14.5.9.8.15 Deep Network Training, Learning, Strategy, Design, Techniques

Chapter Contents (Back)
Deep Nets. Neural Networks. Training. Learning.

Ghesu, F.C.[Florin C.], Georgescu, B., Zheng, Y., Grbic, S., Maier, A., Hornegger, J.[Joachim], Comaniciu, D.,
Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans,
PAMI(41), No. 1, January 2019, pp. 176-189.
IEEE DOI 1812
Machine learning, Biomedical imaging, Search problems, Training, Real-time systems, Deep learning, intelligent localization BibRef

Wu, F.[Fei], Wang, Z.H.[Zhu-Hao], Lu, W.M.[Wei-Ming], Li, X.[Xi], Yang, Y.[Yi], Luo, J.B.[Jie-Bo], Zhuang, Y.T.[Yue-Ting],
Regularized Deep Belief Network for Image Attribute Detection,
CirSysVideo(27), No. 7, July 2017, pp. 1464-1477.
IEEE DOI 1707
Computational modeling, Context modeling, Correlation, Feature extraction, Neural networks, Semantics, Training, Contextual correlation, deep belief network (DBN), deep learning, image, attribute BibRef

Lee, H., Kwon, H.,
Going Deeper With Contextual CNN for Hyperspectral Image Classification,
IP(26), No. 10, October 2017, pp. 4843-4855.
IEEE DOI 1708
geophysical image processing, hyperspectral imaging, image classification, neural nets, CNN-based hyperspectral image classification, contextual deep CNN, joint spatio-spectral feature map, local contextual interactions, multiscale convolutional filter bank, Biological neural networks, Feature extraction, Hyperspectral imaging, Principal component analysis, Training, hyperspectral image classification, multi-scale filter bank, BibRef

Wang, K.[Keze], Zhang, D.Y.[Dong-Yu], Li, Y.[Ya], Zhang, R.M.[Rui-Mao], Lin, L.[Liang],
Cost-Effective Active Learning for Deep Image Classification,
CirSysVideo(27), No. 12, December 2017, pp. 2591-2600.
IEEE DOI 1712
Labeling, Learning systems, Measurement uncertainty, Neural networks, Training, Uncertainty, Visualization, incremental learning BibRef

Liu, Y.F.[Yan-Fei], Zhong, Y.F.[Yan-Fei], Fei, F.[Feng], Zhu, Q.Q.[Qi-Qi], Qin, Q.Q.[Qian-Qing],
Scene Classification Based on a Deep Random-Scale Stretched Convolutional Neural Network,
RS(10), No. 3, 2018, pp. xx-yy.
DOI Link 1804
BibRef

Liu, Y.F.[Yan-Fei], Zhong, Y.F.[Yan-Fei], Qin, Q.Q.[Qian-Qing],
Scene Classification Based on Multiscale Convolutional Neural Network,
GeoRS(56), No. 12, December 2018, pp. 7109-7121.
IEEE DOI 1812
Feature extraction, Remote sensing, Semantics, Convolutional neural networks, Training, Machine learning, similarity measure BibRef

Zhou, Y.C.[Yu-Can], Hu, Q.H.[Qing-Hua], Wang, Y.[Yu],
Deep super-class learning for long-tail distributed image classification,
PR(80), 2018, pp. 118-128.
Elsevier DOI 1805
Super-class construction, Block-structured sparsity, Deep learning, Long-tail distribution BibRef

Zheng, X.T.[Xiang-Tao], Yuan, Y.[Yuan], Lu, X.Q.[Xiao-Qiang],
A Deep Scene Representation for Aerial Scene Classification,
GeoRS(57), No. 7, July 2019, pp. 4799-4809.
IEEE DOI 1907
Feature extraction, Encoding, Strain, Task analysis, Remote sensing, Training, Semantics, Aerial scene classification, multiscale representation BibRef

Liao, Z.B.[Zhi-Bin], Drummond, T.[Tom], Reid, I.D.[Ian D.], Carneiro, G.[Gustavo],
Approximate Fisher Information Matrix to Characterize the Training of Deep Neural Networks,
PAMI(42), No. 1, January 2020, pp. 15-26.
IEEE DOI 1912
Training, Machine learning, Neural networks, Computational modeling, Convergence, Linear programming, Testing, neural network training characterisation BibRef

Liao, Z.B.[Zhi-Bin], Carneiro, G.[Gustavo],
On the importance of normalisation layers in deep learning with piecewise linear activation units,
WACV16(1-8)
IEEE DOI 1606
Data models BibRef

Zhuang, B., Lin, G., Shen, C., Reid, I.D.,
Fast Training of Triplet-Based Deep Binary Embedding Networks,
CVPR16(5955-5964)
IEEE DOI 1612
BibRef

Lyu, K., Li, Y., Zhang, Z.,
Attention-Aware Multi-Task Convolutional Neural Networks,
IP(29), No. 1, 2020, pp. 1867-1878.
IEEE DOI 1912
Task analysis, Deep learning, Feature extraction, Training, Estimation, Semantics, Convolutional neural networks, representation sharing BibRef

Zhang, D.W.[Ding-Wen], Han, J.W.[Jun-Wei], Zhang, Y.[Yu], Xu, D.[Dong],
Synthesizing Supervision for Learning Deep Saliency Network without Human Annotation,
PAMI(42), No. 7, July 2020, pp. 1755-1769.
IEEE DOI 2006
Object detection, Detectors, Training, Knowledge engineering, Task analysis, Semantics, Feature extraction, weakly supervised semantic segmentation BibRef

Santiago, C.[Carlos], Barata, C.[Catarina], Sasdelli, M.[Michele], Carneiro, G.[Gustavo], Nascimento, J.C.[Jacinto C.],
LOW: Training deep neural networks by learning optimal sample weights,
PR(110), 2021, pp. 107585.
Elsevier DOI 2011
Deep learning, Sample weighting, Imbalanced data sets BibRef

Dixit, M.[Mandar], Li, Y.S.[Yun-Sheng], Vasconcelos, N.M.[Nuno M.],
Semantic Fisher Scores for Task Transfer: Using Objects to Classify Scenes,
PAMI(42), No. 12, December 2020, pp. 3102-3118.
IEEE DOI 2011
BibRef
And: A2, A1, A3:
Deep Scene Image Classification with the MFAFVNet,
ICCV17(5757-5765)
IEEE DOI 1802
Semantics, Neural networks, Training data, Object recognition, Neural networks, Computational modeling, Probability, MFA. Computational modeling, Covariance matrices, Feature extraction, Training BibRef

Luo, P.[Ping], Zhang, R.M.[Rui-Mao], Ren, J.M.[Jia-Min], Peng, Z.L.[Zhang-Lin], Li, J.Y.[Jing-Yu],
Switchable Normalization for Learning-to-Normalize Deep Representation,
PAMI(43), No. 2, February 2021, pp. 712-728.
IEEE DOI 2101
Task analysis, Training, Graphics processing units, Switches, Object detection, Image segmentation, Head, Deep learning, semantic segmentation and face verification BibRef

Liu, D.[Defu], Ning, J.[Jin], Wu, J.Z.[Jin-Zhao], Yang, G.W.[Guo-Wu],
Extending Ordinary-Label Learning Losses to Complementary-Label Learning,
SPLetters(28), 2021, pp. 852-856.
IEEE DOI 2106
Training, Neural networks, Signal processing algorithms, Risk management, Mean square error methods, Machine learning, deep neural networks BibRef

Chen, Z.[Zhe], Wu, X.J.[Xiao-Jun], Xu, T.Y.[Tian-Yang], Kittler, J.V.[Josef V.],
Learning Alternating Deep-Layer Cascaded Representation,
SPLetters(28), 2021, pp. 1520-1524.
IEEE DOI 2108
Training, Encoding, Collaboration, Mathematical model, Feature extraction, Deep learning, image classification BibRef

Wang, R.[Rui], Wu, X.J.[Xiao-Jun], Chen, Z.H.[Zi-Heng], Xu, T.Y.[Tian-Yang], Kittler, J.V.[Josef V.],
DreamNet: A Deep Riemannian Manifold Network for SPD Matrix Learning,
ACCV22(VI:646-663).
Springer DOI 2307
symmetric positive definite. BibRef

Fan, B.[Bin], Liu, H.M.[Hong-Min], Zeng, H.[Hui], Zhang, J.Y.[Ji-Yong], Liu, X.[Xin], Han, J.W.[Jun-Wei],
Deep Unsupervised Binary Descriptor Learning Through Locality Consistency and Self Distinctiveness,
MultMed(23), 2021, pp. 2770-2781.
IEEE DOI 2109
Machine learning, Robustness, Quantization (signal), Binary codes, Task analysis, Feature extraction, Training, Unsupervised learning, image retrieval BibRef

Miao, Y.Q.[Yun-Qi], Lin, Z.J.[Zi-Jia], Ma, X.[Xiao], Ding, G.G.[Gui-Guang], Han, J.G.[Jun-Gong],
Learning Transformation-Invariant Local Descriptors With Low-Coupling Binary Codes,
IP(30), 2021, pp. 7554-7566.
IEEE DOI 2109
Correlation, Binary codes, Training, Visualization, Feature extraction, Entropy, Deep learning, deep learning BibRef

