14.5.9.6.2 Convolutional Neural Networks, Design, Implementation Issues

Chapter Contents (Back)
Convolutional Neural Networks. Neural Networks. Deep Nets. CNN. Convolutional networks for image classification progressively reduce resolution until the image is represented by tiny feature maps in which the spatial structure of the scene is no longer discernible. Mostly variations on network structures and design.
See also Training Issues for Convolutional Neural Networks.
See also Neural Architecture, Neural Architecture Search.
See also Pooling in Convolutional Neural Networks Implementations.
See also Neural Net Pruning.
See also Adversarial Networks, Adversarial Inputs, Generative Adversarial.
See also Recurrent Neural Networks for Shapes and Complex Features, RNN. ResNets:
See also Residual Neural Networks, ResNet.
See also Efficient Implementations Convolutional Neural Networks.
See also Data Augmentation, Generative Network, Convolutional Network.

McKernel: A Library for Approximate Kernel Expansions in Log-linear Time,
2020.
WWW Link.
PDF File. Code, Neural Networks. Code, Kernel Expansion. 2009

Rahimi, A.[Ali], Recht, B.[Benjamin],
Random Features for Large-Scale Kernel Machines,
NIPS07(xx-yy).
PDF File. 2009
BibRef

Rahimi, A.[Ali], Recht, B.[Benjamin],
Weighted Sums of Random Kitchen Sinks: Replacing minimization NIPS08,
(xx-yy).
PDF File. 2009
BibRef

Kim, I.J.[In-Jung], Choi, C.[Changbeom], Lee, S.H.[Sang-Heon],
Improving discrimination ability of convolutional neural networks by hybrid learning,
IJDAR(19), No. 1, March 2016, pp. 1-9.
WWW Link. 1602
BibRef

Nogueira, K.[Keiller], Penatti, O.A.B.[Otávio A.B.], dos Santos, J.A.[Jefersson A.],
Towards better exploiting convolutional neural networks for remote sensing scene classification,
PR(61), No. 1, 2017, pp. 539-556.
Elsevier DOI 1705
BibRef
Earlier: A2, A1, A3:
Do deep features generalize from everyday objects to remote sensing and aerial scenes domains?,
EarthObserv15(44-51)
IEEE DOI 1510
Accuracy. Evaluation of convolutional networks. BibRef

Kuo, C.C.J.[C.C. Jay],
Understanding convolutional neural networks with a mathematical model,
JVCIR(41), No. 1, 2016, pp. 406-413.
Elsevier DOI 1612
Award, JVCI. Convolutional neural network (CNN) BibRef

Chellappa, R.[Rama],
The changing fortunes of pattern recognition and computer vision,
IVC(55, Part 1), No. 1, 2016, pp. 3-5.
Elsevier DOI 1612
Convolutional Neural Networks BibRef

Xu, C., Lu, C., Liang, X., Gao, J., Zheng, W., Wang, T., Yan, S.,
Multi-loss Regularized Deep Neural Network,
CirSysVideo(26), No. 12, December 2016, pp. 2273-2283.
IEEE DOI 1612
Computer architecture BibRef

Du, B.[Bo], Xiong, W.[Wei], Wu, J.[Jia], Zhang, L.F.[Le-Fei], Zhang, L.P.[Liang-Pei], Tao, D.C.[Da-Cheng],
Stacked Convolutional Denoising Auto-Encoders for Feature Representation,
Cyber(47), No. 4, April 2017, pp. 1017-1027.
IEEE DOI 1704
Convolution BibRef

Malik, J.[Jitendra],
Technical Perspective: What Led Computer Vision to Deep Learning?,
CACM(60), No. 6, June 2017, pp. 82-83.
DOI Link 1706
Discusses next paper BibRef

Krizhevsky, A.[Alex], Sutskever, I.[Ilya], Hinton, G.E.[Geoffrey E.],
ImageNet Classification with Deep Convolutional Neural Networks,
CACM(60), No. 6, June 2017, pp. 84-90.
DOI Link 1706
Survey, Convolutional Networks. BibRef

Pan, X.Q.[Xia-Qing], Chen, Y.[Yueru], Kuo, C.C.J.[C.C. Jay],
Design, analysis and application of a volumetric convolutional neural network,
JVCIR(46), No. 1, 2017, pp. 128-138.
Elsevier DOI 1706
Convolutional, neural, network BibRef

Mishkin, D.[Dmytro], Sergievskiy, N.[Nikolay], Matas, J.G.[Jiri G.],
Systematic evaluation of convolution neural network advances on the Imagenet,
CVIU(161), No. 1, 2017, pp. 11-19.
Elsevier DOI 1708
CNN BibRef

Chen, Z.L.[Zhang-Ling], Wang, J.[Jun], Li, W.J.[Wen-Juan], Li, N.[Nan], Wu, H.M.[Hua-Ming], Wang, D.W.[Da-Wei],
Convolutional neural network with nonlinear competitive units,
SP:IC(60), No. 1, 2018, pp. 193-198.
Elsevier DOI 1712
Nonlinear competitive unit BibRef

Cui, Z., Niu, Z., Liu, L., Yan, S.,
Layerwise Class-Aware Convolutional Neural Network,
CirSysVideo(27), No. 12, December 2017, pp. 2601-2612.
IEEE DOI 1712
Biological neural networks, Computational modeling, Computer architecture, Convolutional codes, Mutual information, object classification BibRef

Akilan, T.[Thangarajah], Wu, Q.M.J.[Qing-Ming Jonathan], Zhang, H.[Hui],
Effect of fusing features from multiple DCNN architectures in image classification,
IET-IPR(12), No. 7, July 2018, pp. 1102-1110.
DOI Link 1806
BibRef

Ye, J., Han, Y., Cha, E.,
Deep Convolutional Framelets: A General Deep Learning Framework for Inverse Problems,
SIIMS(11), No. 2, 2018, pp. 991-1048.
DOI Link 1807
BibRef

Fu, R.G.[Rui-Gang], Li, B.[Biao], Gao, Y.[Yinghui], Wang, P.[Ping],
CNN with coarse-to-fine layer for hierarchical classification,
IET-CV(12), No. 6, September 2018, pp. 892-899.
DOI Link 1808
BibRef

Mohammadnia-Qaraei, M.R.[Mohammad Reza], Monsefi, R.[Reza], Ghiasi-Shirazi, K.[Kamaledin],
Convolutional kernel networks based on a convex combination of cosine kernels,
PRL(116), 2018, pp. 127-134.
Elsevier DOI 1812
Convolutional kernel networks (CKN), Convolutional neural networks (CNN), Kernel approximation, Sum of squared errors BibRef

Yao, J., Wang, J., Tsang, I.W., Zhang, Y., Sun, J., Zhang, C., Zhang, R.,
Deep Learning From Noisy Image Labels With Quality Embedding,
IP(28), No. 4, April 2019, pp. 1909-1922.
IEEE DOI 1901
Big Data, gradient methods, image denoising, image recognition, learning (artificial intelligence), optimisation, probability, quality embedding BibRef

Gong, Z.Q.[Zhi-Qiang], Zhong, P.[Ping], Hu, W.D.[Wei-Dong], Hua, Y.M.[Yu-Ming],
Joint Learning of the Center Points and Deep Metrics for Land-Use Classification in Remote Sensing,
RS(11), No. 1, 2019, pp. xx-yy.
DOI Link 1901
BibRef

Matiz, S.[Sergio], Barner, K.E.[Kenneth E.],
Inductive conformal predictor for convolutional neural networks: Applications to active learning for image classification,
PR(90), 2019, pp. 172-182.
Elsevier DOI 1903
Conformal prediction, Convolutional neural networks, Active learning, Distance metric learning, Image classification BibRef

Liu, Y.[Yang], Luo, T.[Tiejian],
The optimization of sum-product network structure learning,
JVCIR(60), 2019, pp. 391-397.
Elsevier DOI 1903
Machine learning, Deep learning, Sum-product network, Structure learning BibRef

Guo, C.S.[Chun-Sheng], Li, R.Z.[Rui-Zhe], Yang, M.[Meng], Tang, X.G.[Xian-Ghong],
Deep neural network with FGL for small dataset classification,
IET-IPR(13), No. 3, February 2019, pp. 491-497.
DOI Link 1903
FGL: feature generalisation layer. BibRef

Xie, G.T.[Guo-Tian], Yang, K.Y.[Kui-Yuan], Lai, J.H.[Jian-Huang],
Filter-in-Filter: Low Cost CNN Improvement by Sub-filter Parameter Sharing,
PR(91), 2019, pp. 391-403.
Elsevier DOI 1904
Sub-pattern, Sub-filter, Expressibility of filter, Visualization, Filter-in-filter BibRef

Takahashi, R., Matsubara, T., Uehara, K.,
A Novel Weight-Shared Multi-Stage CNN for Scale Robustness,
CirSysVideo(29), No. 4, April 2019, pp. 1090-1101.
IEEE DOI 1904
Convolution, Robustness, Task analysis, Feature extraction, Network architecture, Degradation, Neural networks, shared weights BibRef

Ghosh, S.[Swarnendu], Das, N.[Nibaran], Nasipuri, M.[Mita],
Reshaping inputs for convolutional neural network: Some common and uncommon methods,
PR(93), 2019, pp. 79-94.
Elsevier DOI 1906
Deep learning, Convolutional neural network, Reshaping, Resizing, Input size BibRef

Wang, Y.H.[Yun-He], Xu, C.[Chang], Xu, C.[Chao], Tao, D.C.[Da-Cheng],
Packing Convolutional Neural Networks in the Frequency Domain,
PAMI(41), No. 10, October 2019, pp. 2495-2510.
IEEE DOI 1909
Convolution, Frequency-domain analysis, Discrete cosine transforms, Image coding, Redundancy, DCT bases BibRef

Chen, H.T.[Han-Ting], Wang, Y.H.[Yun-He], Shu, H.[Han], Tang, Y.H.[Ye-Hui], Xu, C.J.[Chun-Jing], Shi, B.X.[Bo-Xin], Xu, C.[Chao], Tian, Q.[Qi], Xu, C.[Chang],
Frequency Domain Compact 3D Convolutional Neural Networks,
CVPR20(1638-1647)
IEEE DOI 2008
Convolution, Frequency-domain analysis, Convolutional neural networks, Task analysis BibRef

Chen, Z.[Zhi], Ho, P.H.[Pin-Han],
Global-connected network with generalized ReLU activation,
PR(96), 2019, pp. 106961.
Elsevier DOI 1909
CNN, Deep learning, Activation BibRef

Zhao, Q.[Qi], Liu, J.H.[Jia-Hui], Zhang, B.X.[Bo-Xue], Lyu, S.C.[Shu-Chang], Raoof, N.[Nauman], Feng, W.Q.[Wen-Quan],
Interpretable Relative Squeezing bottleneck design for compact convolutional neural networks model,
IVC(89), 2019, pp. 276-288.
Elsevier DOI 1909
Image recognition, Compact CNN, Relative-Squeezing bottleneck, Learned group convolutions BibRef

Wang, J.Q.[Jun-Qian], Zhang, H.Y.[Han-Yu], Han, P.Y.[Pei-Yi], Liu, C.Y.[Chuan-Yi], Xu, Y.[Yong],
Pixel re-representations for better classification of images,
PRL(140), 2020, pp. 310-317.
Elsevier DOI 2012
Image classification, Image re-representation, Sparse representation, Collaborative representation, Pattern recognition BibRef

