14.3.1 Noisy Labels for Learning

Chapter Contents (Back)
Noisy Labels. Robust Technique. Not all labeled samples are correct.

Liu, T., Tao, D.,
Classification with Noisy Labels by Importance Reweighting,
PAMI(38), No. 3, March 2016, pp. 447-461.
IEEE DOI 1602
Algorithm design and analysis. Sample labels are randomly corrupted. BibRef

Zhang, R.[Rui], Chen, Z.H.[Zheng-Hao], Zhang, S.X.[San-Xing], Song, F.[Fei], Zhang, G.[Gang], Zhou, Q.C.[Quan-Cheng], Lei, T.[Tao],
Remote Sensing Image Scene Classification with Noisy Label Distillation,
RS(12), No. 15, 2020, pp. xx-yy.
DOI Link 2008
Training CNN requires lots of clean data. BibRef

Gu, S.W.[Song-Wei], Zhang, R.[Rui], Luo, H.X.[Hong-Xia], Li, M.Y.[Meng-Yao], Feng, H.[Huamei], Tang, X.G.[Xu-Guang],
Improved SinGAN Integrated with an Attentional Mechanism for Remote Sensing Image Classification,
RS(13), No. 9, 2021, pp. xx-yy.
DOI Link 2105
BibRef

Zhang, Q.[Qian], Lee, F.F.[Fei-Fei], Wang, Y.G.[Ya-Gang], Miao, R.[Ran], Chen, L.[Lei], Chen, Q.[Qiu],
An improved noise loss correction algorithm for learning from noisy labels,
JVCIR(72), 2020, pp. 102930.
Elsevier DOI 2010
Noisy labels, KL entropy, Mix-up loss, DNN BibRef

de Aquino Afonso, B.K.[Bruno Klaus], Berton, L.[Lilian],
Identifying noisy labels with a transductive semi-supervised leave-one-out filter,
PRL(140), 2020, pp. 127-134.
Elsevier DOI 2012
Semi-supervised learning, Classification, Graph-based, Filter, Label noise BibRef

Han, Y.[Yan], Roy, S.K.[Soumava Kumar], Petersson, L.[Lars], Harandi, M.[Mehrtash],
Discrepant collaborative training by Sinkhorn divergences,
IVC(112), 2021, pp. 104213.
Elsevier DOI 2107
BibRef
Earlier:
Learning from Noisy Labels via Discrepant Collaborative Training,
WACV20(3158-3167)
IEEE DOI 2006
Co-training, Noisy labels, Weak-supervised learning. Noise measurement, Training, Collaboration, Task analysis, Feature extraction, Discrete cosine transforms, Neural networks BibRef

Sun, H.L.[Hao-Liang], Guo, C.H.[Chen-Hui], Wei, Q.[Qi], Han, Z.Y.[Zhong-Yi], Yin, Y.L.[Yi-Long],
Learning to rectify for robust learning with noisy labels,
PR(124), 2022, pp. 108467.
Elsevier DOI 2203
Label noise, Meta-learning, Probabilistic model, Robust learning BibRef

Algan, G.[Görkem], Ulusoy, I.[Ilkay],
MetaLabelNet: Learning to Generate Soft-Labels From Noisy-Labels,
IP(31), 2022, pp. 4352-4362.
IEEE DOI 2207
Training, Noise measurement, Noise robustness, Feature extraction, Training data, Deep learning, Wide band gap semiconductors, meta-learning BibRef

Yi, R.[Rumeng], Huang, Y.P.[Ya-Ping],
TC-Net: Detecting Noisy Labels Via Transform Consistency,
MultMed(24), 2022, pp. 4328-4341.
IEEE DOI 2210
Noise measurement, Training, Visualization, Transforms, Predictive models, Perturbation methods, Airplanes, Noisy labels, visual attention consistency BibRef

Nomura, Y.[Yuichiro], Kurita, T.[Takio],
Sample Selection Approach with Number of False Predictions for Learning with Noisy Labels,
IEICE(E105-D), No. 10, October 2022, pp. 1759-1768.
WWW Link. 2210
BibRef