Zhao, T.Y.[Tian-Yu], Zhao, J.[Jian], Zhou, W.G.[Wen-Gang], Zhou, Y.[Yun], Li, H.Q.[Hou-Qiang],
State Representation Learning With Adjacent State Consistency Loss for Deep Reinforcement Learning,
MultMedMag(28), No. 3, July 2021, pp. 117-127.
IEEE DOI 2109
Training data, Task analysis, Reinforcement learning, Feature extraction, Games, Neural networks, Deep learning BibRef

Lu, Z.Q.[Zi-Qing], Xu, C.[Chang], Du, B.[Bo], Ishida, T.[Takashi], Zhang, L.[Lefei], Sugiyama, M.[Masashi],
LocalDrop: A Hybrid Regularization for Deep Neural Networks,
PAMI(44), No. 7, July 2022, pp. 3590-3601.
IEEE DOI 2206
Complexity theory, Biological neural networks, Bayes methods, Training, Deep learning, Upper bound, Random variables, regularization BibRef

Wang, Y.L.[Yu-Lin], Huang, G.[Gao], Song, S.[Shiji], Pan, X.[Xuran], Xia, Y.T.[Yi-Tong], Wu, C.[Cheng],
Regularizing Deep Networks With Semantic Data Augmentation,
PAMI(44), No. 7, July 2022, pp. 3733-3748.
IEEE DOI 2206
Semantics, Training, Task analysis, Upper bound, Training data, Data models, Supervised learning, Data augmentation, deep learning, semi-supervised learning BibRef

Pan, X.[Xuran], Ge, C.J.[Chun-Jiang], Lu, R.[Rui], Song, S.[Shiji], Chen, G.F.[Guan-Fu], Huang, Z.Y.[Ze-Yi], Huang, G.[Gao],
On the Integration of Self-Attention and Convolution,
CVPR22(805-815)
IEEE DOI 2210
Code, Representation Learning.
WWW Link. Representation learning, Image recognition, Convolution, Computational modeling, Object detection, Pattern recognition, Representation learning BibRef

Kim, J.[Jinwook], Yoon, H.[Heeyong], Kim, M.S.[Min-Soo],
Tweaking Deep Neural Networks,
PAMI(44), No. 9, September 2022, pp. 5715-5728.
IEEE DOI 2208
Synapses, Biological neural networks, Neurons, Artificial neural networks, Training, Training data, Arrays, synaptic join BibRef

Li, Y.[Yao], Wang, Y.H.[Yu-Hui], Gan, Y.Z.[Yao-Zhong], Tan, X.Y.[Xiao-Yang],
Alleviating the estimation bias of deep deterministic policy gradient via co-regularization,
PR(131), 2022, pp. 108872. x
Elsevier DOI 2208
Reinforcement learning, Overestimation, Underestimation, Co-training, Deterministic policy gradient BibRef

Li, Y.[Yao], Wang, Y.H.[Yu-Hui], Tan, X.Y.[Xiao-Yang],
Self-imitation guided goal-conditioned reinforcement learning,
PR(144), 2023, pp. 109845.
Elsevier DOI 2310
Goal-conditioned reinforcement learning, Self-imitation learning, Deterministic policy gradient, Behavior cloning BibRef

Wang, D.[Di], Tang, L.[Lulu], Wang, X.[Xu], Luo, L.Q.[Lu-Qing], Yang, Z.X.[Zhi-Xin],
Improving deep learning on point cloud by maximizing mutual information across layers,
PR(131), 2022, pp. 108892.
Elsevier DOI 2208
Deep learning, 3D vision, Point clouds, Mutual information BibRef

Lei, C.Y.[Chen-Yang], Xing, Y.Z.[Ya-Zhou], Ouyang, H.[Hao], Chen, Q.F.[Qi-Feng],
Deep Video Prior for Video Consistency and Propagation,
PAMI(45), No. 1, January 2023, pp. 356-371.
IEEE DOI 2212

WWW Link. Consistent learning across the video. Task analysis, Training, Electronics packaging, Image color analysis, Optical imaging, Image reconstruction, deep learning BibRef

Murdock, C.[Calvin], Cazenavette, G.[George], Lucey, S.[Simon],
Reframing Neural Networks: Deep Structure in Overcomplete Representations,
PAMI(45), No. 1, January 2023, pp. 964-979.
IEEE DOI 2212
Neural networks, Deep learning, Computer architecture, Representation learning, Optimization, Network architecture, sparsity BibRef

Wang, Z.W.[Zi-Wei], Xiao, H.[Han], Duan, Y.Q.[Yue-Qi], Zhou, J.[Jie], Lu, J.W.[Ji-Wen],
Learning Deep Binary Descriptors via Bitwise Interaction Mining,
PAMI(45), No. 2, February 2023, pp. 1919-1933.
IEEE DOI 2301
Reliability, Reinforcement learning, Costs, Binary codes, Training, Task analysis, Semantics, Binary descriptors, graph convolutional networks BibRef

Duan, Y.Q.[Yue-Qi], Wang, Z.W.[Zi-Wei], Lu, J.W.[Ji-Wen], Lin, X.D.[Xu-Dong], Zhou, J.[Jie],
GraphBit: Bitwise Interaction Mining via Deep Reinforcement Learning,
CVPR18(8270-8279)
IEEE DOI 1812
Reliability, Binary codes, Linear programming, Training, Mutual information BibRef

Chen, D.D.[Dong-Dong], Davies, M.[Mike], Ehrhardt, M.J.[Matthias J.], Schönlieb, C.B.[Carola-Bibiane], Sherry, F.[Ferdia], Tachella, J.[Julián],
Imaging With Equivariant Deep Learning: From unrolled network design to fully unsupervised learning,
SPMag(40), No. 1, January 2023, pp. 134-147.
IEEE DOI 2301
Deep learning, Neural networks, Imaging, Signal processing algorithms, Self-supervised learning, Iterative methods BibRef

Tang, A.[Anda], Niu, L.F.[Ling-Feng], Miao, J.Y.[Jian-Yu], Zhang, P.[Peng],
Training Compact DNNs with L1/2 Regularization,
PR(136), 2023, pp. 109206.
Elsevier DOI 2301
Deep neural networks, Model compression, Quasi-norm, Non-Lipschitz regularization, Sparse optimization BibRef

Shu, J.[Jun], Zhu, Y.[Yanwen], Zhao, Q.[Qian], Meng, D.Y.[De-Yu], Xu, Z.B.[Zong-Ben],
MLR-SNet: Transferable LR Schedules for Heterogeneous Tasks,
PAMI(45), No. 3, March 2023, pp. 3505-3521.
IEEE DOI 2302

WWW Link. LR: Learning Rate. Schedules, Task analysis, Training, Optimization, Convergence, Data models, Heuristic algorithms, Meta learning, stochastic gradient descent BibRef

Wang, Y.M.[Yi-Ming], Chang, D.X.[Dong-Xia], Fu, Z.Q.[Zhi-Qiang], Zhao, Y.[Yao],
Learning a bi-directional discriminative representation for deep clustering,
PR(137), 2023, pp. 109237.
Elsevier DOI 2302
Deep clustering, Representation learning, Manifold learning, Mutual information BibRef

Zhu, Q.Y.[Qiu-Yu], Zu, X.W.[Xue-Wen],
A Softmax-Free Loss Function Based on Predefined Optimal-Distribution of Latent Features for Deep Learning Classifier,
CirSysVideo(33), No. 3, March 2023, pp. 1386-1397.
IEEE DOI 2303
Training, Feature extraction, Deep learning, Neural networks, Image classification, Face recognition BibRef

Qin, W.[Wei], Zhang, H.W.[Han-Wang], Hong, R.C.[Ri-Chang], Lim, E.P.[Ee-Peng], Sun, Q.R.[Qian-Ru],
Causal Interventional Training for Image Recognition,
MultMed(25), 2023, pp. 1033-1044.
IEEE DOI 2303

WWW Link. Training without bias. Training, Automobiles, Task analysis, Visualization, Road transportation, Image recognition, Data models, Causality, image recognition BibRef

Chen, C.[Cheng], Li, B.[Bo],
An Interpretable Channelwise Attention Mechanism based on Asymmetric and Skewed Gaussian Distribution,
PR(139), 2023, pp. 109467.
Elsevier DOI 2304
Channelwise attention, Interpretable modeling, Skewness distribution, Asymmetric distribution BibRef

Wu, Z.Z.[Zi-Zhang], Wang, M.[Man], Sun, W.W.[Wei-Wei], Li, Y.C.[Yu-Chen], Xu, T.H.[Tian-Hao], Wang, F.[Fan], Huang, K.[Keke],
CAT: Learning to collaborate channel and spatial attention from multi-information fusion,
IET-CV(17), No. 3, 2023, pp. 309-318.
DOI Link 2305
Performance boost for deep learning. channel attention, dynamic learning, entropy pooling, spatial attention BibRef

