14.5.10.7.15 Deep Learning with Noisy Labels, Robust Deep Learning

Chapter Contents (Back)
Deep Nets. Neural Networks. Robust.

Achille, A.[Alessandro], Soatto, S.[Stefano],
Information Dropout: Learning Optimal Representations Through Noisy Computation,
PAMI(40), No. 12, December 2018, pp. 2897-2905.
IEEE DOI 1811
Neural networks, Deep learning, Bayes methods, Machine learning, Information theory, Noise measurement, Learning systems, minimality BibRef

Ding, G.G.[Gui-Guang], Guo, Y.C.[Yu-Chen], Chen, K.[Kai], Chu, C.Q.[Chao-Qun], Han, J.G.[Jun-Gong], Dai, Q.G.[Qion-Ghai],
DECODE: Deep Confidence Network for Robust Image Classification,
IP(28), No. 8, August 2019, pp. 3752-3765.
IEEE DOI 1907
convolutional neural nets, data visualisation, image classification, image denoising, confidence model BibRef

Amjad, R.A.[Rana Ali], Geiger, B.C.[Bernhard C.],
Learning Representations for Neural Network-Based Classification Using the Information Bottleneck Principle,
PAMI(42), No. 9, September 2020, pp. 2225-2239.
IEEE DOI 2008
Training, Task analysis, Robustness, Cost function, Neurons, Neural networks, Deep learning, information bottleneck, stochastic neural networks BibRef

Pretorius, A.[Arnu], Kamper, H.[Herman], Kroon, S.[Steve],
On the expected behaviour of noise regularised deep neural networks as Gaussian processes,
PRL(138), 2020, pp. 75-81.
Elsevier DOI 2010
Neural networks, Gaussian processes, Signal propagation, Noise regularisation BibRef

Liu, R.[Rui], Liu, Y.[Yi], Wang, R.[Rui], Zhou, Y.C.[Yu-Cong],
Mutual calibration training: Training deep neural networks with noisy labels using dual-models,
CVIU(212), 2021, pp. 103277.
Elsevier DOI 2110
Image classification, Deep neural networks, Weak supervisor BibRef

Yan, Z.[Ziang], Guo, Y.[Yiwen], Zhang, C.S.[Chang-Shui],
Adversarial Margin Maximization Networks,
PAMI(43), No. 4, April 2021, pp. 1129-1139.
IEEE DOI 2103
Perturbation methods, Training, Support vector machines, Distortion, Radio frequency, Robustness, Neural networks, deep neural networks BibRef

Li, S.[Shuai], Jia, K.[Kui], Wen, Y.X.[Yu-Xin], Liu, T.L.[Tong-Liang], Tao, D.C.[Da-Cheng],
Orthogonal Deep Neural Networks,
PAMI(43), No. 4, April 2021, pp. 1352-1368.
IEEE DOI 2103
Training, Robustness, Jacobian matrices, Task analysis, Neural networks, Optimization, Deep learning, Deep neural networks, image classification BibRef

Kortylewski, A.[Adam], Liu, Q.[Qing], Wang, A.T.[Ang-Tian], Sun, Y.H.[Yi-Hong], Yuille, A.L.[Alan L.],
Compositional Convolutional Neural Networks: A Robust and Interpretable Model for Object Recognition Under Occlusion,
IJCV(129), No. 3, March 2021, pp. 736-760.
Springer DOI 2103
BibRef

Kortylewski, A., He, J., Liu, Q., Yuille, A.L.,
Compositional Convolutional Neural Networks: A Deep Architecture With Innate Robustness to Partial Occlusion,
CVPR20(8937-8946)
IEEE DOI 2008
Robustness, Training, Computational modeling, Solid modeling, Artificial neural networks BibRef

Wang, Q.L.[Qi-Long], Xie, J.T.[Jiang-Tao], Zuo, W.M.[Wang-Meng], Zhang, L.[Lei], Li, P.H.[Pei-Hua],
Deep CNNs Meet Global Covariance Pooling: Better Representation and Generalization,
PAMI(43), No. 8, August 2021, pp. 2582-2597.
IEEE DOI 2107
Covariance matrices, Robustness, Estimation, Geometry, Measurement, Visualization, Complexity theory, Global covariance pooling, visual recognition BibRef


Chen, D.D.[Dong-Dong], Tachella, J.[Julián], Davies, M.E.[Mike E.],
Robust Equivariant Imaging: A fully unsupervised framework for learning to image from noisy and partial measurements,
CVPR22(5637-5646)
IEEE DOI 2210

WWW Link. With noise. Training, Photography, Inverse problems, Computational modeling, Imaging, Self-supervised learning, Performance gain, Self- semi- meta- unsupervised learning BibRef

Iscen, A.[Ahmet], Valmadre, J.[Jack], Arnab, A.[Anurag], Schmid, C.[Cordelia],
Learning with Neighbor Consistency for Noisy Labels,
CVPR22(4662-4671)
IEEE DOI 2210
Training, Deep learning, Stochastic processes, Semisupervised learning, Deep learning architectures and techniques BibRef

Xu, Y.J.[You-Jiang], Zhu, L.C.[Lin-Chao], Jiang, L.[Lu], Yang, Y.[Yi],
Faster Meta Update Strategy for Noise-Robust Deep Learning,
CVPR21(144-153)
IEEE DOI 2111
Training, Deep learning, Training data, Robustness, Pattern recognition, Noise robustness BibRef