You, H.F.[Hong-Feng], Tian, S.W.[Sheng-Wei], Yu, L.[Long], Lv, Y.L.[Ya-Long],
Pixel-Level Remote Sensing Image Recognition Based on Bidirectional Word Vectors,
GeoRS(58), No. 2, February 2020, pp. 1281-1293.
IEEE DOI 2001
To get relationships in addition to pixel features. Feature extraction, Remote sensing, Recurrent neural networks, Image recognition, Semantics, Deep learning, Image color analysis, sliced recurrent neural network (SRNN) BibRef

Liu, J.Q.[Jia-Qi], Li, Z.H.[Zheng-Hao], Tang, Y.L.[Yong-Liang], Hu, W.[Wei], Wu, J.[Jun],
3D Convolutional Neural Network based on memristor for video recognition,
PRL(130), 2020, pp. 116-124.
Elsevier DOI 2002
3D Convolution, Basic memristor array, Behavior recognition, Memristors, Neuromorphic network BibRef

Lauriola, I.[Ivano], Gallicchio, C.[Claudio], Aiolli, F.[Fabio],
Enhancing deep neural networks via multiple kernel learning,
PR(101), 2020, pp. 107194.
Elsevier DOI 2003
Deep neural networks, Deep learning, Multiple kernel learning, Ensemble learning BibRef

Veit, A.[Andreas], Belongie, S.[Serge],
Convolutional Networks with Adaptive Inference Graphs,
IJCV(128), No. 3, March 2020, pp. 730-741.
Springer DOI 2003
BibRef
Earlier: ECCV18(I: 3-18).
Springer DOI 1810
BibRef

Wu, Y.X.[Yu-Xin], He, K.M.[Kai-Ming],
Group Normalization,
IJCV(128), No. 3, March 2020, pp. 742-755.
Springer DOI 2003
BibRef
Earlier: ECCV18(XIII: 3-19).
Springer DOI 1810
Award, ECCV, HM. BibRef

For deep learning. Uses:
See also COCO: Common Objects in Context.

Santra, B.[Bikash], Paul, A.[Angshuman], Mukherjee, D.P.[Dipti Prasad],
Deterministic dropout for deep neural networks using composite random forest,
PRL(131), 2020, pp. 205-212.
Elsevier DOI 2004
Deterministic dropout, Composite random forest, Deep neural network, Regularizer BibRef

Moya-Sánchez, E.U.[E. Ulises], Xambó-Descamps, S.[Sebastiá], Sánchez Pérez, A.[Abraham], Salazar-Colores, S.[Sebastián], Martínez-Ortega, J.[Jorge], Cortés, U.[Ulises],
A bio-inspired quaternion local phase CNN layer with contrast invariance and linear sensitivity to rotation angles,
PRL(131), 2020, pp. 56-62.
Elsevier DOI 2004
BibRef

Gao, H.Y.[Hong-Yang], Yuan, H.[Hao], Wang, Z.Y.[Zheng-Yang], Ji, S.W.[Shui-Wang],
Pixel Transposed Convolutional Networks,
PAMI(42), No. 5, May 2020, pp. 1218-1227.
IEEE DOI 2004
Convolution, Semantics, Image segmentation, Kernel, Task analysis, Image generation, Analytical models, Deep learning, pixel transposed convolution BibRef

Hackel, T.[Timo], Usvyatsov, M.[Mikhail], Galliani, S.[Silvano], Wegner, J.D.[Jan D.], Schindler, K.[Konrad],
Inference, Learning and Attention Mechanisms that Exploit and Preserve Sparsity in CNNs,
IJCV(128), No. 4, April 2020, pp. 1047-1059.
Springer DOI 2004
BibRef
Earlier: GCPR18(597-611).
Springer DOI 1905
BibRef

Park, J.[Jongchan], Woo, S.[Sanghyun], Lee, J.Y.[Joon-Young], Kweon, I.S.[In So],
A Simple and Light-Weight Attention Module for Convolutional Neural Networks,
IJCV(128), No. 4, April 2020, pp. 783-798.
Springer DOI 2004
BibRef
Earlier: A2, A1, A3, A4:
CBAM: Convolutional Block Attention Module,
ECCV18(VII: 3-19).
Springer DOI 1810
BibRef

Innamorati, C.[Carlo], Ritschel, T.[Tobias], Weyrich, T.[Tim], Mitra, N.J.[Niloy J.],
Learning on the Edge: Investigating Boundary Filters in CNNs,
IJCV(128), No. 4, April 2020, pp. 773-782.
Springer DOI 2004
Dealing with edge effects in CNN filters. BibRef

Zhang, Y.Q.[Yong-Qiang], Bai, Y.C.[Yan-Cheng], Ding, M.L.[Ming-Li], Ghanem, B.[Bernard],
Multi-task Generative Adversarial Network for Detecting Small Objects in the Wild,
IJCV(128), No. 6, June 2020, pp. 1810-1828.
Springer DOI 2006
BibRef
Earlier: A2, A1, A3, A4:
SOD-MTGAN: Small Object Detection via Multi-Task Generative Adversarial Network,
ECCV18(XIII: 210-226).
Springer DOI 1810
BibRef

Tabernik, D.[Domen], Kristan, M.[Matej], Leonardis, A.[Aleš],
Spatially-Adaptive Filter Units for Compact and Efficient Deep Neural Networks,
IJCV(128), No. 8-9, September 2020, pp. 2049-2067.
Springer DOI 2008
BibRef
Earlier:
Spatially-Adaptive Filter Units for Deep Neural Networks,
CVPR18(9388-9396)
IEEE DOI 1812
Standards, Task analysis, Kernel, Neural networks, Graphics processing units, Strain, Interpolation BibRef

Singh, P.[Pravendra], Verma, V.K.[Vinay Kumar], Rai, P.[Piyush], Namboodiri, V.P.[Vinay P.],
HetConv: Beyond Homogeneous Convolution Kernels for Deep CNNs,
IJCV(128), No. 8-9, September 2020, pp. 2068-2088.
Springer DOI 2008
BibRef

Dai, Y.P.[Yong-Peng], Jin, T.[Tian], Song, Y.K.[Yong-Kun], Sun, S.L.[Shi-Long], Wu, C.[Chen],
Convolutional Neural Network with Spatial-Variant Convolution Kernel,
RS(12), No. 17, 2020, pp. xx-yy.
DOI Link 2009
BibRef

Cococcioni, M., Rossi, F., Ruffaldi, E., Saponara, S., Dupont de Dinechin, B.,
Novel Arithmetics in Deep Neural Networks Signal Processing for Autonomous Driving: Challenges and Opportunities,
SPMag(38), No. 1, January 2021, pp. 97-110.
IEEE DOI 2012
Neurons, Real-time systems, Radar signal processing, Security, Task analysis, Autonomous vehicles, Biological neural networks BibRef

Yang, J.J.[Jing-Jing], Wu, J.Z.[Jin-Zhao], Wang, X.J.[Xiao-Jing],
Convolutional neural network based on differential privacy in exponential attenuation mode for image classification,
IET-IPR(14), No. 15, 15 December 2020, pp. 3676-3681.
DOI Link 2103
Adding gaussian noise. BibRef

Liu, C.L.[Chun-Lei], Ding, W.R.[Wen-Rui], Hu, Y.[Yuan], Zhang, B.C.[Bao-Chang], Liu, J.Z.[Jian-Zhuang], Guo, G.D.[Guo-Dong], Doermann, D.[David],
Rectified Binary Convolutional Networks with Generative Adversarial Learning,
IJCV(129), No. 4, April 2021, pp. 998-1012.
Springer DOI 2104
BibRef

Liu, C.L.[Chun-Lei], Ding, W.R.[Wen-Rui], Xia, X.[Xin], Zhang, B.C.[Bao-Chang], Gu, J.X.[Jia-Xin], Liu, J.Z.[Jian-Zhuang], Ji, R.R.[Rong-Rong], Doermann, D.[David],
Circulant Binary Convolutional Networks: Enhancing the Performance of 1-Bit DCNNs With Circulant Back Propagation,
CVPR19(2686-2694).
IEEE DOI 2002
BibRef

Luo, W.J.[Wen-Jie], Zhang, H.[Han], Ni, P.[Peng], Tian, X.D.[Xue-Dong],
Balanced principal component for 3D shape recognition using convolutional neural networks,
IET-IPR(14), No. 17, 24 December 2020, pp. 4468-4476.
DOI Link 2104
Evaluation of using PCA in CNN analysis. BibRef

Zhao, F.Q.[Fen-Qiang], Wu, Z.W.[Zheng-Wang], Wang, L.[Li], Lin, W.L.[Wei-Li], Gilmore, J.H.[John H.], Xia, S.R.[Shun-Ren], Shen, D.G.[Ding-Gang], Li, G.[Gang],
Spherical Deformable U-Net: Application to Cortical Surface Parcellation and Development Prediction,
MedImg(40), No. 4, April 2021, pp. 1217-1228.
IEEE DOI 2104
CNN on spherical representations. Convolution, Task analysis, Shape, Computer architecture, Distortion, Biomedical imaging, Surface treatment, triangular mesh BibRef

Li, X.X.[Xiao-Xu], Yu, L.Y.[Li-Yun], Yang, X.C.[Xiao-Chen], Ma, Z.Y.[Zhan-Yu], Xue, J.H.[Jing-Hao], Cao, J.[Jie], Guo, J.[Jun],
ReMarNet: Conjoint Relation and Margin Learning for Small-Sample Image Classification,
CirSysVideo(31), No. 4, April 2021, pp. 1569-1579.
IEEE DOI 2104
Train 2 networks, one for relations, on for margin learning. Training, Prototypes, Neural networks, Feature extraction, Task analysis, Deep learning, Adaptation models, discriminative feature learning BibRef

Zhong, Z.[Zhao], Yang, Z.C.[Zi-Chen], Deng, B.[Boyang], Yan, J.J.[Jun-Jie], Wu, W.[Wei], Shao, J.[Jing], Liu, C.L.[Cheng-Lin],
BlockQNN: Efficient Block-Wise Neural Network Architecture Generation,
PAMI(43), No. 7, July 2021, pp. 2314-2328.
IEEE DOI 2106
BibRef
Earlier: A1, A4, A5, A6, A7, Only:
Practical Block-Wise Neural Network Architecture Generation,
CVPR18(2423-2432)
IEEE DOI 1812
Computer architecture, Task analysis, Neural networks, Network architecture, Graphics processing units, Acceleration, Q-learning. Indexes, Convolutional codes, Convolutional neural networks BibRef

Alkhelaiwi, M.[Munirah], Boulila, W.[Wadii], Ahmad, J.[Jawad], Koubaa, A.[Anis], Driss, M.[Maha],
An Efficient Approach Based on Privacy-Preserving Deep Learning for Satellite Image Classification,
RS(13), No. 11, 2021, pp. xx-yy.
DOI Link 2106
Privacy of data and results when using cloud services for deep learning. Train on encrypted data. BibRef

Ruan, D.S.[Dong-Sheng], Shi, Y.[Yu], Wen, J.[Jun], Zheng, N.G.[Neng-Gan], Zheng, M.[Min],
Spatially-Aware Context Neural Networks,
IP(30), 2021, pp. 6906-6916.
IEEE DOI 2108
Context modeling, Convolution, Semantics, Computational modeling, Transforms, Task analysis, Object detection, context modeling BibRef