Wang, S.[Shaoru], Gao, J.[Jin], Li, B.[Bing], Hu, W.M.[Wei-Ming],
Narrowing the Gap: Improved Detector Training With Noisy Location Annotations,
IP(31), 2022, pp. 6369-6380.
IEEE DOI 2211
Annotations, Noise measurement, Detectors, Task analysis, Training, Object detection, Degradation, Object detection, noisy label, teacher-student learning BibRef

Xu, Z.[Zhe], Lu, D.[Donghuan], Luo, J.[Jie], Wang, Y.X.[Yi-Xin], Yan, J.P.[Jiang-Peng], Ma, K.[Kai], Zheng, Y.F.[Ye-Feng], Tong, R.K.Y.[Raymond Kai-Yu],
Anti-Interference From Noisy Labels: Mean-Teacher-Assisted Confident Learning for Medical Image Segmentation,
MedImg(41), No. 11, November 2022, pp. 3062-3073.
IEEE DOI 2211
Image segmentation, Noise measurement, Training, Biomedical imaging, Task analysis, Quality control, label denoising BibRef

Zhang, L.[Le], Tanno, R.[Ryutaro], Xu, M.[Moucheng], Huang, Y.W.[Ya-Wen], Bronik, K.[Kevin], Jin, C.[Chen], Jacob, J.[Joseph], Zheng, Y.F.[Ye-Feng], Shao, L.[Ling], Ciccarelli, O.[Olga], Barkhof, F.[Frederik], Alexander, D.C.[Daniel C.],
Learning from multiple annotators for medical image segmentation,
PR(138), 2023, pp. 109400.
Elsevier DOI 2303
Multi-Annotator, Label fusion, Segmentation BibRef

Miao, Q.[Qing], Wu, X.H.[Xiao-He], Xu, C.[Chao], Zuo, W.M.[Wang-Meng], Meng, Z.P.[Zhao-Peng],
On better detecting and leveraging noisy samples for learning with severe label noise,
PR(136), 2023, pp. 109210.
Elsevier DOI 2301
Severe label noise, Lipschitz regularization, Adaptive modeling and detection of label noise, Semi-supervised learning BibRef

Gong, C.[Chen], Ding, Y.L.[Yong-Liang], Han, B.[Bo], Niu, G.[Gang], Yang, J.[Jian], You, J.[Jane], Tao, D.C.[Da-Cheng], Sugiyama, M.[Masashi],
Class-Wise Denoising for Robust Learning Under Label Noise,
PAMI(45), No. 3, March 2023, pp. 2835-2848.
IEEE DOI 2302
Noise measurement, Training, Entropy, Estimation, Neural networks, Matrix decomposition, Fasteners, Label noise, centroid estimation, variance reduction BibRef

Xia, X.B.[Xiao-Bo], Han, B.[Bo], Wang, N.N.[Nan-Nan], Deng, J.K.[Jian-Kang], Li, J.T.[Jia-Tong], Mao, Y.[Yinian], Liu, T.L.[Tong-Liang],
Extended T: Learning With Mixed Closed-Set and Open-Set Noisy Labels,
PAMI(45), No. 3, March 2023, pp. 3047-3058.
IEEE DOI 2302
Noise measurement, Training, Training data, Data models, Search engines, Face recognition, Computer science, robustness BibRef

Li, S.K.[Shi-Kun], Liu, T.L.[Tong-Liang], Tan, J.Y.[Ji-Yong], Zeng, D.[Dan], Ge, S.M.[Shi-Ming],
Trustable Co-Label Learning From Multiple Noisy Annotators,
MultMed(25), 2023, pp. 1045-1057.
IEEE DOI 2303
Noise measurement, Data models, Training, Labeling, Supervised learning, Robustness, Deep learning, Label noise, learning from crowds BibRef

Liang, C.[Chao], Yang, Z.X.[Zong-Xin], Zhu, L.C.[Lin-Chao], Yang, Y.[Yi],
Co-Learning Meets Stitch-Up for Noisy Multi-Label Visual Recognition,
IP(32), 2023, pp. 2508-2519.
IEEE DOI 2305
Noise measurement, Training, Dogs, Deep learning, Annotations, Visualization, Training data, Noisy labels, deep learning BibRef