Li, Y.[Yao], Min, M.R.[Martin Renqiang], Lee, T.[Thomas], Yu, W.C.[Wen-Chao], Kruus, E.[Erik], Wang, W.[Wei], Hsieh, C.J.[Cho-Jui],
Towards Robustness of Deep Neural Networks via Regularization,
ICCV21(7476-7485)
IEEE DOI 2203
Deep learning, Manifolds, Analytical models, Computational modeling, Neural networks, Benchmark testing, Recognition and classification BibRef

Wang, X.S.[Xin-Shao], Hua, Y.[Yang], Kodirov, E.[Elyor], Clifton, D.A.[David A.], Robertson, N.M.[Neil M.],
ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networks,
CVPR21(752-761)
IEEE DOI 2111
Training, Deep learning, Semantics, Neural networks, Predictive models, Minimization, Entropy BibRef

Dong, X.Y.[Xiao-Yi], Chen, D.D.[Dong-Dong], Zhou, H.[Hang], Hua, G.[Gang], Zhang, W.M.[Wei-Ming], Yu, N.H.[Neng-Hai],
Self-Robust 3D Point Recognition via Gather-Vector Guidance,
CVPR20(11513-11521)
IEEE DOI 2008
Robustness, Perturbation methods, Training, Image restoration, Aircraft BibRef

Qian, Q.[Qi], Hu, J.H.[Ju-Hua], Li, H.[Hao],
Hierarchically Robust Representation Learning,
CVPR20(7334-7342)
IEEE DOI 2008
Robustness, Task analysis, Feature extraction, Optimization, Benchmark testing, Training, Data models BibRef

Rodríguez-Rodríguez, J.A.[José A.], Molina-Cabello, M.A.[Miguel A.], Benítez-Rochel, R.[Rafaela], López-Rubio, E.[Ezequiel],
The Effect of Noise and Brightness on Convolutional Deep Neural Networks,
MOI2QDN20(639-654).
Springer DOI 2103
BibRef

Zhang, R., Peng, Z., Wu, L., Li, Z., Luo, P.,
Exemplar Normalization for Learning Deep Representation,
CVPR20(12723-12732)
IEEE DOI 2008
Task analysis, Training, Tensile stress, Standards, Switches, Noise measurement, Benchmark testing BibRef

Jaiswal, M.S., Kang, B., Lee, J., Cho, M.,
MUTE: Inter-class Ambiguity Driven Multi-hot Target Encoding for Deep Neural Network Design,
DeepVision20(3254-3263)
IEEE DOI 2008
Encoding, Neural networks, Hamming distance, Noise measurement, Semantics, Computational modeling, Training BibRef

Huang, Y., Yu, Y.,
An Internal Covariate Shift Bounding Algorithm for Deep Neural Networks by Unitizing Layers' Outputs,
CVPR20(8462-8470)
IEEE DOI 2008
Integrated circuits, Upper bound, Training, Neural networks, Convergence, Noise measurement, Earth BibRef

Wang, Z.[Zhen], Hu, G.S.[Guo-Sheng], Hu, Q.H.[Qing-Hua],
Training Noise-Robust Deep Neural Networks via Meta-Learning,
CVPR20(4523-4532)
IEEE DOI 2008
Noise measurement, Optimization, Training, Noise robustness, Natural language processing, Robustness BibRef

Zhang, L., Qi, G.,
WCP: Worst-Case Perturbations for Semi-Supervised Deep Learning,
CVPR20(3911-3920)
IEEE DOI 2008
Perturbation methods, Training, Additives, Robustness, Predictive models, Data models, Additive noise BibRef

Han, J., Luo, P., Wang, X.,
Deep Self-Learning From Noisy Labels,
ICCV19(5137-5146)
IEEE DOI 2004
data handling, learning (artificial intelligence), neural nets, robust network, noisy labels, clean data, Optimization BibRef

Gowal, S.[Sven], Dvijotham, K.[Krishnamurthy], Stanforth, R.[Robert], Bunel, R.[Rudy], Qin, C.[Chongli], Uesato, J.[Jonathan], Arandjelovic, R.[Relja], Mann, T.A.[Timothy Arthur], Kohli, P.[Pushmeet],
Scalable Verified Training for Provably Robust Image Classification,
ICCV19(4841-4850)
IEEE DOI 2004
Robustness, Training, Neural networks, Perturbation methods, Upper bound, Adaptation models, Optimization BibRef

Wang, Y.S.[Yi-Sen], Ma, X.J.[Xing-Jun], Chen, Z.Y.[Zai-Yi], Luo, Y.[Yuan], Yi, J.F.[Jin-Feng], Bailey, J.[James],
Symmetric Cross Entropy for Robust Learning With Noisy Labels,
ICCV19(322-330)
IEEE DOI 2004
entropy, neural nets, symmetric cross entropy learning, noise robust counterpart reverse cross entropy, noisy labels, Task analysis BibRef

Nazaré, T.S.[Tiago S.], da Costa, G.B.P.[Gabriel B. Paranhos], Contato, W.A.[Welinton A.], Ponti, M.P.[Moacir P.],
Deep Convolutional Neural Networks and Noisy Images,
CIARP17(416-424).
Springer DOI 1802
BibRef

Rodner, E.[Erik], Simon, M.[Marcel], Fisher, R.[Robert], Denzler, J.[Joachim],
Fine-grained Recognition in the Noisy Wild: Sensitivity Analysis of Convolutional Neural Networks Approaches,
BMVC16(xx-yy).
HTML Version. 1805
BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Structural Description, Spatial Descriptions in Deep Networks .


Last update:Nov 28, 2022 at 16:32:47