Zeng, Y.Y.[Yu-Yuan], Dai, T.[Tao], Chen, B.[Bin], Xia, S.T.[Shu-Tao], Lu, J.[Jian],
Correlation-based structural dropout for convolutional neural networks,
PR(120), 2021, pp. 108117.
Elsevier DOI 2109
Over-fitting, Regularization, Dropout, Convolutional neural networks BibRef

Wang, Z.[Ziwei], Lu, J.W.[Ji-Wen], Zhou, J.[Jie],
Learning Channel-Wise Interactions for Binary Convolutional Neural Networks,
PAMI(43), No. 10, October 2021, pp. 3432-3445.
IEEE DOI 2109
BibRef
And: A1, A2, A3: Add A3: Tao, C.X.[Chen-Xin], A5: Tian, Q.[Qi], CVPR19(568-577).
IEEE DOI 2002
Convolutional neural networks, Quantization (signal), Learning (artificial intelligence), Noise reduction, feature denoising BibRef

Jeon, Y.H.[Yun-Ho], Kim, J.[Junmo],
Integrating Multiple Receptive Fields Through Grouped Active Convolution,
PAMI(43), No. 11, November 2021, pp. 3892-3903.
IEEE DOI 2110
Convolution, Shape, Task analysis, Computer architecture, Semantics, Network architecture, Backpropagation, deep learning BibRef

Zhao, W.Y.[Wen-Yi], Yang, H.H.[Hui-Hua], Pan, X.P.[Xi-Peng], Li, L.Q.[Ling-Qiao],
S2-aware network for visual recognition,
SP:IC(99), 2021, pp. 116458.
Elsevier DOI 2111
Convolution neural network, Size aware, Shape aware, Light weight BibRef


Yao, Z.L.[Zhu-Liang], Cao, Y.[Yue], Zheng, S.[Shuxin], Huang, G.[Gao], Lin, S.[Stephen],
Cross-Iteration Batch Normalization,
CVPR21(12326-12335)
IEEE DOI 2111

WWW Link. Training, Upper bound, Codes, Estimation, Object detection, Pattern recognition BibRef

Li, D.[Duo], Hu, J.[Jie], Wang, C.[Changhu], Li, X.[Xiangtai], She, Q.[Qi], Zhu, L.[Lei], Zhang, T.[Tong], Chen, Q.[Qifeng],
Involution: Inverting the Inherence of Convolution for Visual Recognition,
CVPR21(12316-12325)
IEEE DOI 2111

WWW Link. Deep learning, Visualization, Image segmentation, Convolution, Computational modeling, Neural networks, Benchmark testing BibRef

Zhang, S.D.[Sheng-Dong], Nezhadarya, E.[Ehsan], Fashandi, H.[Homa], Liu, J.Y.[Jia-Yi], Graham, D.[Darin], Shah, M.[Mohak],
Stochastic Whitening Batch Normalization,
CVPR21(10973-10982)
IEEE DOI 2111
Training, Deep learning, Stochastic processes, Pattern recognition, Iterative methods, Convolutional neural networks BibRef

Ding, X.H.[Xiao-Han], Zhang, X.Y.[Xiang-Yu], Han, J.G.[Jun-Gong], Ding, G.G.[Gui-Guang],
Diverse Branch Block: Building a Convolution as an Inception-like Unit,
CVPR21(10881-10890)
IEEE DOI 2111
Training, Image segmentation, Costs, Convolution, Semantics, Computer architecture, Object detection BibRef

Böhle, M.[Moritz], Fritz, M.[Mario], Schiele, B.[Bernt],
Convolutional Dynamic Alignment Networks for Interpretable Classifications,
CVPR21(10024-10033)
IEEE DOI 2111
New variation on neural networks. Measurement, Visualization, Computational modeling, Neural networks, Transforms, Predictive models BibRef

Zhen, X.J.[Xing-Jian], Chakraborty, R.[Rudrasis], Singh, V.[Vikas],
Simpler Certified Radius Maximization by Propagating Covariances,
CVPR21(7288-7297)
IEEE DOI 2111
Neighborhood around a given training sample for which the model’s prediction remains unchanged. Training, Smoothing methods, Runtime, Neural networks, Transforms, Predictive models, Robustness BibRef

Fayyaz, M.[Mohsen], Bahrami, E.[Emad], Diba, A.[Ali], Noroozi, M.[Mehdi], Adeli, E.[Ehsan], Van Gool, L.J.[Luc J.], Gall, J.[Juergen],
3D CNNs with Adaptive Temporal Feature Resolutions,
CVPR21(4729-4738)
IEEE DOI 2111
Costs, Adaptive systems, Computer architecture, Pattern recognition BibRef

Zhong, Y.Y.[Yuan-Yi], Wang, J.F.[Jian-Feng], Wang, L.J.[Li-Juan], Peng, J.[Jian], Wang, Y.X.[Yu-Xiong], Zhang, L.[Lei],
DAP: Detection-Aware Pre-training with Weak Supervision,
CVPR21(4535-4544)
IEEE DOI 2111
Training, Location awareness, Transforms, Object detection, Detectors, Predictive models BibRef

Chaman, A.[Anadi], Dokmanic, I.[Ivan],
Truly shift-invariant convolutional neural networks,
CVPR21(3772-3782)
IEEE DOI 2111
Training, Adaptive systems, Convolution, Pattern recognition, Convolutional neural networks BibRef

Takahashi, N.[Naoya], Mitsufuji, Y.[Yuki],
Densely connected multidilated convolutional networks for dense prediction tasks,
CVPR21(993-1002)
IEEE DOI 2111
Image segmentation, Image resolution, Source separation, Convolution, Semantics, Computer architecture, Topology BibRef

Wang, P.[Peng], Han, K.[Kai], Wei, X.S.[Xiu-Shen], Zhang, L.[Lei], Wang, L.[Lei],
Contrastive Learning based Hybrid Networks for Long-Tailed Image Classification,
CVPR21(943-952)
IEEE DOI 2111
Network structure being composed of a supervised contrastive loss to learn image representations and a cross-entropy loss to learn classifiers. Training, Memory management, Graphics processing units, Image representation, Proposals BibRef

Dollár, P.[Piotr], Singh, M.[Mannat], Girshick, R.[Ross],
Fast and Accurate Model Scaling,
CVPR21(924-932)
IEEE DOI 2111
Runtime, Computational modeling, Hardware, Pattern recognition, Compounds, Convolutional neural networks BibRef

Han, D.Y.[Dong-Yoon], Yun, S.[Sangdoo], Heo, B.[Byeongho], Yoo, Y.J.[Young-Joon],
Rethinking Channel Dimensions for Efficient Model Design,
CVPR21(732-741)
IEEE DOI 2111

WWW Link. Image segmentation, Computational modeling, Search methods, Transfer learning, Object detection, Network architecture, Computational efficiency BibRef

Girish, S.[Sharath], Maiya, S.R.[Shishira R], Gupta, K.[Kamal], Chen, H.[Hao], Davis, L.[Larry], Shrivastava, A.[Abhinav],
The Lottery Ticket Hypothesis for Object Recognition,
CVPR21(762-771)
IEEE DOI 2111
States that deep neural networks trained on large datasets contain smaller subnetworks that achieve on par performance as the dense networks. Training, Performance evaluation, Computational modeling, Pipelines, Estimation, Object detection, Software BibRef

Lin, J.M.[Jamie Menjay], Noorzad, P.[Parham], Yang, Y.[Yang], Kwak, N.[Nojun], Porikli, F.M.[Fatih M.],
Phase Selective Convolution,
EVW21(3193-3202)
IEEE DOI 2109
Measurement, Tensors, Convolution, Estimation, Network architecture, Search problems, Pattern recognition BibRef

Misra, D.[Diganta], Nalamada, T.[Trikay], Arasanipalai, A.U.[Ajay Uppili], Hou, Q.[Qibin],
Rotate to Attend: Convolutional Triplet Attention Module,
WACV21(3138-3147)
IEEE DOI 2106
For an input tensor, triplet attention builds inter-dimensional dependencies by the rotation operation followed by residual transformations and encodes inter-channel and spatial information with negligible computational overhead. Convolutional codes, Tensors, Object detection. BibRef

Babicz, D.[Dóra], Kontár, S.[Soma], Peto, M.[Márk], Fülöp, A.[András], Szabó, G.[Gergely], Horváth, A.[András],
Receptive Field Size Optimization with Continuous Time Pooling,
WACV21(1448-1457)
IEEE DOI 2106
Training, Quantization (signal), Perturbation methods, Neurons, Differential equations, Computer architecture, Network architecture BibRef

Huang, G.X.[Guo-Xi], Bors, A.G.[Adrian G.],
Region-based Non-local Operation for Video Classification,
ICPR21(10010-10017)
IEEE DOI 2105
Code, Classification.
WWW Link. Integrate into existing CNN framework. Training, Convolution, Stacking, Benchmark testing, Convolutional neural networks, Optimization BibRef

Mantini, P.[Pranav], Shah, S.K.[Shishr K.],
CQNN: Convolutional Quadratic Neural Networks,
ICPR21(9819-9826)
IEEE DOI 2105
Training, Computational modeling, Atomic layer deposition, Neurons, Computer architecture, Feature extraction BibRef

Yang, X.Y.[Xing-Yu], Meng, M.Y.[Ming-Yuan], Xiao, S.L.[Shan-Lin], Yu, Z.Y.[Zhi-Yi],
SPA: Stochastic Probability Adjustment for System Balance of Unsupervised SNNs,
ICPR21(6417-6424)
IEEE DOI 2105
Training, Transmitters, Computational modeling, Biological system modeling, Neurons, Stochastic processes, Brownian process BibRef

Finnveden, L.[Lukas], Jansson, Y.[Ylva], Lindeberg, T.[Tony],
Understanding when spatial transformer networks do not support invariance, and what to do about it,
ICPR21(3427-3434)
IEEE DOI 2105
a way to do translation invariance in CNN. Location awareness, Transforms, Complexity theory, Convolutional neural networks BibRef

Lin, X.D.[Xu-Dong], Ma, L.[Lin], Liu, W.[Wei], Chang, S.F.[Shih-Fu],
Context-gated Convolution,
ECCV20(XVIII:701-718).
Springer DOI 2012
BibRef

Ma, N.N.[Ning-Ning], Zhang, X.Y.[Xiang-Yu], Huang, J.W.[Jia-Wei], Sun, J.[Jian],
WeightNet: Revisiting the Design Space of Weight Networks,
ECCV20(XV:776-792).
Springer DOI 2011
Code, Neural Nets.
WWW Link. Unifies two current distinct and extremely effective SENet and CondConv. BibRef

Wu, L.H.[Lin-Huang], Yang, X.J.[Xiu-Jun], Fan, Z.J.[Zhen-Jia], Wang, C.J.[Chun-Jun], Chen, Z.F.[Zhi-Feng],
Channel-Spatial fusion aware net for accurate and fast object Detection,
ICIP20(758-762)
IEEE DOI 2011
Detectors, Convolution, Object detection, Complexity theory, Computer architecture, Feature extraction, Real-time systems, fusion awareness BibRef

Habi, H.V.[Hai Victor], Jennings, R.H.[Roy H.], Netzer, A.[Arnon],
HMQ: Hardware Friendly Mixed Precision Quantization Block for CNNs,
ECCV20(XXVI:448-463).
Springer DOI 2011
BibRef

