mlsanityData to 7 Oct 2026

On Learning Contrastive Representations for Learning with Noisy Labels

arXiv 2203.01785 ↗First posted 3 Mar 2022cs.LG cs.CVcited by 21

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are able to memorize noisy labels easily with a softmax cross-entropy (CE) loss. Previous studies attempted to address this issue focus on incorporating a noise-robust loss function to the CE loss. However, the memorization issue is alleviated but still remains due to the non-robust CE loss. To address this issue, we focus on learning robust contrastive representations of data on which the classifier is hard to memorize the label noise under the CE loss. We propose a novel contrastive regularization function to learn such representations over noisy data where label noise does not dominate the representation learning. By theoretically investigating the representations induced by the proposed regularization function, we reveal that the learned representations keep information related to true labels and discard information related to corrupted labels. Moreover, our theoretical results also indicate that the learned representations are robust to the label noise. The effectiveness of this method is demonstrated with experiments on benchmark datasets.

Key facts. Cited by 21 papers in the map (data through 7 Oct 2026). Builds on 39 of its 54 references that are in the map. First posted on arXiv 3 Mar 2022.

Builds on

39 of 54 references.

References · 39

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,712
  6. 2020Exploring Simple Siamese Representation Learningcited by 2,853
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  9. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  10. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
  11. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
  12. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
27 more
  1. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  2. 2017A Closer Look at Memorization in Deep Networkscited by 936
  3. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 745
  4. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  5. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  6. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  7. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  8. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  9. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  10. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  11. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  12. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  13. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  14. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  15. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  16. 2021DetCo: Unsupervised Contrastive Learning for Object Detectioncited by 205
  17. 2019Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networkscited by 158
  18. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  19. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  20. 2020Learning Invariant Representations and Risks for Semi-supervised Domain Adaptationcited by 69
  21. 2020MoPro: Webly Supervised Learning with Momentum Prototypescited by 66
  22. 2019Robust Bi-Tempered Logistic Loss Based on Bregman Divergencescited by 61
  23. 2020What Do Neural Networks Learn When Trained With Random Labels?cited by 58
  24. 2021Contrastive Learning Improves Model Robustness Under Label Noisecited by 36
  25. 2020Improving Generalization by Controlling Label-Noise Information in Neural Network Weightscited by 35
  26. 2016A Minimax Approach to Supervised Learningcited by 33
  27. 2021A Framework using Contrastive Learning for Classification with Noisy Labelscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 10; 2024: 3; 2025: 6; 2026: 2.

21 papers.

Sort:

By area:

  1. 2023Dynamic Conceptional Contrastive Learning for Generalized Category Discoverycited by 90
  2. 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labelscited by 46
  3. 2023Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learningcited by 8
  4. 2024Bootstrap Latents of Nodes and Neighbors for Graph Self-Supervised Learningcited by 6
  5. 2023Compensation Learning in Semantic Segmentationcited by 5
  6. 2023Unleashing the Potential of Regularization Strategies in Learning with Noisy Labelscited by 5
  7. 2024Meta-Learning Guided Label Noise Distillation for Robust Signal Modulation Classificationcited by 4
  8. 2025Sample Selection via Contrastive Fragmentation for Noisy Label Regressioncited by 4
  9. 2025Guiding Noisy Label Conditional Diffusion Models with Score-based Discriminator Correctioncited by 3
  10. 2023Decoupled conditional contrastive learning with variable metadata for prostate lesion detectioncited by 2
  11. 2023Learning with Noisy Labels Using Collaborative Sample Selection and Contrastive Semi-Supervised Learningcited by 2
  12. 2024Granular-ball Representation Learning for Deep CNN on Learning with Label Noisecited by 2
9 more
  1. 2025Robust Classification with Noisy Labels Based on Posterior Maximizationcited by 2
  2. 2025Multi-level Supervised Contrastive Learningcited by 1
  3. 2023VALERIAN: Invariant Feature Learning for IMU Sensor-based Human Activity Recognition in the Wildcited by 0
  4. 2023Channel-Wise Contrastive Learning for Learning with Noisy Labelscited by 0
  5. 2023Resist Label Noise with PGM for Graph Neural Networkscited by 0
  6. 2025Set a Thief to Catch a Thief: Combating Label Noise through Noisy Meta Learningcited by 0
  7. 2025Similarity-based Outlier Detection for Noisy Object Re-Identification Using Beta Mixturescited by 0
  8. 2026FedCova: Robust Federated Covariance Learning Against Noisy Labelscited by 0
  9. 2026Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noisecited by 0