks may possess a variety of topologies. That is ensured by using unique blocks that determine their essential features, namely, the compression and excitation unit, the attention module convolution unit, the channel attention module, the spatial attention module, the residual unit, the ResNeXt block. This, first of all, is due to the need to increase their effi

APA, Harvard, Vancouver, ISO, and other styles

28

Liao, Siyu, and Bo Yuan. "CircConv: A Structured Convolution with Low Complexity." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 4287–94. http://dx.doi.org/10.1609/aaai.v33i01.33014287.

Full text

Abstract:

Deep neural networks (DNNs), especially deep convolutional neural networks (CNNs), have emerged as the powerful technique in various machine learning applications. However, the large model sizes of DNNs yield high demands on computation resource and weight storage, thereby limiting the practical deployment of DNNs. To overcome these limitations, this paper proposes to impose the circulant structure to the construction of convolutional layers, and hence leads to circulant convolutional layers (CircConvs) and circulant CNNs. The circulant structure and models can be either trained from scratch o

APA, Harvard, Vancouver, ISO, and other styles

29

Shi, Hao, Guo Cao, Zixian Ge, Youqiang Zhang, and Peng Fu. "Double-Branch Network with Pyramidal Convolution and Iterative Attention for Hyperspectral Image Classification." Remote Sensing 13, no. 7 (2021): 1403. http://dx.doi.org/10.3390/rs13071403.

Full text

Abstract:

Deep-learning methods, especially convolutional neural networks (CNN), have become the first choice for hyperspectral image (HSI) classification to date. It is a common procedure that small cubes are cropped from hyperspectral images and then fed into CNNs. However, standard CNNs find it difficult to extract discriminative spectral–spatial features. How to obtain finer spectral–spatial features to improve the classification performance is now a hot topic of research. In this regard, the attention mechanism, which has achieved excellent performance in other computer vision, holds the exciting p

APA, Harvard, Vancouver, ISO, and other styles

30

Wang, Dong, Ying Li, Li Ma, Zongwen Bai, and Jonathan Chan. "Going Deeper with Densely Connected Convolutional Neural Networks for Multispectral Pansharpening." Remote Sensing 11, no. 22 (2019): 2608. http://dx.doi.org/10.3390/rs11222608.

Full text

Abstract:

In recent years, convolutional neural networks (CNNs) have shown promising performance in the field of multispectral (MS) and panchromatic (PAN) image fusion (MS pansharpening). However, the small-scale data and the gradient vanishing problem have been preventing the existing CNN-based fusion approaches from leveraging deeper networks that potentially have better representation ability to characterize the complex nonlinear mapping relationship between the input (source) and the targeting (fused) images. In this paper, we introduce a very deep network with dense blocks and residual learning to

APA, Harvard, Vancouver, ISO, and other styles

31

Li, Haotian, Hongyan Xu, Xiaodong Tian, et al. "Bridge Crack Detection Based on SSENets." Applied Sciences 10, no. 12 (2020): 4230. http://dx.doi.org/10.3390/app10124230.

Full text

Abstract:

Bridge crack detection is essential to prevent transportation accidents. However, the surrounding environment has great interference with the detection of cracks, which makes it difficult to ensure the accuracy of the detection. In order to accurately detect bridge cracks, we proposed an end-to-end model named Skip-Squeeze-and-Excitation Networks (SSENets). It is mainly composed of the Skip-Squeeze-Excitation (SSE) module and the Atrous Spatial Pyramid Pooling (ASPP) module. The SSE module uses skip-connection strategy to enhance the gradient correlation between the shallow network and deeper

APA, Harvard, Vancouver, ISO, and other styles

32

Li, Jin, and Zilong Liu. "Multispectral Transforms Using Convolution Neural Networks for Remote Sensing Multispectral Image Compression." Remote Sensing 11, no. 7 (2019): 759. http://dx.doi.org/10.3390/rs11070759.