Li, D.[Duo], Yao, A.B.[An-Bang], Chen, Q.F.[Qi-Feng],
PSConv: Squeezing Feature Pyramid into One Compact Poly-Scale Convolutional Layer,
ECCV20(XXI:615-632).
Springer DOI 2011
Code, CNN.
WWW Link. BibRef

Shen, W.[Wen], Zhang, B.B.[Bin-Bin], Huang, S.K.[Shi-Kun], Wei, Z.H.[Zhi-Hua], Zhang, Q.S.[Quan-Shi],
3D-Rotation-Equivariant Quaternion Neural Networks,
ECCV20(XX:531-547).
Springer DOI 2011
BibRef

Huang, Y.[Yi], Wang, F.[Fan], Kong, A.W.K.[Adams Wai-Kin], Lam, K.Y.[Kwok-Yan],
New Threats Against Object Detector with Non-local Block,
ECCV20(XX:481-497).
Springer DOI 2011
Introduce of non-local blocks to the traditional CNN architecture. BibRef

Teney, D.[Damien], Abbasnedjad, E.[Ehsan], van den Hengel, A.[Anton],
Learning What Makes a Difference from Counterfactual Examples and Gradient Supervision,
ECCV20(X:580-599).
Springer DOI 2011
Dealing with the issue of spurious learning. BibRef

Li, L.[Lida], Wang, K.[Kun], Li, S.[Shuai], Feng, X.C.[Xiang-Chu], Zhang, L.[Lei],
Lst-net: Learning a Convolutional Neural Network with a Learnable Sparse Transform,
ECCV20(X:562-579).
Springer DOI 2011
BibRef

Pérez, J.C.[Juan C.], Alfarra, M.[Motasem], Jeanneret, G.[Guillaume], Bibi, A.[Adel], Thabet, A.[Ali], Ghanem, B.[Bernard], Arbeláez, P.[Pablo],
Gabor Layers Enhance Network Robustness,
ECCV20(IX:450-466).
Springer DOI 2011
BibRef

Kim, S.[Seungryong], Süsstrunk, S.[Sabine], Salzmann, M.[Mathieu],
Volumetric Transformer Networks,
ECCV20(XXVIII:561-578).
Springer DOI 2011
different features, have different transformation, CNN imposes the same on all. BibRef

Du, X.Z.[Xian-Zhi], Lin, T.Y.[Tsung-Yi], Jin, P.C.[Peng-Chong], Cui, Y.[Yin], Tan, M.X.[Ming-Xing], Le, Q.[Quoc], Song, X.D.[Xiao-Dan],
Efficient Scale-Permuted Backbone with Learned Resource Distribution,
ECCV20(XXIII:572-586).
Springer DOI 2011
SpineNet. BibRef

Huh, M.Y.[Min-Young], Zhang, R.[Richard], Zhu, J.Y.[Jun-Yan], Paris, S.[Sylvain], Hertzmann, A.[Aaron],
Transforming and Projecting Images into Class-conditional Generative Networks,
ECCV20(II:17-34).
Springer DOI 2011
Code, GAN.
WWW Link. BibRef

Patel, Y.[Yash], Hodan, T.[Tomáš], Matas, J.[Jirí],
Learning Surrogates via Deep Embedding,
ECCV20(XXX: 205-221).
Springer DOI 2010
BibRef

Quader, N.[Niamul], Bhuiyan, M.M.I.[Md Mafijul Islam], Lu, J.W.[Ju-Wei], Dai, P.[Peng], Li, W.[Wei],
Weight Excitation: Built-in Attention Mechanisms in Convolutional Neural Networks,
ECCV20(XXX: 87-103).
Springer DOI 2010
BibRef

Bose, L.[Laurie], Dudek, P.[Piotr], Chen, J.N.[Jia-Ning], Carey, S.J.[Stephen J.], Mayol-Cuevas, W.W.[Walterio W.],
Fully Embedding Fast Convolutional Networks on Pixel Processor Arrays,
ECCV20(XXIX: 488-503).
Springer DOI 2010
BibRef

Li, D.[Duo], Yao, A.B.[An-Bang], Chen, Q.F.[Qi-Feng],
Learning to Learn Parameterized Classification Networks for Scalable Input Images,
ECCV20(XXIX: 19-35).
Springer DOI 2010
Code, CNN.
WWW Link. CNNs don't do well with resolution changes. BibRef

Li, Q.S.[Qin-Song], Liu, S.J.[Sheng-Jun], Hu, L.[Ling], Liu, X.R.[Xin-Ru],
Shape correspondence using anisotropic Chebyshev spectral CNNs,
CVPR20(14646-14655)
IEEE DOI 2008
Shape, Manifolds, Convolution, Kernel, Machine learning, Eigenvalues and eigenfunctions, Chebyshev approximation BibRef

Chi, L.[Lu], Yuan, Z.H.[Ze-Huan], Mu, Y.D.[Ya-Dong], Wang, C.H.[Chang-Hu],
Non-Local Neural Networks With Grouped Bilinear Attentional Transforms,
CVPR20(11801-11810)
IEEE DOI 2008
Model spatial. Convolution, Transforms, Kernel, Computer architecture, Task analysis, Biological neural networks BibRef

Choy, C.[Christopher], Lee, J.H.[Jun-Ha], Ranftl, R.[René], Park, J.[Jaesik], Koltun, V.[Vladlen],
High-Dimensional Convolutional Networks for Geometric Pattern Recognition,
CVPR20(11224-11233)
IEEE DOI 2008
4-D to 32-D. Kernel, Pattern recognition, Estimation, Robustness, Noise measurement BibRef

Li, S.H.[Shao-Hua], Xue, K.P.[Kai-Ping], Zhu, B.[Bin], Ding, C.K.[Chen-Kai], Gao, X.D.[Xin-Di], Wei, D.[David], Wan, T.[Tao],
FALCON: A Fourier Transform Based Approach for Fast and Secure Convolutional Neural Network Predictions,
CVPR20(8702-8711)
IEEE DOI 2008
To classify private images with a public service. Servers, Encryption, Protocols, Predictive models, Data models, Computational modeling BibRef

Chodosh, N., Lucey, S.,
When to Use Convolutional Neural Networks for Inverse Problems,
CVPR20(8223-8232)
IEEE DOI 2008
Inverse problems, Convolutional codes, Convolution, Encoding, Mathematical model, Task analysis, Dictionaries BibRef

Cai, Z., Vasconcelos, N.,
Rethinking Differentiable Search for Mixed-Precision Neural Networks,
CVPR20(2346-2355)
IEEE DOI 2008
Complexity theory, Computer architecture, Neural networks, Bit rate, Sensitivity, Task analysis, Optimization BibRef

Yang, L., Han, Y., Chen, X., Song, S., Dai, J., Huang, G.,
Resolution Adaptive Networks for Efficient Inference,
CVPR20(2366-2375)
IEEE DOI 2008
Redundancy, Adaptive systems, Spatial resolution, Adaptation models, Feature extraction, Task analysis, Computer architecture BibRef

Wang, C., Liao, H.M.[H. Mark], Wu, Y., Chen, P., Hsieh, J., Yeh, I.,
CSPNet: A New Backbone that can Enhance Learning Capability of CNN,
LPCV20(1571-1580)
IEEE DOI 2008
Object detection, Computer architecture, Detectors, Mathematical model, Computational modeling, Computer science BibRef

Wang, M., Liu, B., Foroosh, H.,
Wide Hidden Expansion Layer for Deep Convolutional Neural Networks,
WACV20(923-931)
IEEE DOI 2006
Memory management, Tensile stress, Neurons, Kernel, Complexity theory, Convolutional neural networks BibRef

Li, S.C.[Sui-Chan], Chen, D.P.[Da-Peng], Liu, B.[Bin], Yu, N.H.[Neng-Hai], Zhao, R.[Rui],
Memory-Based Neighbourhood Embedding for Visual Recognition,
ICCV19(6101-6110)
IEEE DOI 2004
Enhance a CNN. convolutional neural nets, feature extraction, image retrieval, learning (artificial intelligence), object recognition, Image recognition BibRef

Zhang, Z.Y.[Zhao-Yang], Li, J.Y.[Jing-Yu], Shao, W.Q.[Wen-Qi], Peng, Z.L.[Zhang-Lin], Zhang, R.M.[Rui-Mao], Wang, X.G.[Xiao-Gang], Luo, P.[Ping],
Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks,
ICCV19(3541-3550)
IEEE DOI 2004
computational complexity, convolutional neural nets, learning (artificial intelligence), group convolution, Convolutional neural networks BibRef

Li, D., Zhou, A., Yao, A.,
HBONet: Harmonious Bottleneck on Two Orthogonal Dimensions,
ICCV19(3315-3324)
IEEE DOI 2004
Code, Convolutional Neural Nets.
WWW Link. convolutional neural nets, feature extraction, image classification, image representation, object detection, Tensile stress BibRef

Radosavovic, I.[Ilija], Johnson, J.[Justin], Xie, S.N.[Sai-Ning], Lo, W.Y.[Wan-Yen], Dollar, P.[Piotr],
On Network Design Spaces for Visual Recognition,
ICCV19(1882-1890)
IEEE DOI 2004
neural net architecture, statistical analysis, standard model families, visual recognition, Standards BibRef

Ding, X., Guo, Y., Ding, G., Han, J.,
ACNet: Strengthening the Kernel Skeletons for Powerful CNN via Asymmetric Convolution Blocks,
ICCV19(1911-1920)
IEEE DOI 2004
convolutional neural nets, learning (artificial intelligence), ACNet, kernel skeletons, convolutional neural network, Computational modeling BibRef

Liu, Y.[Yu], Liu, J.H.[Ji-Hao], Wang, X.G.[Xiao-Gang], Zeng, A.L.[Ai-Ling],
Differentiable Kernel Evolution,
ICCV19(1834-1843)
IEEE DOI 2004
convolutional neural nets, evolutionary computation, face recognition, gradient methods, greedy algorithms, Interpolation BibRef

Kim, Y.D.[Young-Dong], Yim, J.[Junho], Yun, J.[Juseung], Kim, J.[Junmo],
NLNL: Negative Learning for Noisy Labels,
ICCV19(101-110)
IEEE DOI 2004
convolutional neural nets, image classification, image denoising, image filtering, learning (artificial intelligence), convergence BibRef

Abduraimjonov, A., Choi, H., Ko, J.,
Extending Input Channel Using Global Feature Image for Convolutional Neural Networks,
IVCNZ19(1-4)
IEEE DOI 2004
convolutional neural nets, feature extraction, learning (artificial intelligence), convolutional networks BibRef

Yang, T.Y.[Tsun-Yi], Nguyen, D.K.[Duy Kien], Heijnen, H.[Huub], Balntas, V.[Vassileios],
DAME WEB: DynAmic MEan with Whitening Ensemble Binarization for Landmark Retrieval without Human Annotation,
CEFRL19(2913-2922)
IEEE DOI 2004
feature extraction, image classification, image matching, image retrieval, learning (artificial intelligence), neural nets, whitening BibRef

Kortylewski, A.[Adam], Liu, Q.[Qing], Wang, H.Y.[Hui-Yu], Zhang, Z.S.[Zhi-Shuai], Yuille, A.L.[Alan L.],
Combining Compositional Models and Deep Networks For Robust Object Classification under Occlusion,
WACV20(1322-1330)
IEEE DOI 2006
BibRef
And:
Localizing Occluders with Compositional Convolutional Networks,
NeruArch19(2029-2032)
IEEE DOI 2004
Robustness, Dictionaries, Data models, Mathematical model, Feature extraction, Solid modeling. convolutional neural nets, image classification, learning (artificial intelligence), Compositional Models BibRef