Huang, Z.Z.[Zhi-Zhong], Chen, J.[Jie], Zhang, J.P.[Jun-Ping], Shan, H.M.[Hong-Ming],
Learning Representation for Clustering Via Prototype Scattering and Positive Sampling,
PAMI(45), No. 6, June 2023, pp. 7509-7524.
IEEE DOI
WWW Link. 2305
Prototypes, Scattering, Representation learning, Task analysis, Self-supervised learning, Clustering methods, Semantics, unsupervised learning BibRef

Feng, F.[Fan], Liu, Q.[Qi], Peng, Z.L.[Zhang-Lin], Zhang, R.M.[Rui-Mao], Chan, R.H.M.[Rosa H.M.],
Community Channel-Net: Efficient channel-wise interactions via community graph topology,
PR(141), 2023, pp. 109536.
Elsevier DOI 2306
Deep Neural Networks, Complex Networks, Representation Learning BibRef

Xu, Y.H.[Yu-Hui], Xie, L.X.[Ling-Xi], Xie, C.H.[Ci-Hang], Dai, W.R.[Wen-Rui], Mei, J.[Jieru], Qiao, S.Y.[Si-Yuan], Shen, W.[Wei], Xiong, H.K.[Hong-Kai], Yuille, A.L.[Alan L.],
BNET: Batch Normalization With Enhanced Linear Transformation,
PAMI(45), No. 7, July 2023, pp. 9225-9232.
IEEE DOI 2306
Task analysis, Convolution, Training, Visualization, Neurons, Kernel, Performance gain, Batch normalization, linear transformation, deep learning BibRef

Huang, Y.J.[Yu-Jie], Chen, W.S.[Wen-Shu], Peng, L.Y.[Li-Yuan], Liu, Y.H.[Yu-Hao], Wang, M.Y.[Ming-Yu], Zhang, X.P.[Xiao-Ping], Zeng, X.Y.[Xiao-Yang],
LineDL: Processing Images Line-by-Line With Deep Learning,
IP(32), 2023, pp. 3150-3162.
IEEE DOI 2306
Task analysis, Image processing, Noise reduction, Computational modeling, Image coding, Superresolution, superresolution BibRef

Lin, M.B.[Ming-Bao], Chen, B.H.[Bo-Hong], Chao, F.[Fei], Ji, R.R.[Rong-Rong],
Training Compact CNNs for Image Classification Using Dynamic-Coded Filter Fusion,
PAMI(45), No. 8, August 2023, pp. 10478-10487.
IEEE DOI 2307
Training, Convolutional neural networks, Computational modeling, Temperature distribution, Information filters, Convolution, compact CNNs BibRef

Khan, S.D.[Sultan Daud], Basalamah, S.[Saleh],
Multi-Branch Deep Learning Framework for Land Scene Classification in Satellite Imagery,
RS(15), No. 13, 2023, pp. 3408.
DOI Link 2307
BibRef

Zhu, Z.Z.[Ze-Zhou], Zhou, Y.C.[Yu-Cong], Dong, Y.[Yuan], Zhong, Z.[Zhao],
PWLU: Learning Specialized Activation Functions With the Piecewise Linear Unit,
PAMI(45), No. 10, October 2023, pp. 12269-12286.
IEEE DOI 2310
BibRef
Earlier: A2, A1, A4, Only:
Learning specialized activation functions with the Piecewise Linear Unit,
ICCV21(12075-12084)
IEEE DOI 2203
Learning systems, Deep learning, Neural networks, Task analysis, Recognition and classification BibRef

Chen, X.H.[Xiong-Hui], Luo, F.M.[Fan-Ming], Yu, Y.[Yang], Li, Q.Y.[Qing-Yang], Qin, Z.W.[Zhi-Wei], Shang, W.J.[Wen-Jie], Ye, J.P.[Jie-Ping],
Offline Model-Based Adaptable Policy Learning for Decision-Making in Out-of-Support Regions,
PAMI(45), No. 12, December 2023, pp. 15260-15274.
IEEE DOI 2311
BibRef

Wang, Q.L.[Qi-Long], Zhang, Z.L.[Zhao-Lin], Gao, M.Z.[Ming-Ze], Xie, J.T.[Jiang-Tao], Zhu, P.F.[Peng-Fei], Li, P.H.[Pei-Hua], Zuo, W.M.[Wang-Meng], Hu, Q.H.[Qing-Hua],
Towards a Deeper Understanding of Global Covariance Pooling in Deep Learning: An Optimization Perspective,
PAMI(45), No. 12, December 2023, pp. 15802-15819.
IEEE DOI 2311
BibRef

Wang, J.[Jing], Chen, J.H.[Jia-Hong], Zhang, K.[Kuangen], Sigal, L.[Leonid],
Training feedforward neural nets in Hopfield-energy-based configuration: A two-step approach,
PR(145), 2024, pp. 109954.
Elsevier DOI 2311
Hopfield-based energy, Feedforward neural nets, Learning algorithm, Supervised learning BibRef

Todros, K.[Koby],
Training a Radial Basis Function Network Under Transformed Probability Measure,
SPLetters(30), 2023, pp. 1567-1571.
IEEE DOI 2311
BibRef

Xing, W.W.[Wei-Wei], Yao, J.[Jie], Liu, Z.X.[Zi-Xia], Liu, W.B.[Wei-Bin], Zhang, S.[Shunli], Wang, L.Q.[Li-Qiang],
Contrastive JS: A Novel Scheme for Enhancing the Accuracy and Robustness of Deep Models,
MultMed(25), 2023, pp. 7881-7893.
IEEE DOI 2312
BibRef

Wang, Y.[Yida], Tan, D.J.[David Joseph], Navab, N.[Nassir], Tombari, F.[Federico],
Self-Supervised Latent Space Optimization With Nebula Variational Coding,
PAMI(46), No. 3, March 2024, pp. 1397-1411.
IEEE DOI 2402
Variational model to help deep learning. Training, Measurement, Image reconstruction, Decoding, Optimization, Feature extraction, Nebula anchor, variational inference, metric learning BibRef

Lee, H.[Hyeongmin], Kim, T.[Taeoh], Son, H.[Hanbin], Baek, S.W.[Sang-Wook], Cheon, M.[Minsu], Lee, S.Y.[Sang-Youn],
A Nonlinear, Regularized, and Data-Independent Modulation for Continuously Interactive Image Processing Network,
IJCV(132), No. 1, January 2024, pp. 74-94.
Springer DOI 2402
Usually CNN trained to, e.g. denoise a certain degree of noise, so multiple training for general noise levels. How to avoid this. BibRef

Zhao, C.Y.[Chao-Yu], Qian, J.J.[Jian-Jun], Zhu, S.M.[Shu-Min], Xie, J.[Jin], Yang, J.[Jian],
Learning Robust Facial Representation From the View of Diversity and Closeness,
IJCV(132), No. 2, February 2024, pp. 410-427.
Springer DOI 2402
Both closeess and diversity in training. BibRef

Zhou, H.Y.[He-Yu], Liu, A.A.[An-An], Zhang, C.Y.[Chen-Yu], Zhu, P.[Ping], Zhang, Q.Y.[Qian-Yi], Kankanhalli, M.[Mohan],
Multi-Modal Meta-Transfer Fusion Network for Few-Shot 3D Model Classification,
IJCV(132), No. 3, March 2024, pp. 673-688.
Springer DOI 2402
Scaling and Shifting to avoid overtraining. BibRef

Trosten, D.J.[Daniel J.], Løkse, S.[Sigurd], Jenssen, R.[Robert], Kampffmeyer, M.[Michael],
Leveraging tensor kernels to reduce objective function mismatch in deep clustering,
PR(149), 2024, pp. 110229.
Elsevier DOI Code:
WWW Link. 2403
Tensor kernels, Unsupervised companion objectives, Objective function mismatch, Deep clustering BibRef

Qin, Z.[Zhen], Tan, X.[Xuwei], Zhu, Z.H.[Zhi-Hui],
Convergence Analysis for Learning Orthonormal Deep Linear Neural Networks,
SPLetters(31), 2024, pp. 795-799.
IEEE DOI 2404
Training, Convergence, Neural networks, Manifolds, Covariance matrices, Robustness, Optimization, Riemannian optimization BibRef

Liu, X.Z.[Xin-Zhi], Yu, J.[Jun], Kurihara, T.[Toru], Wu, C.Z.[Cong-Zhong], Zhan, S.[Shu],
Spectrum Attention Mechanism for a Complex Neural Network,
SPLetters(31), 2024, pp. 815-819.
IEEE DOI 2404
Discrete cosine transforms, Neural networks, Discrete Fourier transforms, Training, Hyperspectral imaging, spectrum attention BibRef

Hamidi, S.M.[Shayan Mohajer],
Training Neural Networks on Remote Edge Devices for Unseen Class Classification,
SPLetters(31), 2024, pp. 1004-1008.
IEEE DOI 2404
Training, Vectors, Artificial neural networks, Dogs, Costs, Entropy, Computational modeling, Training on edge devices, Lipschitz regularization BibRef