Gong, X.W.[Xiu-Wen], Yuan, D.[Dong], Bao, W.[Wei], Luo, F.[Fulin],
A Unifying Probabilistic Framework for Partially Labeled Data Learning,
PAMI(45), No. 7, July 2023, pp. 8036-8048.
IEEE DOI 2306
Phase locked loops, Correlation, Training, Probabilistic logic, Testing, Task analysis, Noise measurement, classification BibRef

Zhao, Z.L.[Zhi-Lin], Cao, L.B.[Long-Bing], Lin, K.Y.[Kun-Yu],
Revealing the Distributional Vulnerability of Discriminators by Implicit Generators,
PAMI(45), No. 7, July 2023, pp. 8888-8901.
IEEE DOI 2306
Generators, Training, Standards, Entropy, Detectors, Sensitivity, Neural networks, Deep learning, generator-discriminator, shannon entropy BibRef

Yao, J.C.[Jiang-Chao], Han, B.[Bo], Zhou, Z.H.[Zhi-Han], Zhang, Y.[Ya], Tsang, I.W.[Ivor W.],
Latent Class-Conditional Noise Model,
PAMI(45), No. 8, August 2023, pp. 9964-9980.
IEEE DOI 2307
Noise measurement, Training, Optimization, Deep learning, Bayes methods, Robustness, Computational modeling, semi-supervised learning BibRef

Wang, L.[Lin], Xu, X.M.[Xiang-Min], Guo, K.[Kailing], Cai, B.[Bolun], Liu, F.[Fang],
Reflective Learning With Label Noise,
CirSysVideo(33), No. 7, July 2023, pp. 3343-3357.
IEEE DOI 2307
Noise measurement, Training, Iterative methods, Task analysis, Entropy, Optimization, Transfer learning, Reflective learning, dynamic iterative function BibRef

Chen, Y.Q.[Yuan-Qi], Jin, C.[Cece], Li, G.[Ge], Li, T.H.[Thomas H.], Gao, W.[Wei],
Mitigating Label Noise in GANs via Enhanced Spectral Normalization,
CirSysVideo(33), No. 8, August 2023, pp. 3924-3934.
IEEE DOI 2308
Noise measurement, Training, Task analysis, Image synthesis, Generators, Generative adversarial networks, Neural networks, learning with noisy labels BibRef

Sumbul, G.[Gencer], Demir, B.[Begum],
Generative Reasoning Integrated Label Noise Robust Deep Image Representation Learning,
IP(32), 2023, pp. 4529-4542.
IEEE DOI 2309
BibRef

Gong, Y.S.[Yong-Shun], Li, Z.B.[Zhi-Bin], Liu, W.[Wei], Lu, X.[Xiankai], Liu, X.W.[Xin-Wang], Tsang, I.W.[Ivor W.], Yin, Y.L.[Yi-Long],
Missingness-Pattern-Adaptive Learning With Incomplete Data,
PAMI(45), No. 9, September 2023, pp. 11053-11066.
IEEE DOI 2309

WWW Link. BibRef

Liu, D.[Defu], Li, W.[Wen], Duan, L.X.[Li-Xin], Tsang, I.W.[Ivor W.], Yang, G.W.[Guo-Wu],
Noisy Label Learning With Provable Consistency for a Wider Family of Losses,
PAMI(45), No. 11, November 2023, pp. 13536-13552.
IEEE DOI 2310
BibRef

Liu, F.C.[Fu-Chang], Wang, Y.[Yu], Li, Z.[Zheng], Pan, Z.G.[Zhi-Geng],
GEIKD: Self-knowledge distillation based on gated ensemble networks and influences-based label noise removal,
CVIU(235), 2023, pp. 103771.
Elsevier DOI 2310
Self-distillation, Gated ensemble network, Influences estimation, Noisy labels BibRef