Cao, Y., Xu, J., Lin, S., Wei, F., Hu, H.,
GCNet: Non-Local Networks Meet Squeeze-Excitation Networks and Beyond,
NeruArch19(1971-1980)
IEEE DOI 2004
convolutional neural nets, image retrieval, object detection, query processing, global context network, network archietcture BibRef

Huang, Y., Ou, P., Wu, R., Feng, Z.,
Sequentially Aggregated Convolutional Networks,
NeruArch19(1900-1909)
IEEE DOI 2004
Code Convolutional Networks.
WWW Link. convolutional neural nets, image classification, learning (artificial intelligence), optimisation, Image classification BibRef

Gamba, M., Azizpour, H., Carlsson, S., Björkman, M.,
On the Geometry of Rectifier Convolutional Neural Networks,
SDL-CV19(793-797)
IEEE DOI 2004
convolutional neural nets, learning (artificial intelligence), gradient descent, natural data, preactivation space, understanding BibRef

Elad, A., Haviv, D., Blau, Y., Michaeli, T.,
Direct Validation of the Information Bottleneck Principle for Deep Nets,
SDL-CV19(758-762)
IEEE DOI 2004
entropy, learning (artificial intelligence), neural nets, direct validation, information bottleneck principle, deep nets, Information Bottleneck BibRef

Kumar, D.[Dinesh], Sharma, D.[Dharmendra], Goecke, R.[Roland],
Feature Map Augmentation to Improve Rotation Invariance in Convolutional Neural Networks,
ACIVS20(348-359).
Springer DOI 2003
BibRef

Mukundan, A.[Arun], Tolias, G.[Giorgos], Chum, O.[Ondrej],
Explicit Spatial Encoding for Deep Local Descriptors,
CVPR19(9386-9395).
IEEE DOI 2002
BibRef

Xue, C.[Chao], Yan, J.C.[Jun-Chi], Yan, R.[Rong], Chu, S.M.[Stephen M.], Hu, Y.G.[Yong-Gang], Lin, Y.[Yonghua],
Transferable AutoML by Model Sharing Over Grouped Datasets,
CVPR19(8994-9003).
IEEE DOI 2002
Automated Machine Learning. BibRef

Li, X.[Xilai], Song, X.[Xi], Wu, T.F.[Tian-Fu],
AOGNets: Compositional Grammatical Architectures for Deep Learning,
CVPR19(6213-6223).
IEEE DOI 2002
grammar models and DNNs. BibRef

Liu, C.[Chang], Wan, F.[Fang], Ke, W.[Wei], Xiao, Z.W.[Zhuo-Wei], Yao, Y.[Yuan], Zhang, X.S.[Xiao-Song], Ye, Q.X.[Qi-Xiang],
Orthogonal Decomposition Network for Pixel-Wise Binary Classification,
CVPR19(6057-6066).
IEEE DOI 2002
CNN uses convolution so single pixel classification is not done. BibRef

Shevlev, I.[Irina], Avidan, S.[Shai],
Co-Occurrence Neural Network,
CVPR19(4792-4799).
IEEE DOI 2002
Adding spatial information. BibRef

Li, X.[Xiang], Chen, S.[Shuo], Hu, X.L.[Xiao-Lin], Yang, J.[Jian],
Understanding the Disharmony Between Dropout and Batch Normalization by Variance Shift,
CVPR19(2677-2685).
IEEE DOI 2002
BibRef

Lee, Y.[Yeonkun], Jeong, J.[Jaeseok], Yun, J.[Jongseob], Cho, W.[Wonjune], Yoon, K.J.[Kuk-Jin],
SpherePHD: Applying CNNs on a Spherical PolyHeDron Representation of 360deg Images,
CVPR19(9173-9181).
IEEE DOI 2002
BibRef

Komarichev, A.[Artem], Zhong, Z.[Zichun], Hua, J.[Jing],
A-CNN: Annularly Convolutional Neural Networks on Point Clouds,
CVPR19(7413-7422).
IEEE DOI 2002
BibRef

Osawa, K.[Kazuki], Tsuji, Y.[Yohei], Ueno, Y.[Yuichiro], Naruse, A.[Akira], Yokota, R.[Rio], Matsuoka, S.[Satoshi],
Large-Scale Distributed Second-Order Optimization Using Kronecker-Factored Approximate Curvature for Deep Convolutional Neural Networks,
CVPR19(12351-12359).
IEEE DOI 2002
BibRef

Engilberge, M.[Martin], Chevallier, L.[Louis], Perez, P.[Patrick], Cord, M.[Matthieu],
SoDeep: A Sorting Deep Net to Learn Ranking Loss Surrogates,
CVPR19(10784-10793).
IEEE DOI 2002
BibRef

Su, Y.C.[Yu-Chuan], Grauman, K.[Kristen],
Kernel Transformer Networks for Compact Spherical Convolution,
CVPR19(9434-9443).
IEEE DOI 2002
BibRef

Xu, D.J.[De-Jiang], Lee, M.L.[Mong Li], Hsu, W.[Wynne],
Propagation Mechanism for Deep and Wide Neural Networks,
CVPR19(9212-9220).
IEEE DOI 2002
BibRef

Chen, Q.[Qiuyu], Zhang, W.[Wei], Yu, J.[Jun], Fan, J.P.[Jian-Ping],
Embedding Complementary Deep Networks for Image Classification,
CVPR19(9230-9239).
IEEE DOI 2002
BibRef

Duan, Y.Q.[Yue-Qi], Chen, L.[Lei], Lu, J.W.[Ji-Wen], Zhou, J.[Jie],
Deep Embedding Learning With Discriminative Sampling Policy,
CVPR19(4959-4968).
IEEE DOI 2002
BibRef

Singh, P.[Pravendra], Verma, V.K.[Vinay Kumar], Rai, P.[Piyush], Namboodiri, V.P.[Vinay P.],
Leveraging Filter Correlations for Deep Model Compression,
WACV20(824-833)
IEEE DOI 2006
BibRef
And:
HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs,
CVPR19(4830-4839).
IEEE DOI 2002
Correlation, Memory management, Quantization (signal), Redundancy, Transmission line measurements, Acceleration, Task analysis BibRef

Kumawat, S.[Sudhakar], Raman, S.[Shanmuganathan],
LP-3DCNN: Unveiling Local Phase in 3D Convolutional Neural Networks,
CVPR19(4898-4907).
IEEE DOI 2002
BibRef

Choy, C.[Christopher], Gwak, J.Y.[Jun-Young], Savarese, S.[Silvio],
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks,
CVPR19(3070-3079).
IEEE DOI 2002
BibRef

Mehta, D.[Dushyant], Kim, K.I.[Kwang In], Theobalt, C.[Christian],
On Implicit Filter Level Sparsity in Convolutional Neural Networks,
CVPR19(520-528).
IEEE DOI 2002
BibRef

Li, X.[Xiang], Wang, W.[Wenhai], Hu, X.L.[Xiao-Lin], Yang, J.[Jian],
Selective Kernel Networks,
CVPR19(510-519).
IEEE DOI 2002
BibRef

Tsuzuku, Y.[Yusuke], Sato, I.[Issei],
On the Structural Sensitivity of Deep Convolutional Networks to the Directions of Fourier Basis Functions,
CVPR19(51-60).
IEEE DOI 2002
BibRef

Wang, C.[Chen], Yang, J.F.[Jian-Fei], Xie, L.H.[Li-Hua], Yuan, J.S.[Jun-Song],
Kervolutional Neural Networks,
CVPR19(31-40).
IEEE DOI 2002
kernel convolution BibRef

Nguyen, A., Choi, S., Kim, W., Ahn, S., Kim, J., Lee, S.,
Distribution Padding in Convolutional Neural Networks,
ICIP19(4275-4279)
IEEE DOI 1910
Deep learning, convolutional neural network, image padding BibRef

Hataya, R.[Ryuichiro], Nakayama, H.[Hideki],
LOL: Learning To Optimize Loss Switching Under Label Noise,
ICIP19(3621-3625)
IEEE DOI 1910
Deal with label corruption. Alternate between Categorical cross entropy and mean absolute error. BibRef

Zhang, K.[Ke], Guo, Y.R.[Yu-Rong], Wang, X.S.[Xin-Sheng], Yuan, J.S.[Jin-Sha], Ma, Z.Y.[Zhan-Yu], Zhao, Z.B.[Zhen-Bing],
Channel-Wise and Feature-Points Reweights DenseNet for Image Classification,
ICIP19(410-414)
IEEE DOI 1910
CFR-DenseNet, CAPR-DenseNet, FPRM, SEM, Image classification BibRef

Eda, T., Muramatsu, S., Enomoto, S., Xu, S.,
An Expandable Deep Learning Inference Framework With Adjustability to Workload Requirement,
ICIP19(2454-2454)
IEEE DOI 1910
BibRef

Zhang, K., Zhou, X., Wu, J.,
U-Module: Better Parameters Initialization of Convolutional Neural Network for Medical Image Classification,
ICIP19(799-803)
IEEE DOI 1910
U-module, convolutional neural network, unsupervised loss, parameters initialization BibRef

Köpüklü, O., Babaee, M., Hörmann, S., Rigoll, G.,
Convolutional Neural Networks with Layer Reuse,
ICIP19(345-349)
IEEE DOI 1910
layer reuse, convolutional neural networks, inference routing BibRef

Rodriguez, R., Dokladalova, E., Dokladal, P.,
Rotation Invariant CNN Using Scattering Transform for Image Classification,
ICIP19(654-658)
IEEE DOI 1910
Rotation, invariant, covariant, convolutional neural network, image classification BibRef

Cotter, F., Kingsbury, N.,
A Learnable Scatternet: Locally Invariant Convolutional Layers,
ICIP19(350-354)
IEEE DOI 1910
CNN, ScatterNet, invariant, wavelet, DTCWT BibRef

Jiang, R., Mei, S.,
Polar Coordinate Convolutional Neural Network: From Rotation-Invariance to Translation-Invariance,
ICIP19(355-359)
IEEE DOI 1910
rotation-invariant, convolutional neural network, image classification, polar coordinate BibRef

Peralta, B.[Billy], Reyes, J.[Juan], Caro, L.[Luis], Pieringer, C.[Christian],
A Proposal of Neural Networks with Intermediate Outputs,
IbPRIA19(I:206-215).
Springer DOI 1910
BibRef

Belbahri, M.[Mouloud], Sari, E.[Eyyüb], Darabi, S.[Sajad], Nia, V.P.[Vahid Partovi],
Foothill: A Quasiconvex Regularization for Edge Computing of Deep Neural Networks,
ICIAR19(II:3-14).
Springer DOI 1909
BibRef

Wong, A.[Alexander],
NetScore: Towards Universal Metrics for Large-Scale Performance Analysis of Deep Neural Networks for Practical On-Device Edge Usage,
ICIAR19(II:15-26).
Springer DOI 1909
BibRef

Xin, Y.J.[Yong-Jian], Wang, S.H.[Shu-Hui], Li, L.[Liang], Zhang, W.G.[Wei-Gang], Huang, Q.M.[Qing-Ming],
Reverse Densely Connected Feature Pyramid Network for Object Detection,
ACCV18(V:530-545).
Springer DOI 1906
BibRef