Yin, Z.[Zimo], Pu, J.[Jian], Wan, R.[Ru], Xue, X.Y.[Xiang-Yang],
Embrace sustainable AI: Dynamic data subset selection for image classification,
PR(151), 2024, pp. 110392.
Elsevier DOI 2404
Data selection, Dynamic subset selection, Weighted sampling, Class distribution, Training efficiency BibRef

Li, J.T.[Jun-Tao], Liang, X.B.[Xiao-Bo], Wu, L.J.[Li-Jun], Wang, Y.[Yue], Meng, Q.[Qi], Qin, T.[Tao], Zhang, M.[Min], Liu, T.Y.[Tie-Yan],
Randomness Regularization With Simple Consistency Training for Neural Networks,
PAMI(46), No. 8, August 2024, pp. 5763-5778.
IEEE DOI 2407
Training, Data models, Transformers, Mathematical models, Task analysis, Predictive models, Computational modeling, neural networks BibRef

Zhong, Y.Y.[Yang-Yang], Yan, Y.F.[Yun-Feng], Luo, P.X.[Peng-Xin], Zhou, Y.H.[Yu-Hao], Qi, D.L.[Dong-Lian],
ADIR: Advanced domain-invariant representation via decoupling learning and information bottleneck,
IET-IPR(18), No. 9, 2024, pp. 2506-2520.
DOI Link 2407
Biases in learning DNN/CNN image processing BibRef

Barisin, T.[Tin], Angulo, J.[Jesus], Schladitz, K.[Katja], Redenbach, C.[Claudia],
Riesz Feature Representation: Scale Equivariant Scattering Network for Classification Tasks,
SIIMS(17), No. 2, 2024, pp. 1284-1313.
DOI Link 2407
BibRef

Wu, Z.T.[Zhou-Tong], Xiao, M.Q.[Ming-Qing], Fang, C.[Cong], Lin, Z.C.[Zhou-Chen],
Designing Universally-Approximating Deep Neural Networks: A First-Order Optimization Approach,
PAMI(46), No. 9, September 2024, pp. 6231-6246.
IEEE DOI 2408
Optimization, Approximation algorithms, Design methodology, Manuals, Reviews, Knowledge engineering, Image classification, width-bounded BibRef

Bojesomo, A.[Alabi], Liatsis, P.[Panos], Al Marzouqi, H.[Hasan],
Deep Hypercomplex Networks for Spatiotemporal Data Processing: Parameter efficiency and superior performance,
SPMag(41), No. 3, May 2024, pp. 101-112.
IEEE DOI 2408
[Hypercomplex Signal and Image Processing] Training data, Convolutional neural networks, Algebra, Quaternions, Image processing, Data processing, Spatiotemporal phenomena, Batch normalization BibRef

Lu, M.F.[Ming-Fei], Xing, L.[Lei], Chen, B.D.[Ba-Dong],
Measuring generalized divergence for multiple distributions with application to deep clustering,
PR(157), 2025, pp. 110864.
Elsevier DOI Code:
WWW Link. 2409
Generalized divergence measures, Sample-based estimation, Jensen-Rényi divergence, Deep clustering BibRef

Liu, K.J.[Kang-Jun], Chen, K.[Ke], Jia, K.[Kui], Wang, Y.W.[Yao-Wei],
Improving deep representation learning via auxiliary learnable target coding,
PR(157), 2025, pp. 110938.
Elsevier DOI 2409
Image classification, Representation learning, Target coding BibRef

Wen, J.J.[Jia-Jun], Kong, H.[Heng], Lai, Z.H.[Zhi-Hui], Zhu, Z.J.[Zhi-Jie],
Characteristic discriminative prototype network with detailed interpretation for classification,
PR(157), 2025, pp. 110901.
Elsevier DOI 2409
Classification, Prototype learning, Deep learning BibRef

Feng, G.R.[Guo-Rui], Li, S.[Sheng], Zhao, J.[Jian], Wang, Z.[Zheng],
Recent Advances in Deep Learning Model Security,
PRL(185), 2024, pp. 262-263.
Elsevier DOI 2410
BibRef

Karpukhin, I.[Ivan], Dereka, S.[Stanislav], Kolesnikov, S.[Sergey],
EXACT: How to train your accuracy,
PRL(185), 2024, pp. 23-30.
Elsevier DOI 2410
Classification, Image recognition, Deep learning, Training objective, Loss function, Accuracy enhancement, Label noise BibRef


Cormier, M.[Michael],
Kaskade-CNN and NB-KDE-CNN: CNN Architectures with KDE and Probabilistic Reasoning Layers,
CRV23(113-120)
IEEE DOI 2406
Training, Computational modeling, Estimation, Wheels, Computer architecture, Probabilistic logic, Cognition, probabilistic reasoning BibRef

Ilhan, F.[Fatih], Chow, K.H.[Ka-Ho], Hu, S.[Sihao], Huang, T.S.[Tian-Sheng], Tekin, S.[Selim], Wei, W.Q.[Wen-Qi], Wu, Y.Z.[Yan-Zhao], Lee, M.J.[Myung-Jin], Kompella, R.[Ramana], Latapie, H.[Hugo], Liu, G.W.[Gao-Wen], Liu, L.[Ling],
Adaptive Deep Neural Network Inference Optimization with EENet,
WACV24(1362-1371)
IEEE DOI 2404
Terminate early when confident. Adaptation models, Visualization, Adaptive systems, Computational modeling, Optimization methods, Image recognition and understanding BibRef

Bu, H.R.[Hao-Ran],
Deep Clustering Based on Contractive Autoencoder and Self-paced Learning,
CVIDL23(458-462)
IEEE DOI 2403
Training, Learning systems, Deep learning, Clustering algorithms, Big Data, Partitioning algorithms, Self-paced learning BibRef

He, H.[Haoze], Dube, P.[Parijat],
RCD-SGD: Resource-Constrained Distributed SGD in Heterogeneous Environment Via Submodular Partitioning,
REDLCV23(1385-1393)
IEEE DOI 2401
BibRef

Wang, S.[Shunxin], Brune, C.[Christoph], Veldhuis, R.[Raymond], Strisciuglio, N.[Nicola],
DFM-X: Augmentation by Leveraging Prior Knowledge of Shortcut Learning,
VIPriors23(129-138)
IEEE DOI Code:
WWW Link. 2401
Augmentation so nets don't get stuck on superficial data. BibRef

Wei, Y.[Yao], Sun, Y.C.[Yan-Chao], Zheng, R.J.[Rui-Jie], Vemprala, S.[Sai], Bonatti, R.[Rogerio], Chen, S.[Shuhang], Madaan, R.[Ratnesh], Ba, Z.J.[Zhong-Jie], Kapoor, A.[Ashish], Ma, S.[Shuang],
Is Imitation All You Need? Generalized Decision-Making with Dual-Phase Training,
ICCV23(16175-16185)
IEEE DOI Code:
WWW Link. 2401
BibRef

Wang, Y.L.[Yu-Lin], Yue, Y.[Yang], Lu, R.[Rui], Liu, T.J.[Tian-Jiao], Zhong, Z.[Zhao], Song, S.[Shiji], Huang, G.[Gao],
EfficientTrain: Exploring Generalized Curriculum Learning for Training Visual Backbones,
ICCV23(5829-5841)
IEEE DOI Code:
WWW Link. 2401
BibRef

Zhou, Y.F.[Yi-Fei], Li, Z.[Zilu], Shrivastava, A.[Abhinav], Zhao, H.S.[Heng-Shuang], Torralba, A.[Antonio], Tian, T.[Taipeng], Lim, S.N.[Ser-Nam],
BT2: Backward-compatible Training with Basis Transformation,
ICCV23(11195-11204)
IEEE DOI Code:
WWW Link. 2401
BibRef

Saratchandran, H.[Hemanth], Chng, S.F.[Shin-Fang], Ramasinghe, S.[Sameera], MacDonald, L.[Lachlan], Lucey, S.[Simon],
Curvature-Aware Training for Coordinate Networks,
ICCV23(13282-13292)
IEEE DOI 2401
BibRef

Ni, Z.L.[Zan-Lin], Wang, Y.L.[Yu-Lin], Yu, J.W.[Jiang-Wei], Jiang, H.[Haojun], Cao, Y.[Yue], Huang, G.[Gao],
Deep Incubation: Training Large Models by Divide-and-Conquering,
ICCV23(17289-17299)
IEEE DOI Code:
WWW Link. 2401
BibRef

Park, H.[Hyekang], Noh, J.[Jongyoun], Oh, Y.[Youngmin], Baek, D.[Donghyeon], Ham, B.[Bumsub],
ACLS: Adaptive and Conditional Label Smoothing for Network Calibration,
ICCV23(3913-3922)
IEEE DOI 2401
BibRef

Rao, S.[Sukrut], Böhle, M.[Moritz], Parchami-Araghi, A.[Amin], Schiele, B.[Bernt],
Studying How to Efficiently and Effectively Guide Models with Explanations,
ICCV23(1922-1933)
IEEE DOI Code:
WWW Link. 2401
Training deep networks right. BibRef

Liang, T.[Tong], Davis, J.[Jim],
Inducing Neural Collapse to a Fixed Hierarchy-Aware Frame for Reducing Mistake Severity,
ICCV23(1443-1452)
IEEE DOI Code:
WWW Link. 2401
BibRef