Full text

Abstract:

A multispectral image is a three-order tensor since it is a three-dimensional matrix, i.e.one spectral dimension and two spatial position dimensions. Multispectral image compression canbe achieved by means of the advantages of tensor decomposition (TD), such as NonnegativeTucker Decomposition (NTD). Unfortunately, the TD suffers from high calculation complexity andcannot be used in the on-board low-complexity case (e.g., multispectral cameras) that the hardwareresources and power are limited. Here, we propose a low-complexity compression approach formultispectral images based on convolution ne

APA, Harvard, Vancouver, ISO, and other styles

33

Wang, Zhen, Buhong Wang, Jianxin Guo, and Shanwen Zhang. "Sonar Objective Detection Based on Dilated Separable Densely Connected CNNs and Quantum-Behaved PSO Algorithm." Computational Intelligence and Neuroscience 2021 (January 18, 2021): 1–19. http://dx.doi.org/10.1155/2021/6235319.

Full text

Abstract:

Underwater sonar objective detection plays an important role in the field of ocean exploration. In order to solve the problem of sonar objective detection under the complex environment, a sonar objective detection method is proposed based on dilated separable densely connected convolutional neural networks (DS-CNNs) and quantum-behaved particle swarm optimization (QPSO) algorithm. Firstly, the dilated separable convolution kernel is proposed to extend the local receptive field and enhance the feature extraction ability of the convolution layers. Secondly, based on the linear interpolation algo

APA, Harvard, Vancouver, ISO, and other styles

34

Salih, Omran, and Serestina Viriri. "Skin Lesion Segmentation Using Local Binary Convolution-Deconvolution Architecture." Image Analysis & Stereology 39, no. 3 (2020): 169–85. http://dx.doi.org/10.5566/ias.2397.

Full text

Abstract:

Deep learning techniques such as Deep Convolutional Networks have achieved great success in skin lesion segmentation towards melanoma detection. The performance is however restrained by distinctive and challenging features of skin lesions such as irregular and fuzzy border, noise and artefacts presence and low contrast between lesions. The methods are also restricted with scarcity of annotated lesion images training dataset and limited computing resources. Recent research in convolutional neural network (CNN) has provided a variety of new architectures for deep learning. One interesting new ar

APA, Harvard, Vancouver, ISO, and other styles

35

Zhao, Yulin, Donghui Wang, and Leiou Wang. "Convolution Accelerator Designs Using Fast Algorithms." Algorithms 12, no. 5 (2019): 112. http://dx.doi.org/10.3390/a12050112.

Full text

Abstract:

Convolutional neural networks (CNNs) have achieved great success in image processing. However, the heavy computational burden it imposes makes it difficult for use in embedded applications that have limited power consumption and performance. Although there are many fast convolution algorithms that can reduce the computational complexity, they increase the difficulty of practical implementation. To overcome these difficulties, this paper proposes several convolution accelerator designs using fast algorithms. The designs are based on the field programmable gate array (FPGA) and display a better

APA, Harvard, Vancouver, ISO, and other styles

36

Li, Bin, and Hong Fu. "Real Time Eye Detector with Cascaded Convolutional Neural Networks." Applied Computational Intelligence and Soft Computing 2018 (2018): 1–8. http://dx.doi.org/10.1155/2018/1439312.

Full text

Abstract:

An accurate and efficient eye detector is essential for many computer vision applications. In this paper, we present an efficient method to evaluate the eye location from facial images. First, a group of candidate regions with regional extreme points is quickly proposed; then, a set of convolution neural networks (CNNs) is adopted to determine the most likely eye region and classify the region as left or right eye; finally, the center of the eye is located with other CNNs. In the experiments using GI4E, BioID, and our datasets, our method attained a detection accuracy which is comparable to ex

APA, Harvard, Vancouver, ISO, and other styles

37

Marmanis, D., J. D. Wegner, S. Galliani, K. Schindler, M. Datcu, and U. Stilla. "SEMANTIC SEGMENTATION OF AERIAL IMAGES WITH AN ENSEMBLE OF CNNS." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences III-3 (June 6, 2016): 473–80. http://dx.doi.org/10.5194/isprs-annals-iii-3-473-2016.