Wang, J.H.[Jing-Hua], Jiang, J.M.[Jian-Min],
An Unsupervised Deep Learning Framework via Integrated Optimization of Representation Learning and GMM-Based Modeling,
ACCV18(I:249-265).
Springer DOI 1906
unsupervised deep learning framework. BibRef

Kim, J.B.[Jun-Bong], Lee, M.[Minki], Choi, J.E.[Jong-Eun], Seo, K.S.[Ki-Sung],
GA-Based Filter Selection for Representation in Convolutional Neural Networks,
CEFR-LCV18(IV:609-618).
Springer DOI 1905
BibRef

Chitta, K.[Kashyap],
Targeted Kernel Networks: Faster Convolutions with Attentive Regularization,
CEFR-LCV18(IV:379-397).
Springer DOI 1905
CNN constrained by Attentive Regularization. BibRef

Martinez, M.[Manuel], Stiefelhagen, R.[Rainer],
Taming the Cross Entropy Loss,
GCPR18(628-637).
Springer DOI 1905
BibRef

Lee, Y., Jung, H., Han, D., Kim, K., Kim, J.,
Learning Receptive Field Size by Learning Filter Size,
WACV19(1203-1212)
IEEE DOI 1904
backpropagation, convolutional neural nets, image classification, learning (artificial intelligence), resource allocation, Computer architecture BibRef

Wang, Y., Kato, J.,
Good Choices for Deep Convolutional Feature Encoding,
WACV19(312-320)
IEEE DOI 1904
convolutional neural nets, feature extraction, image coding, image recognition, deep convolutional feature encoding, Convolutional codes BibRef

Atkinson, C., McCane, B., Szymanski, L.,
Increasing the accuracy of convolutional neural networks with progressive reinitialisation,
IVCNZ17(1-5)
IEEE DOI 1902
convolution, feedforward neural nets, freezing, image classification, progressive reinitialisation, Network architecture BibRef

Zoph, B.[Barret], Vasudevan, V.[Vijay], Shlens, J.[Jonathon], Le, Q.V.[Quoc V.],
Learning Transferable Architectures for Scalable Image Recognition,
CVPR18(8697-8710)
IEEE DOI 1812
Computer architecture, Microprocessors, Computational modeling, Aerospace electronics, Convolution, Google, Search methods BibRef

Hu, J.[Jie], Shen, L.[Li], Sun, G.[Gang],
Squeeze-and-Excitation Networks,
CVPR18(7132-7141)
IEEE DOI 1812
Computer architecture, Computational modeling, Convolution, Task analysis, Convolutional codes, Adaptation models, Stacking BibRef

Detlefsen, N.S.[Nicki Skafte], Freifeld, O.[Oren], Hauberg, S.[Sřren],
Deep Diffeomorphic Transformer Networks,
CVPR18(4403-4412)
IEEE DOI 1812
Face, Neural networks, Computer architecture, Standards, Task analysis, Computational modeling, Kernel BibRef

Cheng, C.M.[Chang-Mao], Fu, Y.W.[Yan-Wei], Jiang, Y.G.[Yu-Gang], Liu, W.[Wei], Lu, W.L.[Wen-Lian], Feng, J.F.[Jian-Feng], Xue, X.Y.[Xiang-Yang],
Dual Skipping Networks,
CVPR18(4071-4079)
IEEE DOI 1812
Low frequency and high frequency separate. Visualization, Convolution, Neuroscience, Task analysis, Testing, Computational modeling BibRef

Gast, J.[Jochen], Roth, S.[Stefan],
Lightweight Probabilistic Deep Networks,
CVPR18(3369-3378)
IEEE DOI 1812
Uncertainty, Probabilistic logic, Bayes methods, Neural networks, Standards, Computer architecture, Supervised learning BibRef

Pan, B.W.[Bo-Wen], Lin, W.W.[Wu-Wei], Fang, X.L.[Xiao-Lin], Huang, C.Q.[Chao-Qin], Zhou, B.L.[Bo-Lei], Lu, C.W.[Ce-Wu],
Recurrent Residual Module for Fast Inference in Videos,
CVPR18(1536-1545)
IEEE DOI 1812
CNN for video. Videos, Convolution, Acceleration, Computational modeling, Task analysis, Engines BibRef

Hosseini, H., Xiao, B., Jaiswal, M., Poovendran, R.,
Assessing Shape Bias Property of Convolutional Neural Networks,
Cognitive18(2004-20048)
IEEE DOI 1812
Pattern recognition. BibRef

Wang, S., Suo, S., Ma, W., Pokrovsky, A., Urtasun, R.,
Deep Parametric Continuous Convolutional Neural Networks,
CVPR18(2589-2597)
IEEE DOI 1812
Convolution, Kernel, Neural networks, Standards, Computer architecture BibRef

Dutta, S., Tripp, B., Taylor, G.W.,
Convolutional Neural Networks Regularized by Correlated Noise,
CRV18(375-382)
IEEE DOI 1812
Neurons, Correlation, Stochastic processes, Visualization, Biological neural networks, Additives, Correlated Variability, Stochastic Neurons BibRef

Modasshir, M., Quattrini Li, A., Rekleitis, I.,
Deep Neural Networks: A Comparison on Different Computing Platforms,
CRV18(383-389)
IEEE DOI 1812
Task analysis, Robots, Graphics processing units, Portable computers, Embedded systems, Neural networks, Comparison BibRef

Wang, Y.[Yan], Xie, L.X.[Ling-Xi], Qiao, S.Y.[Si-Yuan], Zhang, Y.[Ya], Zhang, W.J.[Wen-Jun], Yuille, A.L.[Alan L.],
Multi-scale Spatially-Asymmetric Recalibration for Image Classification,
ECCV18(XIII: 523-539).
Springer DOI 1810
To get spatial information in features using multiple scales. BibRef

Fan, Q.N.[Qing-Nan], Chen, D.D.[Dong-Dong], Yuan, L.[Lu], Hua, G.[Gang], Yu, N.H.[Neng-Hai], Chen, B.Q.[Bao-Quan],
Decouple Learning for Parameterized Image Operators,
ECCV18(XIII: 455-471).
Springer DOI 1810
BibRef

Wang, X.[Xin], Yu, F.[Fisher], Dou, Z.Y.[Zi-Yi], Darrell, T.J.[Trevor J.], Gonzalez, J.E.[Joseph E.],
SkipNet: Learning Dynamic Routing in Convolutional Networks,
ECCV18(XIII: 420-436).
Springer DOI 1810
Skip deep layers for simple tasks. BibRef

Zhu, X.Y.[Xuan-Yu], Xu, Y.[Yi], Xu, H.T.[Hong-Teng], Chen, C.J.[Chang-Jian],
Quaternion Convolutional Neural Networks,
ECCV18(VIII: 645-661).
Springer DOI 1810
BibRef

Zhang, S.[Shun], Xie, D.[Di], Pu, S.L.[Shi-Liang],
Extreme Network Compression via Filter Group Approximation,
ECCV18(VIII: 307-323).
Springer DOI 1810
BibRef

Lai, W.S.[Wei-Sheng], Huang, J.B.[Jia-Bin], Wang, O.[Oliver], Shechtman, E.[Eli], Yumer, E.[Ersin], Yang, M.H.[Ming-Hsuan],
Learning Blind Video Temporal Consistency,
ECCV18(XV: 179-195).
Springer DOI 1810
BibRef

Carreira, J.[Joăo], Patraucean, V.[Viorica], Mazare, L.[Laurent], Zisserman, A.[Andrew], Osindero, S.[Simon],
Massively Parallel Video Networks,
ECCV18(II: 680-697).
Springer DOI 1810
BibRef

Xie, S.N.[Sai-Ning], Sun, C.[Chen], Huang, J.[Jonathan], Tu, Z.W.[Zhuo-Wen], Murphy, K.[Kevin],
Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classification,
ECCV18(XV: 318-335).
Springer DOI 1810
BibRef

Ochs, P.[Peter], Meinhardt, T.[Tim], Leal-Taixe, L.[Laura], Moeller, M.[Michael],
Lifting Layers: Analysis and Applications,
ECCV18(I: 53-68).
Springer DOI 1810
BibRef

Yu, X.[Xiyu], Liu, T.L.[Tong-Liang], Gong, M.M.[Ming-Ming], Tao, D.C.[Da-Cheng],
Learning with Biased Complementary Labels,
ECCV18(I: 69-85).
Springer DOI 1810
BibRef

Ahmed, K.[Karim], Torresani, L.[Lorenzo],
MaskConnect: Connectivity Learning by Gradient Descent,
ECCV18(VI: 362-378).
Springer DOI 1810
BibRef

Cheng, B.[Bowen], Wei, Y.C.[Yun-Chao], Shi, H.H.[Hong-Hui], Feris, R.[Rogerio], Xiong, J.J.[Jin-Jun], Huang, T.S.[Thomas S.],
Revisiting RCNN: On Awakening the Classification Power of Faster RCNN,
ECCV18(XV: 473-490).
Springer DOI 1810
BibRef

Chang, S.[Simyung], Yang, J.[John], Park, S.[Seong_Uk], Kwak, N.[Nojun],
Broadcasting Convolutional Network for Visual Relational Reasoning,
ECCV18(XV: 780-796).
Springer DOI 1810
BibRef

Son, S.H.[Sang-Hyun], Nah, S.J.[Seung-Jun], Lee, K.M.[Kyoung Mu],
Clustering Convolutional Kernels to Compress Deep Neural Networks,
ECCV18(VIII: 225-240).
Springer DOI 1810
BibRef

Chen, C.G.[Chan-Gan], Tung, F.[Frederick], Vedula, N.[Naveen], Mori, G.[Greg],
Constraint-Aware Deep Neural Network Compression,
ECCV18(VIII: 409-424).
Springer DOI 1810
BibRef

Zhang, D.Q.[Dong-Qing], Yang, J.L.[Jiao-Long], Ye, D.Q.[Dong-Qiangzi], Hua, G.[Gang],
LQ-Nets: Learned Quantization for Highly Accurate and Compact Deep Neural Networks,
ECCV18(VIII: 373-390).
Springer DOI 1810
BibRef

He, Y.H.[Yi-Hui], Lin, J.[Ji], Liu, Z.J.[Zhi-Jian], Wang, H.[Hanrui], Li, L.J.[Li-Jia], Han, S.[Song],
AMC: AutoML for Model Compression and Acceleration on Mobile Devices,
ECCV18(VII: 815-832).
Springer DOI 1810
To put NN model on mobile device. BibRef

Data, G.W.P.[Gratianus Wesley Putra], Ngu, K.[Kirjon], Murray, D.W.[David William], Prisacariu, V.A.[Victor Adrian],
Interpolating Convolutional Neural Networks Using Batch Normalization,
ECCV18(XIII: 591-606).
Springer DOI 1810
BibRef

Zhao, H.S.[Heng-Shuang], Zhang, Y.[Yi], Liu, S.[Shu], Shi, J.P.[Jian-Ping], Loy, C.C.[Chen Change], Lin, D.[Dahua], Jia, J.Y.[Jia-Ya],
PSANet: Point-wise Spatial Attention Network for Scene Parsing,
ECCV18(IX: 270-286).
Springer DOI 1810
BibRef

Wu, J.L.[Jia-Lin], Li, D.[Dai], Yang, Y.[Yu], Bajaj, C.[Chandrajit], Ji, X.Y.[Xiang-Yang],
Dynamic Filtering with Large Sampling Field for ConvNets,
ECCV18(X: 188-203).
Springer DOI 1810
BibRef