Noh, J.[Jongyoun], Park, H.[Hyekang], Lee, J.[Junghyup], Ham, B.[Bumsub],
RankMixup: Ranking-Based Mixup Training for Network Calibration,
ICCV23(1358-1368)
IEEE DOI 2401
BibRef

Voetman, R.[Roy], van Meekeren, A.[Alexander], Aghaei, M.[Maya], Dijkstra, K.[Klaas],
Using Diffusion Models for Dataset Generation: Prompt Engineering vs. Fine-tuning,
CAIP23(I:142-152).
Springer DOI 2312
Lack of training data is the issue. BibRef

Spatafora, M.A.N.[Maria Ausilia Napoli], Ortis, A.[Alessandro], Battiato, S.[Sebastiano],
GLR: Gradient-based Learning Rate Scheduler,
CIAP23(I:269-281).
Springer DOI 2312
BibRef

Liang, K.M.[Kong-Ming], Wang, X.R.[Xin-Ran], Wei, T.[Tao], Chen, W.[Wei], Ma, Z.Y.[Zhan-Yu], Guo, J.[Jun],
Attribute Learning with Knowledge Enhanced Partial Annotations,
ICIP23(1715-1719)
IEEE DOI Code:
WWW Link. 2312
BibRef

Quétu, V.[Victor], Tartaglione, E.[Enzo],
Dodging the Double Descent in Deep Neural Networks,
ICIP23(1625-1629)
IEEE DOI 2312
BibRef

Kleinman, M.[Michael], Achille, A.[Alessandro], Soatto, S.[Stefano],
Critical Learning Periods for Multisensory Integration in Deep Networks,
CVPR23(24296-24305)
IEEE DOI 2309
BibRef

Solodskikh, K.[Kirill], Kurbanov, A.[Azim], Aydarkhanov, R.[Ruslan], Zhelavskaya, I.[Irina], Parfenov, Y.[Yury], Song, D.H.[De-Hua], Lefkimmiatis, S.[Stamatios],
Integral Neural Networks,
CVPR23(16113-16122)
IEEE DOI 2309
BibRef

He, Q.[Qiang], Su, H.[Huangyuan], Zhang, J.[Jieyu], Hou, X.W.[Xin-Wen],
Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning,
CVPR23(20215-20225)
IEEE DOI 2309
BibRef

An, J.[Jaeju], Kim, T.[Taejune], Ko, D.[Donggeun], Lee, S.[Sangyup], Woo, S.S.[Simon S.],
A2: Adaptive Augmentation for Effectively Mitigating Dataset Bias,
ACCV22(VII:696-712).
Springer DOI 2307

WWW Link. Deep nets overfit the data. BibRef

Fang, Z.[Zilin], Shahbazi, M.[Mohamad], Probst, T.[Thomas], Paudel, D.P.[Danda Pani], Van Gool, L.J.[Luc J.],
Training Dynamics Aware Neural Network Optimization with Stabilization,
ACCV22(I:635-651).
Springer DOI 2307
BibRef

Gottlieb, N.[Noam], Werman, M.[Michael],
Decisionet: A Binary-tree Structured Neural Network,
ACCV22(I:556-570).
Springer DOI 2307
Combined with decision tree concepts. BibRef

Zhao, Y.[Yang], Zhang, H.[Hao],
Neighborhood Region Smoothing Regularization for Finding Flat Minima in Deep Neural Networks,
ACCV22(I:652-665).
Springer DOI 2307
BibRef

Serrano-e-Silva, P.[Pedro], Cruz, R.[Ricardo], Shihavuddin, A.S.M., Gonçalves, T.[Tiago],
Interpretability-guided Human Feedback During Neural Network Training,
IbPRIA23(276-287).
Springer DOI 2307
User guided training. BibRef

Penzel, N.[Niklas], Reimers, C.[Christian], Bodesheim, P.[Paul], Denzler, J.[Joachim],
Investigating Neural Network Training on a Feature Level Using Conditional Independence,
CiV22(383-399).
Springer DOI 2304
BibRef

Bishay, M.[Mina], Ghoneim, A.[Ahmed], Ashraf, M.[Mohamed], Mavadati, M.[Mohammad],
Which CNNs and Training Settings to Choose for Action Unit Detection? A Study Based on a Large-Scale Dataset,
FG21(1-5)
IEEE DOI 2303
Training, Face recognition, Gesture recognition, Computational efficiency, Convolutional neural networks BibRef

Downes, J.[Justin], Gleave, W.[Will], Nakada, D.[Dan],
RarePlanes Soar Higher: Self-Supervised Pretraining for Resource Constrained and Synthetic Datasets,
Pretrain23(1-9)
IEEE DOI 2302
Training, Conferences, Computational modeling, Data models, Task analysis, Remote sensing BibRef

Verma, V.K.[Vinay Kumar], Mehta, N.[Nikhil], Si, S.[Shijing], Henao, R.[Ricardo], Carin, L.[Lawrence],
Pushing the Efficiency Limit Using Structured Sparse Convolutions,
WACV23(6492-6502)
IEEE DOI 2302
Deep learning, Training, Convolutional codes, Tensors, Convolution, Computational modeling, Neural networks, algorithms (including transfer) BibRef

Nag, S.[Sayan], Bhattacharyya, M.[Mayukh], Mukherjee, A.[Anuraag], Kundu, R.[Rohit],
Serf: Towards better training of deep neural networks using log-Softplus ERror activation Function,
WACV23(5313-5322)
IEEE DOI 2302
Training, Deep learning, Neural networks, Object detection, Machine translation, Vision + language and/or other modalities BibRef

Dubey, S.R.[Shiv Ram], Singh, S.K.[Satish Kumar], Chaudhuri, B.B.[Bidyut Baran],
AdaNorm: Adaptive Gradient Norm Correction based Optimizer for CNNs,
WACV23(5273-5282)
IEEE DOI 2302
Training, Stochastic processes, Benchmark testing, Boosting, History, Convolutional neural networks, visual reasoning BibRef

Ni, T.W.[Tian-Wei], Ehsani, K.[Kiana], Weihs, L.[Luca], Salvador, J.[Jordi],
Towards Disturbance-Free Visual Mobile Manipulation,
WACV23(5208-5220)
IEEE DOI 2302
Training, Deep learning, Visualization, Costs, Navigation, Reinforcement learning, Robotics BibRef

Deng, W.J.[Wei-Jian], Suh, Y.[Yumin], Yu, X.[Xiang], Faraki, M.[Masoud], Zheng, L.[Liang], Chandraker, M.[Manmohan],
Split to Learn: Gradient Split for Multi-Task Human Image Analysis,
WACV23(4340-4349)
IEEE DOI 2302
Training, Image analysis, Convolution, Computational modeling, Estimation, Interference, Algorithms: Biometrics, face, gesture, visual reasoning BibRef

Watson, M.[Matthew], Hasan, B.A.S.[Bashar Awwad Shiekh], Moubayed, N.A.[Noura Al],
Learning How to MIMIC: Using Model Explanations to Guide Deep Learning Training,
WACV23(1461-1470)
IEEE DOI 2302
Training, Deep learning, Measurement, Heating systems, Analytical models, Visualization, MIMICs BibRef

Popovic, N.[Nikola], Chakraborty, R.[Ritika], Dadon, D.[David], Fried, O.[Ohad], Hel-Or, Y.[Yacov],
DDNeRF: Depth Distribution Neural Radiance Fields,
WACV23(755-763)
IEEE DOI 2302
Training, Solid modeling, Computational modeling, Neural networks, Predictive models, Algorithms: 3D computer vision, image and video synthesis BibRef

Fang, X.Y.[Xiao-Yu], Wang, L.L.[Lin-Lin], Liu, C.[Chang], Hong, T.[Tao],
An Improved Method of Image Recognition with Deep Learning Combined with Attention Mechanism,
ICIVC22(593-598)
IEEE DOI 2301
Training, Deep learning, Image recognition, Costs, Computational modeling, Data models, attention mechanism BibRef

Pan, J.[Jie], Hu, H.G.[Hai-Gen], Liu, A.[Aizhu], Zhou, Q.W.[Qian-Wei], Guan, Q.[Qiu],
A Channel-Spatial Hybrid Attention Mechanism using Channel Weight Transfer Strategy,
ICPR22(2524-2531)
IEEE DOI 2212

WWW Link. Deep learning, Codes, Computational modeling, Reproducibility of results, Complexity theory BibRef

Xing, E.[Eric], Liu, L.L.[Liang-Liang], Xing, X.[Xin], Qu, Y.[Yunni], Jacobs, N.[Nathan], Liang, G.[Gongbo],
Neural Network Decision-Making Criteria Consistency Analysis via Inputs Sensitivity,
ICPR22(2328-2334)
IEEE DOI 2212
Training, Sensitivity, Uncertainty, Decision making, Closed box, Artificial neural networks, Safety BibRef

Zhu, Z.Z.[Ze-Zhou], Dong, Y.[Yuan],
Non-uniform Piecewise Linear Activation Functions in Deep Neural Networks,
ICPR22(2107-2113)
IEEE DOI 2212
Performance evaluation, Deep learning, Image edge detection, Computational modeling, Neural networks, Distributed databases BibRef