Full text

Abstract:

This paper describes a deep learning approach to semantic segmentation of very high resolution (aerial) images. Deep neural architectures hold the promise of end-to-end learning from raw images, making heuristic feature design obsolete. Over the last decade this idea has seen a revival, and in recent years deep convolutional neural networks (CNNs) have emerged as the method of choice for a range of image interpretation tasks like visual recognition and object detection. Still, standard CNNs do not lend themselves to per-pixel semantic segmentation, mainly because one of their fundamental princ

APA, Harvard, Vancouver, ISO, and other styles

38

Liu, Yao, Lianru Gao, Chenchao Xiao, Ying Qu, Ke Zheng, and Andrea Marinoni. "Hyperspectral Image Classification Based on a Shuffled Group Convolutional Neural Network with Transfer Learning." Remote Sensing 12, no. 11 (2020): 1780. http://dx.doi.org/10.3390/rs12111780.

Full text

Abstract:

Convolutional neural networks (CNNs) have been widely applied in hyperspectral imagery (HSI) classification. However, their classification performance might be limited by the scarcity of labeled data to be used for training and validation. In this paper, we propose a novel lightweight shuffled group convolutional neural network (abbreviated as SG-CNN) to achieve efficient training with a limited training dataset in HSI classification. SG-CNN consists of SG conv units that employ conventional and atrous convolution in different groups, followed by channel shuffle operation and shortcut connecti

APA, Harvard, Vancouver, ISO, and other styles

39

Wang, Congcong, Faouzi Alaya Cheikh, Azeddine Beghdadi, and Ole Jakob Elle. "Adaptive Context Encoding Module for Semantic Segmentation." Electronic Imaging 2020, no. 10 (2020): 27–1. http://dx.doi.org/10.2352/issn.2470-1173.2020.10.ipas-027.

Full text

Abstract:

The object sizes in images are diverse, therefore, capturing multiple scale context information is essential for semantic segmentation. Existing context aggregation methods such as pyramid pooling module (PPM) and atrous spatial pyramid pooling (ASPP) employ different pooling size or atrous rate, such that multiple scale information is captured. However, the pooling sizes and atrous rates are chosen empirically. Rethinking of ASPP leads to our observation that learnable sampling locations of the convolution operation can endow the network learnable fieldof- view, thus the ability of capturing

APA, Harvard, Vancouver, ISO, and other styles

40

Men, J., L. Fang, Y. Liu, and Y. Sun. "LAND USE CLASSIFICATION BASED ON MULTI-STRUCTURE CONVOLUTION NEURAL NETWORK FEATURES CASCADING." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-2/W16 (September 17, 2019): 163–67. http://dx.doi.org/10.5194/isprs-archives-xlii-2-w16-163-2019.

Full text

Abstract:

<p><strong>Abstract.</strong> Learning efficient image representations is at the core of the classification task of remote sensing imagery. The existing methods for solving image classification task, based on either feature coding approaches extracted from convolution neural networks(CNNs) or training new CNNs, can only generate image features with limited representative ability, which essentially prevents them from achieving better performance. In this paper, we investigate how to transfer features from these successfully pre-trained CNNs for classification. We propose a sce

APA, Harvard, Vancouver, ISO, and other styles

41

C. Burkapalli, Vishwanath, and Priyadarshini C. Patil. "Food image segmentation using edge adaptive based deep-CNNs." International Journal of Intelligent Unmanned Systems 8, no. 4 (2019): 243–52. http://dx.doi.org/10.1108/ijius-09-2019-0053.