Yang, T.J.[Tien-Ju], Howard, A.[Andrew], Chen, B.[Bo], Zhang, X.[Xiao], Go, A.[Alec], Sandler, M.[Mark], Sze, V.[Vivienne], Adam, H.[Hartwig],
NetAdapt: Platform-Aware Neural Network Adaptation for Mobile Applications,
ECCV18(X: 289-304).
Springer DOI 1810
BibRef

Dong, J.D.[Jin-Dong], Cheng, A.C.[An-Chieh], Juan, D.C.[Da-Cheng], Wei, W.[Wei], Sun, M.[Min],
DPP-Net: Device-Aware Progressive Search for Pareto-Optimal Neural Architectures,
ECCV18(XI: 540-555).
Springer DOI 1810
Optimize for device properties. BibRef

Decencičre, E.[Etienne], Velasco-Forero, S.[Santiago], Min, F.[Fu], Chen, J.[Juanjuan], Burdin, H.[Hélčne], Gauthier, G.[Gervais], Bornschloegl, B.L.T.[Bruno La˙. Thomas], Baldeweck, T.[Thérčse],
Dealing with Topological Information Within a Fully Convolutional Neural Network,
ACIVS18(462-471).
Springer DOI 1810
BibRef

Kim, H.J.[Hyo Jin], Frahm, J.M.[Jan-Michael],
Hierarchy of Alternating Specialists for Scene Recognition,
ECCV18(XI: 471-488).
Springer DOI 1810
BibRef

Jayaraman, P.K.[Pradeep Kumar], Mei, J.H.[Jian-Han], Cai, J.F.[Jian-Fei], Zheng, J.M.[Jian-Min],
Quadtree Convolutional Neural Networks,
ECCV18(VI: 554-569).
Springer DOI 1810
BibRef

Kenning, M.P.[Michael P.], Xie, X.H.[Xiang-Hua], Edwards, M.[Michael], Deng, J.J.[Jing-Jing],
Local Representation Learning with A Convolutional Autoencoder,
ICIP18(3239-3243)
IEEE DOI 1809
MNIST. Convolution, Neural networks, Kernel, Encoding, Machine learning, Image reconstruction, Interpolation BibRef

Zhang, J.Y.[Jing-Yang], Jia, K.G.[Kai-Ge], Yang, P.S.[Peng-Shuai], Qiao, F.[Fei], Wei, Q.[Qi], Liu, X.J.[Xin-Jun], Yang, H.Z.[Hua-Zhong],
MINTIN: Maxout-Based and Input-Normalized Transformation Invariant Neural Network,
ICIP18(3014-3018)
IEEE DOI 1809
Need to deal with spatial variance in input. Feature extraction, Neural networks, Network topology, Error analysis, Kernel, Calibration, Maxout BibRef

Mitschke, N., Heizmann, M., Noffz, K., Wittmann, R.,
Gradient Based Evolution to Optimize the Structure of Convolutional Neural Networks,
ICIP18(3438-3442)
IEEE DOI 1809
Neurons, Sociology, Statistics, Kernel, Genomics, Bioinformatics, Biological neural networks, Genetic algorithm, neural networks, neuroevolution BibRef

Nousi, P., Patsiouras, E., Tefas, A., Pitas, I.,
Convolutional Neural Networks for Visual Information Analysis with Limited Computing Resources,
ICIP18(321-325)
IEEE DOI 1809
Detectors, Computational modeling, Feature extraction, Task analysis, Visualization, Mobile handsets, Optimization, Inference Optimization BibRef

Gui, L.Y., Gui, L., Wang, Y.X., Morency, L.P., Moura, J.M.F.,
Factorized Convolutional Networks: Unsupervised Fine-Tuning for Image Clustering,
WACV18(1205-1214)
IEEE DOI 1806
convolution, feedforward neural nets, image recognition, image representation, matrix decomposition, pattern clustering, Tuning BibRef

Follmann, P., Bottger, T.,
A Rotationally-Invariant Convolution Module by Feature Map Back-Rotation,
WACV18(784-792)
IEEE DOI 1806
convolution, feature extraction, feedforward neural nets, image classification, learning (artificial intelligence), CNNs, Transforms BibRef

Guo, Y.M.[Yan-Ming], Lew, M.S.[Michael S.],
Bag of Surrogate Parts: one inherent feature of deep CNNs,
BMVC16(xx-yy).
HTML Version. 1805
BibRef

Zhao, S.W.[Shan-Wei], Zhao, Z.C.[Zhi-Cheng], Su, F.[Fei],
Gram matrix based representation for image retrieval,
VCIP17(1-4)
IEEE DOI 1804
Second order features based on convolutional layers. feedforward neural nets, image coding, image representation, image retrieval, matrix algebra, Gram matrix, image retrieval BibRef

Yim, J., Sohn, K.A.,
Enhancing the Performance of Convolutional Neural Networks on Quality Degraded Datasets,
DICTA17(1-8)
IEEE DOI 1804
convolution, image classification, image filtering, learning (artificial intelligence), neural nets, Noise reduction BibRef

Huang, M.Y.[Mou-Yue], Lai, C.H.[Ching-Hao], Chen, S.H.[Sin-Horng],
Fast and accurate image recognition using Deeply-Fused Branchy Networks,
ICIP17(2876-2880)
IEEE DOI 1803
Agriculture, Collaboration, Error analysis, Graphics processing units, Image recognition, Network topology, inference time BibRef

Dominguez, M., Such, F.P., Sah, S., Ptucha, R.,
Towards 3D convolutional neural networks with meshes,
ICIP17(3929-3933)
IEEE DOI 1803
Convolution, Convolutional neural networks, Feature extraction, Graph theory, Tensile stress, voxels BibRef

Yoshiyasu, Y., Yoshida, E., Pirk, S., Guibas, L.J.[Leonidas J.],
3D convolutional neural networks by modal fusion,
ICIP17(1777-1781)
IEEE DOI 1803
Encoding, Robots, Shape, Solid modeling, Testing, BibRef

Pasupuleti, S.K., Miniskar, N.R., Rajagopal, V., Gadde, R.N.,
A novel method to regenerate an optimal CNN by exploiting redundancy patterns in the network,
ICIP17(4407-4411)
IEEE DOI 1803
Complexity theory, Computational modeling, Convolution, Kernel, Neural networks, Redundancy, Semantics, Caffe, light-weight network BibRef

Jeon, S.R.[Sang-Ryul], Kim, S.R.[Seung-Ryong], Sohn, K.H.[Kwang-Hoon],
Convolutional feature pyramid fusion via attention network,
ICIP17(1007-1011)
IEEE DOI 1803
Computer architecture, Estimation, Feature extraction, Optical imaging, Robustness, Semantics, Visualization, feature pyramid BibRef

Ishii, M.[Masato], Sato, A.[Atsushi],
Layer-Wise Weight Decay for Deep Neural Networks,
PSIVT17(276-289).
Springer DOI 1802
BibRef

Gupta, A., Duggal, R.,
P-TELU: Parametric Tan Hyperbolic Linear Unit Activation for Deep Neural Networks,
CEFR-LCV17(974-978)
IEEE DOI 1802
Benchmark testing, Biological neural networks, Computer architecture, Convergence, Neurons, Noise robustness, Standards BibRef

Marcos, D.[Diego], Volpi, M.[Michele], Komodakis, N.[Nikos], Tuia, D.[Devis],
Rotation Equivariant Vector Field Networks,
ICCV17(5058-5067)
IEEE DOI 1802
CNN encoding roataion invariance. convolution, filtering theory, image segmentation, learning (artificial intelligence), medical image processing, BibRef

Zhang, T.[Ting], Qi, G.J.[Guo-Jun], Xiao, B.[Bin], Wang, J.D.[Jing-Dong],
Interleaved Group Convolutions,
ICCV17(4383-4392)
IEEE DOI 1802
Modularized NN. convolution, filtering theory, group theory, image classification, learning (artificial intelligence), neural nets, Tensile stress BibRef

Wang, G., Xie, X., Lai, J., Zhuo, J.,
Deep Growing Learning,
ICCV17(2831-2839)
IEEE DOI 1802
convolution, data handling, learning (artificial intelligence), neural nets, DGL, SSL framework, deep growing learning, deep network, Visualization BibRef

Zhang, Y.[Yan], Ozay, M.[Mete], Li, S.H.[Shuo-Hao], Okatani, T.[Takayuki],
Truncating Wide Networks Using Binary Tree Architectures,
ICCV17(2116-2124)
IEEE DOI 1802
image classification, learning (artificial intelligence), neural nets, pattern classification, trees (mathematics), Vegetation BibRef

Wang, Y.[Yan], Xie, L.X.[Ling-Xi], Liu, C.X.[Chen-Xi], Qiao, S.Y.[Si-Yuan], Zhang, Y.[Ya], Zhang, W.J.[Wen-Jun], Tian, Q.[Qi], Yuille, A.L.[Alan L.],
SORT: Second-Order Response Transform for Visual Recognition,
ICCV17(1368-1377)
IEEE DOI 1802
Second order operators in deep networks. image recognition, neural nets, transforms, SORT, Second-Order Response Transform, chain-styled network, Visualization BibRef

Dai, J.F.[Ji-Feng], Qi, H.Z.[Hao-Zhi], Xiong, Y.[Yuwen], Li, Y.[Yi], Zhang, G.D.[Guo-Dong], Hu, H.[Han], Wei, Y.C.[Yi-Chen],
Deformable Convolutional Networks,
ICCV17(764-773)
IEEE DOI 1802
convolution, feedforward neural nets, image segmentation, learning (artificial intelligence), BibRef

Wen, W., Xu, C., Wu, C., Wang, Y., Chen, Y., Li, H.,
Coordinating Filters for Faster Deep Neural Networks,
ICCV17(658-666)
IEEE DOI 1802
computer vision, image classification, image filtering, learning (artificial intelligence), neural nets, Tensile stress BibRef

Osherov, E., Lindenbaum, M.,
Increasing CNN Robustness to Occlusions by Reducing Filter Support,
ICCV17(550-561)
IEEE DOI 1802
image classification, image filtering, learning (artificial intelligence), neural nets, Weight measurement BibRef

Cecconi, L.[Leonardo], Smets, S.[Sander], Benini, L.[Luca], Verhelst, M.[Marian],
Optimal Tiling Strategy for Memory Bandwidth Reduction for CNNs,
ACIVS17(89-100).
Springer DOI 1712
BibRef

Ceruti, C.[Claudio], Campadelli, P.[Paola], Casiraghi, E.[Elena],
Linear Regularized Compression of Deep Convolutional Neural Networks,
CIAP17(I:244-253).
Springer DOI 1711
BibRef

Wang, P.S.[Pei-Song], Cheng, J.[Jian],
Fixed-Point Factorized Networks,
CVPR17(3966-3974)
IEEE DOI 1711
DNN. Acceleration, Computational modeling, Matrix decomposition, Neural networks, Quantization, (signal) BibRef

Jeon, Y.H.[Yun-Ho], Kim, J.[Junmo],
Active Convolution: Learning the Shape of Convolution for Image Classification,
CVPR17(1846-1854)
IEEE DOI 1711
Convolution, Convolutional codes, Interpolation, Lattices, Neurons, Shape BibRef

Chollet, F.,
Xception: Deep Learning with Depthwise Separable Convolutions,
CVPR17(1800-1807)
IEEE DOI 1711
Biological neural networks, Computer architecture, Convolutional codes, Correlation, BibRef