Dröge, H.[Hannah], Möllenhoff, T.[Thomas], Möller, M.[Michael],
Non-Smooth Energy Dissipating Networks,
ICIP22(3281-3285)
IEEE DOI 2211
Deep learning, Costs, Noise reduction, Neural networks, Predictive models, Cost function, Iterative methods, moreau envelope BibRef

Barucic, D.[Denis], Kybic, J.[Jan],
Fast Learning from Label Proportions with Small Bags,
ICIP22(3156-3160)
IEEE DOI 2211
Learn instances based on how many samples. Training, Deep learning, Codes, Annotations, Neural networks, Approximation algorithms, learning from label proportions, deep learning BibRef

Berk, J.[Jane], Jaszewski, M.[Martin], Deledalle, C.A.[Charles-Alban], Parameswaran, S.[Shibin],
U-Deepdig: Scalable Deep Decision Boundary Instance Generation,
ICIP22(2961-2965)
IEEE DOI 2211
Deep learning, Training, Knowledge engineering, Uncertainty, Neural networks, Classification algorithms BibRef

Qi, S.[Siyu], Chamain, L.D.[Lahiru D.], Ding, Z.[Zhi],
Hierarchical Training for Distributed Deep Learning Based on Multimedia Data over Band-Limited Networks,
ICIP22(2871-2875)
IEEE DOI 2211
Training, Deep learning, Wireless communication, Wireless sensor networks, Image coding, Robustness, Decoding, information theory BibRef

Zhen, X.J.[Xing-Jian], Meng, Z.H.[Zi-Hang], Chakraborty, R.[Rudrasis], Singh, V.[Vikas],
On the Versatile Uses of Partial Distance Correlation in Deep Learning,
ECCV22(XXVI:327-346).
Springer DOI 2211
BibRef

Chrysos, G.G.[Grigorios G.], Georgopoulos, M.[Markos], Deng, J.K.[Jian-Kang], Kossaifi, J.[Jean], Panagakis, Y.[Yannis], Anandkumar, A.[Anima],
Augmenting Deep Classifiers with Polynomial Neural Networks,
ECCV22(XXV:692-716).
Springer DOI 2211
BibRef

Chen, X.[Xuxi], Chen, T.L.[Tian-Long], Cheng, Y.[Yu], Chen, W.Z.[Wei-Zhu], Awadallah, A.[Ahmed], Wang, Z.Y.[Zhang-Yang],
Scalable Learning to Optimize: A Learned Optimizer Can Train Big Models,
ECCV22(XXIII:389-405).
Springer DOI 2211
BibRef

Henig, A.[Amit], Giryes, R.[Raja],
Utilizing Excess Resources in Training Neural Networks,
ICIP22(1941-1945)
IEEE DOI 2211
Training, Filtering, Computational modeling, Neural networks, Supervised learning, Transfer learning, Semisupervised learning, kernel filtering / composition BibRef

Cheng, J.C.[Jia-Cheng], Vasconcelos, N.M.[Nuno M.],
Calibrating Deep Neural Networks by Pairwise Constraints,
CVPR22(13699-13708)
IEEE DOI 2210
Deep learning, Training, Neural networks, Calibration, Pattern recognition BibRef

Zietlow, D.[Dominik], Lohaus, M.[Michael], Balakrishnan, G.[Guha], Kleindessner, M.[Matthäus], Locatello, F.[Francesco], Schölkopf, B.[Bernhard], Russell, C.[Chris],
Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers,
CVPR22(10400-10411)
IEEE DOI 2210
Degradation, Ethics, Adaptation models, Computational modeling, Buildings, Network architecture, Transparency, fairness, Datasets and evaluation BibRef

Cheng, F.[Feng], Xu, M.Z.[Ming-Ze], Xiong, Y.J.[Yuan-Jun], Chen, H.[Hao], Li, X.Y.[Xin-Yu], Li, W.[Wei], Xia, W.[Wei],
Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models,
CVPR22(8291-8300)
IEEE DOI 2210
Training, Backpropagation, Computational modeling, Memory management, Redundancy, Stochastic processes, Video analysis and understanding BibRef

Chavan, A.[Arnav], Tiwari, R.[Rishabh], Bamba, U.[Udbhav], Gupta, D.K.[Deepak K.],
Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-learning,
CVPR22(9841-9850)
IEEE DOI 2210
Performance evaluation, Deep learning, Computational modeling, Memory management, Network architecture, Pattern recognition, Efficient learning and inferences BibRef

Ronen, M.[Meitar], Finder, S.E.[Shahaf E.], Freifeld, O.[Oren],
DeepDPM: Deep Clustering With an Unknown Number of Clusters,
CVPR22(9851-9860)
IEEE DOI 2210
Deep learning, Training, Codes, Statistical analysis, Scalability, Computational modeling, Statistical methods BibRef

Biswas, K.[Koushik], Kumar, S.[Sandeep], Banerjee, S.[Shilpak], Pandey, A.K.[Ashish Kumar],
Smooth Maximum Unit: Smooth Activation Function for Deep Networks using Smoothing Maximum Technique,
CVPR22(784-793)
IEEE DOI 2210
Deep learning, Training, Image segmentation, Smoothing methods, Semantics, Neural networks, Object detection, Optimization methods BibRef

Huang, L.[Lei], Zhou, Y.[Yi], Wang, T.[Tian], Luo, J.[Jie], Liu, X.L.[Xiang-Long],
Delving into the Estimation Shift of Batch Normalization in a Network,
CVPR22(753-762)
IEEE DOI 2210
Deep learning, Training, Representation learning, Sociology, Estimation, Representation learning BibRef

Liu, B.Y.[Bing-Yuan], Ben Ayed, I.[Ismail], Galdran, A.[Adrian], Dolz, J.[Jose],
The Devil is in the Margin: Margin-based Label Smoothing for Network Calibration,
CVPR22(80-88)
IEEE DOI 2210

WWW Link. Deal with over confident predictions. Training, Image segmentation, Smoothing methods, Semantics, Neural networks, Minimization, Calibration, Machine learning BibRef

Loukili, S.E.[Salah Eddine], Ezzati, A.[Abdellah], Alla, S.B.[Said Ben], Zraibi, B.[Brahim],
Reducing the training time of deep learning models using synchronous SGD and large batch size,
ISCV22(1-3)
IEEE DOI 2208
Training, Deep learning, Computational modeling, Neural networks, Stochastic processes, Parallel processing, Throughput, convolutional neural network BibRef

Yuan, K.[Kun], Chen, Y.M.[Yi-Ming], Huang, X.M.[Xin-Meng], Zhang, Y.Y.[Ying-Ya], Pan, P.[Pan], Xu, Y.H.[Ying-Hui], Yin, W.T.[Wo-Tao],
DecentLaM: Decentralized Momentum SGD for Large-batch Deep Training,
ICCV21(3009-3019)
IEEE DOI 2203
Training, Degradation, Deep learning, Runtime, Computational modeling, Task analysis, Machine learning architectures and formulations BibRef

Ramé, A.[Alexandre], Sun, R.[Rémy], Cord, M.[Matthieu],
MixMo: Mixing Multiple Inputs for Multiple Outputs via Deep Subnetworks,
ICCV21(803-813)
IEEE DOI 2203
Training, Fitting, Data models, Image classification, Recognition and classification, Optimization and learning methods BibRef

Tiwari, L.[Lokender], Madan, A.[Anish], Anand, S.[Saket], Banerjee, S.[Subhashis],
REGroup: Rank-aggregating Ensemble of Generative Classifiers for Robust Predictions,
WACV22(3829-3838)
IEEE DOI 2202
Training, Deep learning, Perturbation methods, Neurons, Neural networks, Training data, Predictive models, Vision Systems and Applications Deep Learning BibRef

Boyd, A.[Aidan], Tinsley, P.[Patrick], Bowyer, K.W.[Kevin W.], Czajka, A.[Adam],
CYBORG: Blending Human Saliency Into the Loss Improves Deep Learning-Based Synthetic Face Detection,
WACV23(6097-6106)
IEEE DOI 2302
Training, Visualization, Training data, Brain modeling, Data models, Face detection, Task analysis, Algorithms: Biometrics, face, gesture, Psychology and cognitive science BibRef

Boyd, A.[Aidan], Bowyer, K.W.[Kevin W.], Czajka, A.[Adam],
Human-Aided Saliency Maps Improve Generalization of Deep Learning,
WACV22(1255-1264)
IEEE DOI 2202
Deep learning, Training, Image coding, Biometrics (access control), Human intelligence, Security/Surveillance BibRef

Fields, G.[Greg], Samragh, M.[Mohammad], Javaheripi, M.[Mojan], Koushanfar, F.[Farinaz], Javidi, T.[Tara],
Trojan Signatures in DNN Weights,
AROW21(12-20)
IEEE DOI 2112
Training, Deep learning, Computational modeling, Trojan horses BibRef