Zhao, X.M.[Xue-Mei], Cheng, Y.[Yong], Liang, L.[Luo], Wang, H.[Haijian], Gao, X.Y.[Xing-Yu], Wu, J.[Jun],
A balanced random learning strategy for CNN based Landsat image segmentation under imbalanced and noisy labels,
PR(144), 2023, pp. 109824.
Elsevier DOI 2310
Landsat image segmentation, Noisy labels, Confidence interval, Random learning, Multi-layer features BibRef

Yan, Y.[Yan], Xu, Y.[Youze], Xue, J.H.[Jing-Hao], Lu, Y.[Yang], Wang, H.Z.[Han-Zi], Zhu, W.T.[Wen-Tao],
Drop Loss for Person Attribute Recognition With Imbalanced Noisy-Labeled Samples,
Cyber(53), No. 11, November 2023, pp. 7071-7084.
IEEE DOI 2310
BibRef

Mao, S.[Shunan], Wang, Y.[Yaowei], Wang, X.Y.[Xiao-Yu], Zhang, S.L.[Shi-Liang],
Multi-proxy feature learning for robust fine-grained visual recognition,
PR(143), 2023, pp. 109779.
Elsevier DOI 2310
Fine-grained visual recognition, Noisy label, Long tail, Proxy learning BibRef

Liu, C.Y.[Cheng-Yang], Zhao, L.[Lin], Wu, H.B.[Hai-Bin],
Hyperspectral Images Weakly Supervised Classification with Noisy Labels,
RS(15), No. 20, 2023, pp. 4994.
DOI Link 2310
BibRef

Li, X.C.[Xiu-Chuan], Xia, X.B.[Xiao-Bo], Zhu, F.[Fei], Liu, T.L.[Tong-Liang], Zhang, X.Y.[Xu-Yao], Liu, C.L.[Cheng-Lin],
Dynamics-aware loss for learning with label noise,
PR(144), 2023, pp. 109835.
Elsevier DOI 2310
Label noise, Dynamics, Robust loss function BibRef

Yang, S.[Shuo], Wu, S.[Songhua], Yang, E.[Erkun], Han, B.[Bo], Liu, Y.[Yang], Xu, M.[Min], Niu, G.[Gang], Liu, T.L.[Tong-Liang],
A Parametrical Model for Instance-Dependent Label Noise,
PAMI(45), No. 12, December 2023, pp. 14055-14068.
IEEE DOI 2311
BibRef

Wan, J.[Jia], Wu, Q.Q.[Qiang-Qiang], Chan, A.B.[Antoni B],
Modeling Noisy Annotations for Point-Wise Supervision,
PAMI(45), No. 12, December 2023, pp. 15065-15080.
IEEE DOI 2311
BibRef

Chen, Q.Q.[Qing-Qiang], Jiang, G.X.[Gao-Xia], Cao, F.Y.[Fu-Yuan], Men, C.Q.[Chang-Qian], Wang, W.J.[Wen-Jian],
A general elevating framework for label noise filters,
PR(147), 2024, pp. 110072.
Elsevier DOI 2312
Classification, Label noise, Noise filter, Sample reduction BibRef

Feng, Z.[Zerun], Zeng, Z.M.[Zhi-Min], Guo, C.[Caili], Li, Z.[Zheng], Hu, L.[Lin],
Learning From Noisy Correspondence With Tri-Partition for Cross-Modal Matching,
MultMed(26), 2024, pp. 3884-3896.
IEEE DOI 2402
Noise measurement, Semantics, Training, Semisupervised learning, Data models, Costs, Visualization, Cross-modal matching, video-text matching BibRef

Lacy, F.[Fred], Ruiz-Reyes, A.[Angel], Brescia, A.[Anthony],
Machine learning for low signal-to-noise ratio detection,
PRL(179), 2024, pp. 115-122.
Elsevier DOI 2403
Anomaly, artificial intelligence, Long short-term memory, Low signal-to-noise, Neural network, Signal detection, Surveillance BibRef


Taraday, M.K.[Mitchell Keren], Baskin, C.[Chaim],
Enhanced Meta Label Correction for Coping with Label Corruption,
ICCV23(16249-16258)
IEEE DOI 2401
BibRef