Full text

Abstract:

Purpose Indian food recognition can be considered as a case of fine-grained type visual recognition, where the several photos of same category generally have significant variability. Therefore, effective segmentation and classification technique is required to identify the particular cuisines and fine-grained analysis. The paper aims to discuss this issue. Design/methodology/approach In this paper, the authors provided an effective segmentation approach through the proposed edge adaptive (EA)-deep convolutional neural networks (DCNNs) model, where each input images are divided into patches in

APA, Harvard, Vancouver, ISO, and other styles

42

Marmanis, D., J. D. Wegner, S. Galliani, K. Schindler, M. Datcu, and U. Stilla. "SEMANTIC SEGMENTATION OF AERIAL IMAGES WITH AN ENSEMBLE OF CNNS." ISPRS Annals of Photogrammetry, Remote Sensing and Spatial Information Sciences III-3 (June 6, 2016): 473–80. http://dx.doi.org/10.5194/isprsannals-iii-3-473-2016.

Full text

Abstract:

This paper describes a deep learning approach to semantic segmentation of very high resolution (aerial) images. Deep neural architectures hold the promise of end-to-end learning from raw images, making heuristic feature design obsolete. Over the last decade this idea has seen a revival, and in recent years deep convolutional neural networks (CNNs) have emerged as the method of choice for a range of image interpretation tasks like visual recognition and object detection. Still, standard CNNs do not lend themselves to per-pixel semantic segmentation, mainly because one of their fundamental princ

APA, Harvard, Vancouver, ISO, and other styles

43

Han, Yong, Shukang Wang, Yibin Ren, Cheng Wang, Peng Gao, and Ge Chen. "Predicting Station-Level Short-Term Passenger Flow in a Citywide Metro Network Using Spatiotemporal Graph Convolutional Neural Networks." ISPRS International Journal of Geo-Information 8, no. 6 (2019): 243. http://dx.doi.org/10.3390/ijgi8060243.

Full text

Abstract:

Predicting the passenger flow of metro networks is of great importance for traffic management and public safety. However, such predictions are very challenging, as passenger flow is affected by complex spatial dependencies (nearby and distant) and temporal dependencies (recent and periodic). In this paper, we propose a novel deep-learning-based approach, named STGCNNmetro (spatiotemporal graph convolutional neural networks for metro), to collectively predict two types of passenger flow volumes—inflow and outflow—in each metro station of a city. Specifically, instead of representing metro stati

APA, Harvard, Vancouver, ISO, and other styles

44

Liu, Feng, Xuan Zhou, Xuehu Yan, Yuliang Lu, and Shudong Wang. "Image Steganalysis via Diverse Filters and Squeeze-and-Excitation Convolutional Neural Network." Mathematics 9, no. 2 (2021): 189. http://dx.doi.org/10.3390/math9020189.

Full text

Abstract:

Steganalysis is a method to detect whether the objects contain secret messages. With the popularity of deep learning, using convolutional neural networks (CNNs), steganalytic schemes have become the chief method of combating steganography in recent years. However, the diversity of filters has not been fully utilized in the current research. This paper constructs a new effective network with diverse filter modules (DFMs) and squeeze-and-excitation modules (SEMs), which can better capture the embedding artifacts. As the essential parts, combining three different scale convolution filters, DFMs c

APA, Harvard, Vancouver, ISO, and other styles

45

Azimi, S., E. Vig, F. Kurz, and P. Reinartz. "SEGMENT-AND-COUNT: VEHICLE COUNTING IN AERIAL IMAGERY USING ATROUS CONVOLUTIONAL NEURAL NETWORKS." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLII-1 (September 26, 2018): 19–23. http://dx.doi.org/10.5194/isprs-archives-xlii-1-19-2018.

Full text

Abstract:

<p><strong>Abstract.</strong> High-resolution aerial imagery can provide detailed and in some cases even real-time information about traffic related objects. Vehicle localization and counting using aerial imagery play an important role in a broad range of applications. Recently, convolutional neural networks (CNNs) with atrous convolution layers have shown better performance for semantic segmentation compared to conventional convolutional aproaches. In this work, we propose a joint vehicle segmentation and counting method based on atrous convolutional layers. This method uses

APA, Harvard, Vancouver, ISO, and other styles

46

Huang, Yibin, Congying Qiu, Xiaonan Wang, Shijun Wang, and Kui Yuan. "A Compact Convolutional Neural Network for Surface Defect Inspection." Sensors 20, no. 7 (2020): 1974. http://dx.doi.org/10.3390/s20071974.

