mlsanityData to 7 Oct 2026

Combating noisy labels by agreement: A joint training method with co-regularization

arXiv 2003.02752 ↗First posted 5 Mar 2020cs.CV cs.LG stat.MLcited by 289

Not on the map. Why?

Abstract (arXiv)

Deep Learning with noisy labels is a practically challenging problem in weakly supervised learning. The state-of-the-art approaches "Decoupling" and "Co-teaching+" claim that the "disagreement" strategy is crucial for alleviating the problem of learning with noisy labels. In this paper, we start from a different perspective and propose a robust learning paradigm called JoCoR, which aims to reduce the diversity of two networks during training. Specifically, we first use two networks to make predictions on the same mini-batch data and calculate a joint loss with Co-Regularization for each training example. Then we select small-loss examples to update the parameters of both two networks simultaneously. Trained by the joint loss, these two networks would be more and more similar due to the effect of Co-Regularization. Extensive experimental results on corrupted data from benchmark datasets including MNIST, CIFAR-10, CIFAR-100 and Clothing1M demonstrate that JoCoR is superior to many state-of-the-art approaches for learning with noisy labels.

Key facts. Cited by 289 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 49; 2022: 66; 2023: 56; 2024: 49; 2025: 41; 2026: 28.

289 papers.

Sort:

By area:

  1. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  2. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
  3. 2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
  4. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  5. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  6. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  7. 2022Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognitioncited by 67
  8. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  9. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 63
  10. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  11. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  12. 2021Detecting Corrupted Labels Without Training a Model to Predictcited by 57
38 more
  1. 2022Avoiding Overfitting: A Survey on Regularization Methods for Convolutional Neural Networkscited by 55
  2. 2021Co-learning: Learning from Noisy Labels with Self-supervisioncited by 50
  3. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  4. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  5. 2021Not All Negatives are Equal: Label-Aware Contrastive Loss for Fine-grained Text Classificationcited by 43
  6. 2022Mitigating Memorization of Noisy Labels by Clipping the Model Predictioncited by 40
  7. 2021Faster Meta Update Strategy for Noise-Robust Deep Learningcited by 38
  8. 2022Large Loss Matters in Weakly Supervised Multi-Label Classificationcited by 38
  9. 2022Towards Robust Ranker for Text Retrievalcited by 37
  10. 2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
  11. 2021Multimodal Co-learning: Challenges, Applications with Datasets, Recent Advances and Future Directionscited by 35
  12. 2021Joint Negative and Positive Learning for Noisy Labelscited by 34
  13. 2021Learning from Noisy Labels for Entity-Centric Information Extractioncited by 34
  14. 2022Identifiability of Label Noise Transition Matrixcited by 34
  15. 2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
  16. 2021Boosting Co-teaching with Compression Regularization for Label Noisecited by 31
  17. 2024Textual Knowledge Matters: Cross-Modality Co-Teaching for Generalized Visual Class Discoverycited by 30
  18. 2022PCL: Peer-Contrastive Learning with Diverse Augmentations for Unsupervised Sentence Embeddingscited by 29
  19. 2022Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsingcited by 29
  20. 2022To Aggregate or Not? Learning with Separate Noisy Labelscited by 29
  21. 2022Robust Training of Graph Neural Networks via Noise Governancecited by 29
  22. 2021Continual Learning on Noisy Data Streams via Self-Purified Replaycited by 27
  23. 2022Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Featurescited by 27
  24. 2021Mitigating Memorization of Noisy Labels via Regularization between Representationscited by 26
  25. 2023From Shortcuts to Triggers: Backdoor Defense with Denoised PoEcited by 26
  26. 2023Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Modelscited by 26
  27. 2021Superpixel-guided Iterative Learning from Noisy Labels for Medical Image Segmentationcited by 25
  28. 2022Open-Sampling: Exploring Out-of-Distribution data for Re-balancing Long-tailed datasetscited by 25
  29. 2023Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidancecited by 24
  30. 2021Noise-resistant Deep Metric Learning with Ranking-based Instance Selectioncited by 23
  31. 2021Understanding Instance-Level Label Noise: Disparate Impacts and Treatmentscited by 22
  32. 2021Taxonomy of Machine Learning Safety: A Survey and Primercited by 22
  33. 2022FedMix: Mixed Supervised Federated Learning for Medical Image Segmentationcited by 22
  34. 2023Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learningcited by 22
  35. 2022PiCO+: Contrastive Label Disambiguation for Robust Partial Label Learningcited by 21
  36. 2022On Learning Contrastive Representations for Learning with Noisy Labelscited by 21
  37. 2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 21
  38. 2022Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformercited by 21

50 most cited of 289 All 289 (JSON)