Yenamandra, S.[Sriram], Ramesh, P.[Pratik], Prabhu, V.[Viraj], Hoffman, J.[Judy],
FACTS: First Amplify Correlations and Then Slice to Discover Bias,
ICCV23(4771-4781)
IEEE DOI Code:
WWW Link. 2401
BibRef

Ahn, C.[Chanho], Kim, K.[Kikyung], Baek, J.W.[Ji-Won], Lim, J.[Jongin], Han, S.J.[Seung-Ju],
Sample-wise Label Confidence Incorporation for Learning with Noisy Labels,
ICCV23(1823-1832)
IEEE DOI 2401
BibRef

Yuan, S.[Suqin], Feng, L.[Lei], Liu, T.L.[Tong-Liang],
Late Stopping: Avoiding Confidently Learning from Mislabeled Examples,
ICCV23(16033-16042)
IEEE DOI 2401
BibRef

Huang, H.X.[Hua-Xi], Kang, H.[Hui], Liu, S.[Sheng], Salvado, O.[Olivier], Rakotoarivelo, T.[Thierry], Wang, D.D.[Da-Dong], Liu, T.L.[Tong-Liang],
PADDLES: Phase-Amplitude Spectrum Disentangled Early Stopping for Learning with Noisy Labels,
ICCV23(16673-16684)
IEEE DOI 2401
BibRef

Yang, H.[Han], Wang, T.Y.[Tian-Yu], Hu, X.W.[Xiao-Wei], Fu, C.W.[Chi-Wing],
SILT: Shadow-aware Iterative Label Tuning for Learning to Detect Shadows from Noisy Labels,
ICCV23(12641-12652)
IEEE DOI 2401
BibRef

Xia, X.B.[Xiao-Bo], Han, B.[Bo], Zhan, Y.B.[Yi-Bing], Yu, J.[Jun], Gong, M.M.[Ming-Ming], Gong, C.[Chen], Liu, T.L.[Tong-Liang],
Combating Noisy Labels with Sample Selection by Mining High-Discrepancy Examples,
ICCV23(1833-1843)
IEEE DOI 2401
BibRef

Zhang, M.[Manyi], Zhao, X.Y.[Xu-Yang], Yao, J.[Jun], Yuan, C.[Chun], Huang, W.[Weiran],
When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Method,
ICCV23(15844-15854)
IEEE DOI 2401
BibRef

Rabbani, N.[Navid], Bartoli, A.[Adrien],
Unsupervised Confidence Approximation: Trustworthy Learning from Noisy Labelled Data,
Uncertainty23(4611-4619)
IEEE DOI 2401
BibRef

Ricci, S.[Simone], Uricchio, T.[Tiberio], del Bimbo, A.[Alberto],
Smoothing and Transition Matrices Estimation to Learn with Noisy Labels,
CIAP23(I:450-462).
Springer DOI
WWW Link. 2312
BibRef

Joshi, A.[Aniket], Das, N.[Nilotpal], Yenigalla, P.[Promod],
Product Image Representation Learning on Large Scale Noisy Datasets,
ICIP23(2570-2574)
IEEE DOI 2312
BibRef

Pastor, A.[Andréas], Krasula, L.[Lukáš], Zhu, X.Q.[Xiao-Qing], Li, Z.[Zhi], Callet, P.L.[Patrick Le],
Recovering Quality Scores in Noisy Pairwise Subjective Experiments Using Negative Log-Likelihood,
ICIP23(2635-2639)
IEEE DOI 2312
BibRef

Adachi, K.[Kazuki], Yamaguchi, S.[Shin'Ya], Kumagai, A.[Atsutoshi],
Covariance-Aware Feature Alignment with Pre-Computed Source Statistics for Test-Time Adaptation to Multiple Image Corruptions,
ICIP23(800-804)
IEEE DOI 2312
BibRef

Tai, T.M.[Tsung-Ming], Jhang, Y.J.[Yun-Jie], Hwang, W.J.[Wen-Jyi],
Robust Feature Learning Against Noisy Labels,
ICIP23(2235-2239)
IEEE DOI 2312
BibRef