Lebrat, L.[Léo], Cruz, R.S.[Rodrigo Santa], Fookes, C.[Clinton], Salvado, O.[Olivier],
MongeNet: Efficient Sampler for Geometric Deep Learning,
CVPR21(16659-16668)
IEEE DOI 2111
Training, Deep learning, Solid modeling, Computational modeling, Estimation, Approximation error BibRef

Durasov, N.[Nikita], Bagautdinov, T.[Timur], Baque, P.[Pierre], Fua, P.[Pascal],
Masksembles for Uncertainty Estimation,
CVPR21(13534-13543)
IEEE DOI 2111
Deep learning, Training, Uncertainty, Costs, Computational modeling, Estimation, Reinforcement learning BibRef

Lin, Y.[Yi], Wang, N.[Namin], Ma, X.Q.[Xiao-Qing], Li, Z.W.[Zi-Wei], Bai, G.[Gang],
How Does DCNN Make Decisions ?,
ICPR21(3342-3349)
IEEE DOI 2105
Training, Convolution, Semantics, Decision making, Visual systems, Feature extraction, Deep Convolutional Neural Network BibRef

Mastan, I.D.[Indra Deep], Raman, S.[Shanmuganathan],
DeepCFL: Deep Contextual Features Learning from a Single Image,
WACV21(2896-2905)
IEEE DOI 2106
Training, Image synthesis, Semantics, Training data, Image restoration BibRef

Kobayashi, T.[Takumi],
Phase-wise Parameter Aggregation For Improving SGD Optimization,
WACV21(2624-2633)
IEEE DOI 2106
Stochastic gradient descent. Applied to deep net training. Training, Optimization methods, Convolutional neural networks, Task analysis, Surface treatment BibRef

Ding, P.L.K.[Pak Lun Kevin], Martin, S.[Sarah], Li, B.X.[Bao-Xin],
Improving Batch Normalization with Skewness Reduction for Deep Neural Networks,
ICPR21(7165-7172)
IEEE DOI 2105
Training, Neural networks, Transforms, Optimization BibRef

Liao, W.H.[Wen-Hung], Huang, Y.T.[Yen-Ting],
Investigation of DNN Model Robustness Using Heterogeneous Datasets,
ICPR21(4393-4397)
IEEE DOI 2105
Training, Deep learning, Image coding, Neural networks, Training data, Feature extraction, Data models BibRef

Nakada, M.[Masaki], Chen, H.[Honglin], Lakshmipathy, A.[Arjun], Terzopoulos, D.[Demetri],
Locally-Connected, Irregular Deep Neural Networks for Biomimetic Active Vision in a Simulated Human,
ICPR21(4465-4472)
IEEE DOI 2105
Visualization, Solid modeling, Biological system modeling, Training data, Prototypes, Retina BibRef

Berg, A.[Axel], Oskarsson, M.[Magnus], O'Connor, M.[Mark],
Deep Ordinal Regression with Label Diversity,
ICPR21(2740-2747)
IEEE DOI 2105
Training, Learning systems, Neural networks, Pose estimation, Diversity methods, Predictive models, Search problems BibRef

Hansen, P.[Patrick], Vilkin, A.[Alexey], Krustalev, Y.[Yury], Imber, J.[James], Talagala, D.[Dumidu], Hanwell, D.[David], Mattina, M.[Matthew], Whatmough, P.N.[Paul N.],
ISP4ML: The Role of Image Signal Processing in Efficient Deep Learning Vision Systems,
ICPR21(2438-2445)
IEEE DOI 2105
Training, Machine vision, Pipelines, Memory management, Signal processing, Market research, Software BibRef

Brigato, L.[Lorenzo], Barz, B.[Björn], Iocchi, L.[Luca], Denzler, J.[Joachim],
Tune It or Don't Use It: Benchmarking Data-Efficient Image Classification,
VIPriors21(1071-1080)
IEEE DOI 2112
Deep learning, Training, Satellites, Head, Pipelines, Benchmark testing, Standards BibRef

Brigato, L.[Lorenzo], Iocchi, L.[Luca],
A Close Look at Deep Learning with Small Data,
ICPR21(2490-2497)
IEEE DOI 2105
Training, Deep learning, Computational modeling, Pipelines, Benchmark testing, Complexity theory BibRef

Du, S.Y.[Shuai-Yuan], Hong, C.Y.[Chao-Yi], Pan, Z.Y.[Zhi-Yu], Feng, C.[Chen], Cao, Z.G.[Zhi-Guo],
Parallel Network to Learn Novelty from the Known,
ICPR21(2172-2179)
IEEE DOI 2105
Training, Aggregates, Training data, Benchmark testing, Data models, Anomaly detection BibRef

Meng, L.H.[Ling-Heng], Gorbet, R.[Rob], Kulic, D.[Dana],
The Effect of Multi-step Methods on Overestimation in Deep Reinforcement Learning,
ICPR21(347-353)
IEEE DOI 2105
Computational modeling, Neural networks, Buildings, Reinforcement learning, Approximation error BibRef

Georgiou, T.[Theodoros], Schmitt, S.[Sebastian], Bäck, T.[Thomas], Chen, W.[Wei], Lew, M.[Michael],
Norm Loss: An efficient yet effective regularization method for deep neural networks,
ICPR21(8812-8818)
IEEE DOI 2105
Training, Manifolds, Neural networks, Benchmark testing, Pattern recognition, Computational efficiency BibRef

Deng, X.[Xiang], Zhang, Z.F.M.[Zhong-Fei Mark],
Is the Meta-Learning Idea Able to Improve the Generalization of Deep Neural Networks on the Standard Supervised Learning?,
ICPR21(150-157)
IEEE DOI 2105
Training, Supervised learning, Neural networks, Benchmark testing, Linear programming, Pattern recognition, Computational efficiency BibRef

Beeching, E.[Edward], Debangoye, J.[Jilles], Simonin, O.[Oliver], Wolf, C.[Christian],
Deep Reinforcement Learning on a Budget: 3D Control and Reasoning Without a Supercomputer,
ICPR21(158-165)
IEEE DOI 2105
Training, Solid modeling, Reinforcement learning, Benchmark testing, Cognition, Supercomputers BibRef

Li, X.L.[Xi-Lai], Sun, W.[Wei], Wu, T.F.[Tian-Fu],
Attentive Normalization,
ECCV20(XVII:70-87).
Springer DOI 2011
BibRef

Ma, X., Qiao, Z., Guo, J., Tang, S., Chen, Q., Yang, Q., Fu, S.,
Cascaded Context Dependency: An Extremely Lightweight Module For Deep Convolutional Neural Networks,
ICIP20(1741-1745)
IEEE DOI 2011
Feature extraction, Task analysis, Object detection, Charge coupled devices, Training, multi-scale BibRef

Oyedotun, O.K.[Oyebade K.], Shabayek, A.E.[Abd El_Rahman], Aouada, D.[Djamila], Ottersten, B.[Björn],
Revisiting the Training of Very Deep Neural Networks without Skip Connections,
ICPR21(2724-2731)
IEEE DOI 2105
BibRef
Earlier:
Going Deeper With Neural Networks Without Skip Connections,
ICIP20(1756-1760)
IEEE DOI 2011
Training, Neural networks, Explosions, Pattern recognition, Task analysis, Error analysis, Optimization, Computational modeling, Deep neural network, PlainNet, classification BibRef

Rao, K.[Kanishka], Harris, C.[Chris], Irpan, A.[Alex], Levine, S.[Sergey], Ibarz, J.[Julian], Khansari, M.[Mohi],
RL-CycleGAN: Reinforcement Learning Aware Simulation-to-Real,
CVPR20(11154-11163)
IEEE DOI 2008
Task analysis, Robots, Adaptation models, Grasping, Training, Learning (artificial intelligence) BibRef

Shi, Y.[Yi], Xu, M.C.[Meng-Chen], Yuan, S.H.[Shuai-Hang], Fang, Y.[Yi],
Unsupervised Deep Shape Descriptor With Point Distribution Learning,
CVPR20(9350-9359)
IEEE DOI 2008
To learn shapes. Shape, Robustness, Decoding, Solid modeling, Training, Neural networks BibRef

Xu, Y.H.[Yuan-Hong], Qian, Q.[Qi], Li, H.[Hao], Jin, R.[Rong], Hu, J.[Juhua],
Weakly Supervised Representation Learning with Coarse Labels,
ICCV21(10573-10581)
IEEE DOI 2203
Deep learning, Training, Representation learning, Visualization, Benchmark testing, Data collection, Representation learning, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Huang, L.[Lei], Liu, L.[Li], Zhu, F.[Fan], Wan, D.W.[Di-Wen], Yuan, Z.H.[Ze-Huan], Li, B.[Bo], Shao, L.[Ling],
Controllable Orthogonalization in Training DNNs,
CVPR20(6428-6437)
IEEE DOI 2008
Training, Matrix decomposition, Convergence, Neural networks, Eigenvalues and eigenfunctions, Covariance matrices, Jacobian matrices BibRef

Zhuang, C., She, T., Andonian, A., Sobol Mark, M., Yamins, D.,
Unsupervised Learning From Video With Deep Neural Embeddings,
CVPR20(9560-9569)
IEEE DOI 2008
Task analysis, Visualization, Unsupervised learning, Neural networks, Image recognition BibRef