Zamir, A.R., Wu, T.L., Sun, L., Shen, W.B., Shi, B.E., Malik, J., Savarese, S.,
Feedback Networks,
CVPR17(1808-1817)
IEEE DOI 1711
Computer architecture, Feedforward systems, Logic gates, Microprocessors, Predictive models, Taxonomy BibRef

Harley, A.W., Derpanis, K.G., Kokkinos, I.,
Segmentation-Aware Convolutional Networks Using Local Attention Masks,
ICCV17(5048-5057)
IEEE DOI 1802
convolution, filtering theory, image segmentation, learning (artificial intelligence), neural nets, Semantics BibRef

Juefei-Xu, F.[Felix], Savvides, M.[Marios],
Learning to Invert Local Binary Patterns,
BMVC16(xx-yy).
HTML Version. 1805
BibRef

Kossaifi, J.[Jean], Khanna, A.[Aran], Lipton, Z.[Zachary], Furlanello, T.[Tommaso], Anandkumar, A.[Anima],
Tensor Contraction Layers for Parsimonious Deep Nets,
Tensor17(1940-1946)
IEEE DOI 1709
Complexity theory, Tensile stress BibRef

Araújo, T.[Teresa], Aresta, G.[Guilherme], Almada-Lobo, B.[Bernardo], Mendonça, A.M.[Ana Maria], Campilho, A.[Aurélio],
Improving Convolutional Neural Network Design via Variable Neighborhood Search,
ICIAR17(371-379).
Springer DOI 1706
BibRef

Ibrahim, A.[Ahmed], Abbott, A.L.[A. Lynn], Hussein, M.E.[Mohamed E.],
Input Fast-Forwarding for Better Deep Learning,
ICIAR17(363-370).
Springer DOI 1706
BibRef

Hernández, G.[Gerardo], Zamora, E.[Erik], Sossa, H.[Humberto],
Comparing Deep and Dendrite Neural Networks: A Case Study,
MCPR17(32-41).
Springer DOI 1706
BibRef

Tabernik, D.[Domen], Kristan, M.[Matej], Wyatt, J.L., Leonardis, A.[Aleš],
Towards deep compositional networks,
ICPR16(3470-3475)
IEEE DOI 1705
Computational modeling, Convolution, Cost function, Mathematical model, Neural networks, Standards, Visualization BibRef

Käding, C.[Christoph], Rodner, E.[Erik], Freytag, A.[Alexander], Denzler, J.[Joachim],
Fine-Tuning Deep Neural Networks in Continuous Learning Scenarios,
DeepVisual16(III: 588-605).
Springer DOI 1704
BibRef

Gao, Y., Liu, Z., Wang, D.,
Error models of finite word length arithmetic in CNN accelerator design,
VCIP16(1-4)
IEEE DOI 1701
Analytical models BibRef

Shaheen, F.[Fatma], Verma, B.[Brijesh], Asafuddoula, M.,
Impact of Automatic Feature Extraction in Deep Learning Architecture,
DICTA16(1-8)
IEEE DOI 1701
Biological neural networks BibRef

Mao, F.L.[Feng-Ling], Xiong, W.[Wei], Du, B.[Bo], Zhang, L.[Lefei],
Stochastic Decorrelation Constraint Regularized Auto-Encoder for Visual Recognition,
MMMod17(II: 368-380).
Springer DOI 1701
BibRef

Liu, Y.[Yu], Guo, Y.M.[Yan-Ming], Lew, M.S.[Michael S.],
On the Exploration of Convolutional Fusion Networks for Visual Recognition,
MMMod17(I: 277-289).
Springer DOI 1701
BibRef

Ujiie, T., Hiromoto, M., Sato, T.,
Approximated Prediction Strategy for Reducing Power Consumption of Convolutional Neural Network Processor,
ECVW16(870-876)
IEEE DOI 1612
BibRef

Honari, S.[Sina], Yosinski, J.[Jason], Vincent, P.[Pascal], Pal, C.[Christopher],
Recombinator Networks: Learning Coarse-to-Fine Feature Aggregation,
CVPR16(5743-5752)
IEEE DOI 1612
BibRef

Hu, P.Y.[Pei-Yun], Ramanan, D.[Deva],
Bottom-Up and Top-Down Reasoning with Hierarchical Rectified Gaussians,
CVPR16(5600-5609)
IEEE DOI 1612
BibRef

Lavin, A.[Andrew], Gray, S.[Scott],
Fast Algorithms for Convolutional Neural Networks,
CVPR16(4013-4021)
IEEE DOI 1612
BibRef

Misra, I.[Ishan], Shrivastava, A.[Abhinav], Gupta, A.[Abhinav], Hebert, M.[Martial],
Cross-Stitch Networks for Multi-task Learning,
CVPR16(3994-4003)
IEEE DOI 1612
Learn shared representations. BibRef

Hu, H.X.[He-Xiang], Zhou, G.T.[Guang-Tong], Deng, Z.W.[Zhi-Wei], Liao, Z.C.[Zi-Cheng], Mori, G.[Greg],
Learning Structured Inference Neural Networks with Label Relations,
CVPR16(2960-2968)
IEEE DOI 1612
Network for each layer of representation. BibRef

Szegedy, C.[Christian], Vanhoucke, V.[Vincent], Ioffe, S.[Sergey], Shlens, J.[Jon], Wojna, Z.[Zbigniew],
Rethinking the Inception Architecture for Computer Vision,
CVPR16(2818-2826)
IEEE DOI 1612
scale-up CNN recognition to larger number of classes. BibRef

Jain, A.[Ashesh], Zamir, A.R.[Amir R.], Savarese, S.[Silvio], Saxena, A.[Ashutosh],
Structural-RNN: Deep Learning on Spatio-Temporal Graphs,
CVPR16(5308-5317)
IEEE DOI 1612
Award, CVPR, Student. BibRef

Xie, L., Wang, J., Wei, Z., Wang, M., Tian, Q.,
DisturbLabel: Regularizing CNN on the Loss Layer,
CVPR16(4753-4762)
IEEE DOI 1612
BibRef

Cohen, N., Sharir, O., Shashua, A.,
Deep SimNets,
CVPR16(4782-4791)
IEEE DOI 1612
BibRef

Shankar, S., Robertson, D., Ioannou, Y., Criminisi, A., Cipolla, R.[Roberto],
Refining Architectures of Deep Convolutional Neural Networks,
CVPR16(2212-2220)
IEEE DOI 1612
BibRef

Chen, H.G., Jayasuriya, S., Yang, J., Stephen, J., Sivaramakrishnan, S., Veeraraghavan, A., Molnar, A.,
ASP Vision: Optically Computing the First Layer of Convolutional Neural Networks Using Angle Sensitive Pixels,
CVPR16(903-912)
IEEE DOI 1612
BibRef

Wang, J.D.[Jing-Dong], Yuille, A.L.[Alan L.], Tian, Q.[Qi],
InterActive: Inter-Layer Activeness Propagation,
CVPR16(270-279)
IEEE DOI 1612
BibRef

Jacobsen, J.H., van Gemert, J.C.[Jan C.], Lou, Z., Smeulders, A.W.M.,
Structured Receptive Fields in CNNs,
CVPR16(2610-2619)
IEEE DOI 1612
BibRef

Lebedev, V., Lempitsky, V.,
Fast ConvNets Using Group-Wise Brain Damage,
CVPR16(2554-2564)
IEEE DOI 1612
BibRef

Rastegar, S., Baghshah, M.S.[Mahdieh Soleymani], Rabiee, H.R.[Hamid R.], Shojaee, S.M.,
MDL-CW: A Multimodal Deep Learning Framework with CrossWeights,
CVPR16(2601-2609)
IEEE DOI 1612
BibRef

Moosavi-Dezfooli, S.M., Fawzi, A., Frossard, P.,
DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks,
CVPR16(2574-2582)
IEEE DOI 1612
BibRef

Wu, J.X.[Jia-Xiang], Leng, C.[Cong], Wang, Y.H.[Yu-Hang], Hu, Q.H.[Qing-Hao], Cheng, J.[Jian],
Quantized Convolutional Neural Networks for Mobile Devices,
CVPR16(4820-4828)
IEEE DOI 1612
Implementations. BibRef

Jin, X.J.[Xiao-Jie], Chen, Y.P.[Yun-Peng], Dong, J.[Jian], Feng, J.[Jiashi], Yan, S.C.[Shui-Cheng],
Collaborative Layer-Wise Discriminative Learning in Deep Neural Networks,
ECCV16(VII: 733-749).
Springer DOI 1611
BibRef

Goo, W.[Wonjoon], Kim, J.Y.[Ju-Yong], Kim, G.[Gunhee], Hwang, S.J.[Sung Ju],
Taxonomy-Regularized Semantic Deep Convolutional Neural Networks,
ECCV16(II: 86-101).
Springer DOI 1611
BibRef

Shen, L.[Li], Lin, Z.C.[Zhou-Chen], Huang, Q.M.[Qing-Ming],
Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks,
ECCV16(VII: 467-482).
Springer DOI 1611
BibRef

Wang, Z.Y.[Zhen-Yang], Deng, Z.D.[Zhi-Dong], Wang, S.[Shiyao],
Accelerating Convolutional Neural Networks with Dominant Convolutional Kernel and Knowledge Pre-regression,
ECCV16(VIII: 533-548).
Springer DOI 1611
BibRef

Zhou, H.[Hao], Alvarez, J.M.[Jose M.], Porikli, F.M.[Fatih M.],
Less Is More: Towards Compact CNNs,
ECCV16(IV: 662-677).
Springer DOI 1611
BibRef

Yu, D.[Dan], Wu, X.J.[Xiao-Jun],
VLAD Is not Necessary for CNN,
TASKCV16(III: 492-499).
Springer DOI 1611
BibRef

Bach, S.[Sebastian], Binder, A.[Alexander], Müller, K.R.[Klaus-Robert], Samek, W.[Wojciech],
Controlling explanatory heatmap resolution and semantics via decomposition depth,
ICIP16(2271-2275)
IEEE DOI 1610
Computational modeling BibRef

Pang, J., Lin, H., Su, L., Zhang, C., Zhang, W., Duan, L., Huang, Q., Yin, B.,
Accelerate convolutional neural networks for binary classification via cascading cost-sensitive feature,
ICIP16(1037-1041)
IEEE DOI 1610
Acceleration BibRef

Carvalho, M., Cord, M., Avila, S., Thome, N., Valle, E.,
Deep neural networks under stress,
ICIP16(4443-4447)
IEEE DOI 1610
Computational modeling BibRef

Yang, Z.C.[Zi-Chao], Moczulski, M.[Marcin], Denil, M.[Misha], de Freitas, N.[Nando], Smola, A.J.[Alexander J.], Song, L.[Le], Wang, Z.Y.[Zi-Yu],
Deep Fried Convnets,
ICCV15(1476-1483)
IEEE DOI 1602
Adaptive systems BibRef

Ionescu, C., Vantzos, O., Sminchisescu, C.,
Matrix Backpropagation for Deep Networks with Structured Layers,
ICCV15(2965-2973)
IEEE DOI 1602
Backpropagation BibRef

Yang, B., Yan, J., Lei, Z., Li, S.Z.,
Convolutional Channel Features,
ICCV15(82-90)
IEEE DOI 1602
Boosting BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Training Issues for Convolutional Neural Networks .


Last update:Nov 30, 2021 at 22:19:38