Zhang, Y.Q.[Yong-Qi], Zhang, H.[Hui], Yao, Q.M.[Quan-Ming], Wan, J.[Jun],
Combining Self-Supervised and Supervised Learning with Noisy Labels,
ICIP23(605-609)
IEEE DOI 2312
BibRef

Tallec, G.[Gauthier], Yvinec, E.[Edouard], Dapogny, A.[Arnaud], Bailly, K.[Kevin],
Fighting Over-Fitting with Quantization for Learning Deep Neural Networks on Noisy Labels,
ICIP23(575-579)
IEEE DOI 2312
BibRef

Yu, X.T.[Xiao-Tian], Jiang, Y.[Yang], Shi, T.Q.[Tian-Qi], Feng, Z.[Zunlei], Wang, Y.[Yuexuan], Song, M.L.[Ming-Li], Sun, L.[Li],
How to Prevent the Continuous Damage of Noises to Model Training?,
CVPR23(12054-12063)
IEEE DOI 2309
BibRef

Bucarelli, M.S.[Maria Sofia], Cassano, L.[Lucas], Siciliano, F.[Federico], Mantrach, A.[Amin], Silvestri, F.[Fabrizio],
Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels,
CVPR23(3439-3448)
IEEE DOI 2309
BibRef

Huang, Z.Z.[Zhi-Zhong], Zhang, J.P.[Jun-Ping], Shan, H.M.[Hong-Ming],
Twin Contrastive Learning with Noisy Labels,
CVPR23(11661-11670)
IEEE DOI 2309
BibRef

Feng, C.[Chuanwen], Ren, Y.L.[Yi-Long], Xie, X.[Xike],
OT-Filter: An Optimal Transport Filter for Learning with Noisy Labels,
CVPR23(16164-16174)
IEEE DOI 2309
BibRef

Gan, B.[Bei], Shu, X.J.[Xiu-Jun], Qiao, R.Z.[Rui-Zhi], Wu, H.Q.[Hao-Qian], Chen, K.Y.[Ke-Yu], Li, H.[Hanjun], Ren, B.[Bo],
Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Movies,
CVPR23(18898-18907)
IEEE DOI 2309
BibRef

Li, Y.F.[Yi-Fan], Han, H.[Hu], Shan, S.G.[Shi-Guang], Chen, X.L.[Xi-Lin],
DISC: Learning from Noisy Labels via Dynamic Instance-Specific Selection and Correction,
CVPR23(24070-24079)
IEEE DOI 2309
BibRef

Tatjer, A.[Albert], Nagarajan, B.[Bhalaji], Marques, R.[Ricardo], Radeva, P.[Petia],
CCLM: Class-conditional Label Noise Modelling,
IbPRIA23(3-14).
Springer DOI 2307
BibRef

Tu, Y.P.[Yuan-Peng], Zhang, B.S.[Bo-Shen], Li, Y.X.[Yu-Xi], Liu, L.[Liang], Li, J.[Jian], Zhang, J.N.[Jiang-Ning], Wang, Y.[Yabiao], Wang, C.J.[Cheng-Jie], Zhao, C.R.[Cai Rong],
Learning with Noisy labels via Self-supervised Adversarial Noisy Masking,
CVPR23(16186-16195)
IEEE DOI 2309
BibRef
And:
Earlier: A1, A2, A3, A4, A5, A7, A8, A9, Only:
Learning from Noisy Labels with Decoupled Meta Label Purifier,
CVPR23(19934-19943)
IEEE DOI 2309
BibRef

Zhang, B.S.[Bo-Shen], Li, Y.X.[Yu-Xi], Tu, Y.P.[Yuan-Peng], Peng, J.L.[Jin-Long], Wang, Y.B.[Ya-Biao], Wu, C.[Cunlin], Xiao, Y.[Yang], Zhao, C.R.[Cai-Rong],
Learning from Noisy Labels with Coarse-to-fine Sample Credibility Modeling,
LLID22(21-38).
Springer DOI 2304
BibRef