Xie, X., Kim, K.,
Partial Weight Adaptation for Robust DNN Inference,
CVPR20(9570-9578)
IEEE DOI 2008
Distortion, Training, Streaming media, Robustness, Frequency response, Sensitivity, Training data BibRef

Li, P., Zhao, H., Liu, H.,
Deep Fair Clustering for Visual Learning,
CVPR20(9067-9076)
IEEE DOI 2008
Clustering algorithms, Visualization, Partitioning algorithms, Clustering methods, Machine learning, Training, Measurement BibRef

Mittal, G., Liu, C., Karianakis, N., Fragoso, V., Chen, M., Fu, Y.,
HyperSTAR: Task-Aware Hyperparameters for Deep Networks,
CVPR20(8733-8742)
IEEE DOI 2008
Task analysis, Acceleration, Training, Visualization, Optimization, Bayes methods, Gaussian processes BibRef

Huang, J., Gong, S., Zhu, X.,
Deep Semantic Clustering by Partition Confidence Maximisation,
CVPR20(8846-8855)
IEEE DOI 2008
Indexes, Training, Uncertainty, Semantics, Visualization, Clustering methods, Machine learning BibRef

Joneidi, M., Vahidian, S., Esmaeili, A., Wang, W., Rahnavard, N., Lin, B., Shah, M.,
Select to Better Learn: Fast and Accurate Deep Learning Using Data Selection From Nonlinear Manifolds,
CVPR20(7816-7826)
IEEE DOI 2008
Manifolds, Training, Machine learning, Face, Time complexity BibRef

Chrysos, G.G.[Grigorios G.], Moschoglou, S.[Stylianos], Bouritsas, G.[Giorgos], Panagakis, Y.[Yannis], Deng, J.K.[Jian-Kang], Zafeiriou, S.P.[Stefanos P.],
P-nets: Deep Polynomial Neural Networks,
CVPR20(7323-7333)
IEEE DOI 2008
Neural networks, Tensile stress, Task analysis, Training, Image generation BibRef

Meng, F., Cheng, H., Li, K., Xu, Z., Ji, R., Sun, X., Lu, G.,
Filter Grafting for Deep Neural Networks,
CVPR20(6598-6606)
IEEE DOI 2008
Training, Information filters, Filtering algorithms, Filtering theory, Entropy, Nickel BibRef

Zhan, X., Xie, J., Liu, Z., Ong, Y., Loy, C.C.,
Online Deep Clustering for Unsupervised Representation Learning,
CVPR20(6687-6696)
IEEE DOI 2008
Training, Feature extraction, Task analysis, Frequency modulation, Learning systems, Visualization, Clustering algorithms BibRef

Liu, J., Sun, Y., Han, C., Dou, Z., Li, W.,
Deep Representation Learning on Long-Tailed Data: A Learnable Embedding Augmentation Perspective,
CVPR20(2967-2976)
IEEE DOI 2008
Training, Task analysis, Head, Distortion, Face recognition, Visualization, Additives BibRef

Chen, H., Wang, Y., Xu, C., Shi, B., Xu, C., Tian, Q., Xu, C.,
AdderNet: Do We Really Need Multiplications in Deep Learning?,
CVPR20(1465-1474)
IEEE DOI 2008
Convolutional codes, Adders, Measurement, Computational complexity, Biological neural networks, Training BibRef

Xu, A., Huo, Z., Huang, H.,
On the Acceleration of Deep Learning Model Parallelism With Staleness,
CVPR20(2085-2094)
IEEE DOI 2008
Training, Parallel processing, Computational modeling, Neural networks, Stochastic processes, Acceleration, Convergence BibRef

Singh, P., Varshney, M., Namboodiri, V.P.,
Cooperative Initialization based Deep Neural Network Training,
WACV20(1130-1139)
IEEE DOI 2006
Training, Neurons, Standards, Task analysis, Color, Neural networks, Computer science BibRef

Lo, E., Kohl, J.,
Internet of Things (IoT) Discovery Using Deep Neural Networks,
WACV20(795-803)
IEEE DOI 2006
Object detection, Training, Internet of Things, Modulation, Spectrogram, Microprocessors BibRef

Li, H., Zhang, H., Qi, X., Ruigang, Y., Huang, G.,
Improved Techniques for Training Adaptive Deep Networks,
ICCV19(1891-1900)
IEEE DOI 2004
gradient methods, graph theory, groupware, image classification, inference mechanisms, learning (artificial intelligence), Knowledge transfer BibRef

Haeusser, P.[Philip], Plapp, J.[Johannes], Golkov, V.[Vladimir], Aljalbout, E.[Elie], Cremers, D.[Daniel],
Associative Deep Clustering: Training a Classification Network with No Labels,
GCPR18(18-32).
Springer DOI 1905
BibRef

Keller, M.[Michel], Chen, Z.[Zetao], Maffra, F.[Fabiola], Schmuck, P.[Patrik], Chli, M.[Margarita],
Learning Deep Descriptors with Scale-Aware Triplet Networks,
CVPR18(2762-2770)
IEEE DOI 1812
Training, Neural networks, Task analysis, Feature extraction BibRef

Goh, C.K., Liu, Y., Kong, A.W.K.,
A Constrained Deep Neural Network for Ordinal Regression,
CVPR18(831-839)
IEEE DOI 1812
Optimization, Feature extraction, Neural networks, Support vector machines, Training, Measurement BibRef

Alqahtani, A., Xie, X., Deng, J., Jones, M.W.,
Learning Discriminatory Deep Clustering Models,
CAIP19(I:224-233).
Springer DOI 1909
BibRef
And:
A Deep Convolutional Auto-Encoder with Embedded Clustering,
ICIP18(4058-4062)
IEEE DOI 1809
Image reconstruction, Training, Feature extraction, Linear programming, Task analysis, Convolution, Cost function, Embedded Clustering BibRef

Chun, Y., Fessler, J.A.,
Deep BCD-Net Using Identical Encoding-Decoding CNN Structures for Iterative Image Recovery,
IVMSP18(1-5)
IEEE DOI 1809
Training, Convolution, Iterative decoding, Thresholding (Imaging), Imaging, Decoding, Encoding BibRef

Huang, L., Liu, X., Liu, Y., Lang, B., Tao, D.,
Centered Weight Normalization in Accelerating Training of Deep Neural Networks,
ICCV17(2822-2830)
IEEE DOI 1802
learning (artificial intelligence), multilayer perceptrons, neural nets, centered weight normalization, Training BibRef

Qiu, Z., Yao, T., Mei, T.,
Deep Quantization: Encoding Convolutional Activations with Deep Generative Model,
CVPR17(4085-4094)
IEEE DOI 1711
Computational modeling, Encoding, Optimization, Quantization (signal), Training, Visualization BibRef

Diba, A.[Ali], Sharma, V.[Vivek], Pazandeh, A., Pirsiavash, H., Van Gool, L.J.[Luc J.],
Weakly Supervised Cascaded Convolutional Networks,
CVPR17(5131-5139)
IEEE DOI 1711
Feature extraction, Object detection, Proposals, Reliability, Training BibRef

Cruz, R.S., Fernando, B.[Basura], Cherian, A., Gould, S.[Stephen],
DeepPermNet: Visual Permutation Learning,
CVPR17(6044-6052)
IEEE DOI 1711
Computational modeling, Image sequences, Machine learning, Training, Visualization BibRef

Zheng, S., Song, Y., Leung, T., Goodfellow, I.J.[Ian J.],
Improving the Robustness of Deep Neural Networks via Stability Training,
CVPR16(4480-4488)
IEEE DOI 1612
BibRef

Iandola, F.N., Moskewicz, M.W., Ashraf, K., Keutzer, K.,
FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters,
CVPR16(2592-2600)
IEEE DOI 1612
BibRef

Blot, M., Robert, T., Thome, N., Cord, M.,
Shade: Information-Based Regularization for Deep Learning,
ICIP18(813-817)
IEEE DOI 1809
Entropy, Training, Task analysis, Machine learning, Neurons, Standards, Optimization, Deep learning, regularization, invariance, image understanding BibRef

Liu, M.Y.[Ming-Yu], Mallya, A.[Arun], Tuzel, O.[Oncel], Chen, X.[Xi],
Unsupervised network pretraining via encoding human design,
WACV16(1-9)
IEEE DOI 1606
Computer architecture. Deep NN training. BibRef

Wang, M.[Min], Liu, B.Y.[Bao-Yuan], Foroosh, H.[Hassan],
Look-Up Table Unit Activation Function for Deep Convolutional Neural Networks,
WACV18(1225-1233)
IEEE DOI 1806
BibRef
Earlier:
Factorized Convolutional Neural Networks,
Matrix-Tensor17(545-553)
IEEE DOI 1802
Gaussian processes, convolution, data structures, feedforward neural nets, image recognition, interpolation, Training. Complexity theory, Convolution, Kernel, Standards, BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Deep Learning with Noisy Labels, Robust Deep Learning .


Last update:Oct 22, 2024 at 22:09:59