Full text

Abstract:

The advent of convolutional neural networks (CNNs) has accelerated the progress of computer vision from many aspects. However, the majority of the existing CNNs heavily rely on expensive GPUs (graphics processing units). to support large computations. Therefore, CNNs have not been widely used to inspect surface defects in the manufacturing field yet. In this paper, we develop a compact CNN-based model that not only achieves high performance on tiny defect inspection but can be run on low-frequency CPUs (central processing units). Our model consists of a light-weight (LW) bottleneck and a decod

APA, Harvard, Vancouver, ISO, and other styles

47

Shao, Jiaqi, Changwen Qu, Jianwei Li, and Shujuan Peng. "A Lightweight Convolutional Neural Network Based on Visual Attention for SAR Image Target Classification." Sensors 18, no. 9 (2018): 3039. http://dx.doi.org/10.3390/s18093039.

Full text

Abstract:

With the continuous development of the convolutional neural network (CNN) concept and other deep learning technologies, target recognition in Synthetic Aperture Radar (SAR) images has entered a new stage. At present, shallow CNNs with simple structure are mostly applied in SAR image target recognition, even though their feature extraction ability is limited to a large extent. What’s more, research on improving SAR image target recognition efficiency and imbalanced data processing is relatively scarce. Thus, a lightweight CNN model for target recognition in SAR image is designed in this paper.

APA, Harvard, Vancouver, ISO, and other styles

48

Deng, Lu, Hong-Hu Chu, Peng Shi, Wei Wang, and Xuan Kong. "Region-Based CNN Method with Deformable Modules for Visually Classifying Concrete Cracks." Applied Sciences 10, no. 7 (2020): 2528. http://dx.doi.org/10.3390/app10072528.

Full text

Abstract:

Cracks are often the most intuitive indicators for assessing the condition of in-service structures. Intelligent detection methods based on regular convolutional neural networks (CNNs) have been widely applied to the field of crack detection in recently years; however, these methods exhibit unsatisfying performance on the detection of out-of-plane cracks. To overcome this drawback, a new type of region-based CNN (R-CNN) crack detector with deformable modules is proposed in the present study. The core idea of the method is to replace the traditional regular convolution and pooling operation wit

APA, Harvard, Vancouver, ISO, and other styles

49

Park, Keunyoung, and Doo-Hyun Kim. "Accelerating Image Classification using Feature Map Similarity in Convolutional Neural Networks." Applied Sciences 9, no. 1 (2018): 108. http://dx.doi.org/10.3390/app9010108.

Full text

Abstract:

Convolutional neural networks (CNNs) have greatly improved image classification performance. However, the extensive time required for classification owing to the large amount of computation involved, makes it unsuitable for application to low-performance devices. To speed up image classification, we propose a cached CNN, which can classify input images based on similarity with previously input images. Because the feature maps extracted from the CNN kernel represent the intensity of features, images with a similar intensity can be classified into the same class. In this study, we cache class la

APA, Harvard, Vancouver, ISO, and other styles

50

Meng, Zhe, Feng Zhao, Miaomiao Liang, and Wen Xie. "Deep Residual Involution Network for Hyperspectral Image Classification." Remote Sensing 13, no. 16 (2021): 3055. http://dx.doi.org/10.3390/rs13163055.

Full text

Abstract:

Convolutional neural networks (CNNs) have achieved great results in hyperspectral image (HSI) classification in recent years. However, convolution kernels are reused among different spatial locations, known as spatial-agnostic or weight-sharing kernels. Furthermore, the preference of spatial compactness in convolution (typically, 3×3 kernel size) constrains the receptive field and the ability to capture long-range spatial interactions. To mitigate the above two issues, in this article, we combine a novel operation called involution with residual learning and develop a new deep residual involut

APA, Harvard, Vancouver, ISO, and other styles

We offer discounts on all premium plans for authors whose works are included in thematic literature selections. Contact us to get a unique promo code!