Yang, C.H.H.[Chao-Han Huck], Hung, D.I.T.[Danny I-Te], Liu, Y.C.[Yi-Chieh], Chen, P.Y.[Pin-Yu],
Treatment Learning Causal Transformer for Noisy Image Classification,
WACV23(6128-6139)
IEEE DOI 2302
Deep learning, Visualization, Correlation, Perturbation methods, Training data, Benchmark testing, Transformers BibRef

Garg, A.[Arpit], Nguyen, C.[Cuong], Felix, R.[Rafael], Do, T.T.[Thanh-Toan], Carneiro, G.[Gustavo],
Instance-Dependent Noisy Label Learning via Graphical Modelling,
WACV23(2287-2297)
IEEE DOI 2302
Training, Deep learning, Visualization, Biological system modeling, Ecosystems, Benchmark testing, and algorithms (including transfer) BibRef

Smart, B.[Brandon], Carneiro, G.[Gustavo],
Bootstrapping the Relationship Between Images and Their Clean and Noisy Labels,
WACV23(5333-5343)
IEEE DOI 2302
Training, Computational modeling, Semisupervised learning, Prediction algorithms, Data models, visual reasoning BibRef

Liu, J.[Jiarun], Jiang, D.G.[Da-Guang], Yang, Y.K.[Yu-Kun], Li, R.R.[Rui-Rui],
Agreement or Disagreement in Noise-tolerant Mutual Learning?,
ICPR22(4801-4807)
IEEE DOI 2212
Training, Deep learning, Codes, Collaboration, Resists, Robustness BibRef

Fu, X.M.[Xuan-Ming], Yang, Z.F.[Zheng-Feng], Xue, H.[Hao], Wang, J.L.[Jian-Lin], Zeng, Z.B.[Zhen-Bing],
Robust Training with Feature-Based Adversarial Example,
ICPR22(2957-2963)
IEEE DOI 2212
Training, Perturbation methods, Robustness BibRef

Li, J.C.[Ji-Chang], Li, G.B.[Guan-Bin], Liu, F.[Feng], Yu, Y.Z.[Yi-Zhou],
Neighborhood Collective Estimation for Noisy Label Identification and Chiorrection,
ECCV22(XXIV:128-145).
Springer DOI 2211
BibRef

Gao, Z.Q.[Zheng-Qi], Sun, F.K.[Fan-Keng], Yang, M.[Mingran], Ren, S.C.[Su-Cheng], Xiong, Z.K.[Zi-Kai], Engeler, M.[Marc], Burazer, A.[Antonio], Wildling, L.[Linda], Daniel, L.[Luca], Boning, D.S.[Duane S.],
Learning from Multiple Annotator Noisy Labels via Sample-Wise Label Fusion,
ECCV22(XXIV:407-422).
Springer DOI 2211
BibRef

Wei, Q.[Qi], Sun, H.L.[Hao-Liang], Lu, X.[Xiankai], Yin, Y.L.[Yi-Long],
Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalization,
ECCV22(XXX:516-532).
Springer DOI 2211
BibRef

Cao, T.Y.[Tian-Yue], Wang, Y.X.[Yong-Xin], Xing, Y.F.[Yi-Fan], Xiao, T.J.[Tian-Jun], He, T.[Tong], Zhang, Z.[Zheng], Zhou, H.[Hao], Tighe, J.[Joseph],
PSS: Progressive Sample Selection for Open-World Visual Representation Learning,
ECCV22(XXXI:278-294).
Springer DOI 2211
BibRef

Kim, K.I.[Kwang In],
Active Label Correction Using Robust Parameter Update and Entropy Propagation,
ECCV22(XXI:1-16).
Springer DOI 2211
BibRef

Zhang, Z.[Ziyi], Chen, W.[Weikai], Fang, C.W.[Chao-Wei], Li, Z.[Zhen], Chen, L.[Lechao], Lin, L.[Liang], Li, G.B.[Guan-Bin],
RankMatch: Fostering Confidence and Consistency in Learning with Noisy Labels,
ICCV23(1644-1654)
IEEE DOI 2401
BibRef

Zhao, G.L.[Gan-Long], Li, G.B.[Guan-Bin], Qin, Y.P.[Yi-Peng], Liu, F.[Feng], Yu, Y.Z.[Yi-Zhou],
Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labels,
ECCV22(XXV:21-37).
Springer DOI 2211
BibRef

Kye, S.M.[Seong Min], Choi, K.[Kwanghee], Yi, J.Y.[Joon-Young], Chang, B.[Buru],
Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrection,
ECCV22(XXV:717-738).
Springer DOI 2211
BibRef

Gao, Z.Y.[Zi-Yang], Yan, Y.P.[Ya-Ping], Geng, X.[Xin],
Learning from Noisy Labels via Meta Credible Label Elicitation,
ICIP22(1391-1395)
IEEE DOI 2211
Degradation, Correlation, Neural networks, Benchmark testing, Robustness, Noise measurement, Meta Credible Label Elicitation, Label distribution BibRef

Gao, B.Y.[Bo-Yan], Gouk, H.[Henry], Hospedales, T.M.[Timothy M.],
Searching for Robustness: Loss Learning for Noisy Classification Tasks,
ICCV21(6650-6659)
IEEE DOI 2203
Training, Training data, Network architecture, Search problems, Robustness, Machine learning architectures and formulations BibRef

Wu, Z.F.[Zhi-Fan], Wei, T.[Tong], Jiang, J.W.[Jian-Wen], Mao, C.J.[Chao-Jie], Tang, M.Q.[Ming-Qian], Li, Y.F.[Yu-Feng],
NGC: A Unified Framework for Learning with Open-World Noisy Data,
ICCV21(62-71)
IEEE DOI 2203
Training, Degradation, Prototypes, Machine learning, Detectors, Predictive models, Recognition and classification, Transfer/Low-shot/Semi/Unsupervised Learning BibRef

Zhou, X.[Xiong], Liu, X.M.[Xian-Ming], Wang, C.Y.[Chen-Yang], Zhai, D.[Deming], Jiang, J.J.[Jun-Jun], Ji, X.Y.[Xiang-Yang],
Learning with Noisy Labels via Sparse Regularization,
ICCV21(72-81)
IEEE DOI 2203
Training, Deep learning, Neural networks, Fitting, Robustness, Entropy, Recognition and classification, Efficient training and inference methods BibRef

Yao, Y.Z.[Ya-Zhou], Sun, Z.[Zeren], Zhang, C.Y.[Chuan-Yi], Shen, F.M.[Fu-Min], Wu, Q.[Qi], Zhang, J.[Jian], Tang, Z.M.[Zhen-Min],
Jo-SRC: A Contrastive Approach for Combating Noisy Labels,
CVPR21(5188-5197)
IEEE DOI 2111
Training, Degradation, Deep learning, Codes, Robustness, Pattern recognition BibRef

Goel, P.[Purvi], Chen, L.[Li],
On the Robustness of Monte Carlo Dropout Trained with Noisy Labels,
WiCV21(2219-2228)
IEEE DOI 2109
Training, Uncertainty, Monte Carlo methods, Neurons, Estimation, Robustness, Pattern recognition BibRef

Wei, H., Feng, L., Chen, X., An, B.,
Combating Noisy Labels by Agreement: A Joint Training Method with Co-Regularization,
CVPR20(13723-13732)
IEEE DOI 2008
Noise measurement, Training, Robustness, Semisupervised learning, Neural networks, Machine learning, Estimation BibRef

Zhang, W.H.[Wei-He], Wang, Y.[Yali], Qiao, Y.[Yu],
MetaCleaner: Learning to Hallucinate Clean Representations for Noisy-Labeled Visual Recognition,
CVPR19(7365-7374).
IEEE DOI 2002
BibRef

Li, Y.C.[Yun-Cheng], Yang, J.C.[Jian-Chao], Song, Y.[Yale], Cao, L.L.[Liang-Liang], Luo, J.B.[Jie-Bo], Li, L.J.[Li-Jia],
Learning from Noisy Labels with Distillation,
ICCV17(1928-1936)
IEEE DOI 1802
graph theory, image recognition, learning (artificial intelligence), statistical analysis, Visualization BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Outlier Detection and Analysis, Robust Analysis, Out of Distribution .


Last update:Mar 16, 2024 at 20:36:19