mlsanityData to 7 Oct 2026

Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels

arXiv 1804.06872 ↗First posted 18 Apr 2018cs.LG stat.MLcited by 1,053

Not on the map. Why?

Abstract (arXiv)

Deep learning with noisy labels is practically challenging, as the capacity of deep models is so high that they can totally memorize these noisy labels sooner or later during training. Nonetheless, recent studies on the memorization effects of deep neural networks show that they would first memorize training data of clean labels and then those of noisy labels. Therefore in this paper, we propose a new deep learning paradigm called Co-teaching for combating with noisy labels. Namely, we train two deep neural networks simultaneously, and let them teach each other given every mini-batch: firstly, each network feeds forward all data and selects some data of possibly clean labels; secondly, two networks communicate with each other what data in this mini-batch should be used for training; finally, each network back propagates the data selected by its peer network and updates itself. Empirical results on noisy versions of MNIST, CIFAR-10 and CIFAR-100 demonstrate that Co-teaching is much superior to the state-of-the-art methods in the robustness of trained deep models.

Key facts. Cited by 1,053 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 1; 2021: 221; 2022: 205; 2023: 202; 2024: 168; 2025: 138; 2026: 117.

1,053 papers.

Sort:

By area:

  1. 2022Text Embeddings by Weakly-Supervised Contrastive Pre-trainingcited by 1,216
  2. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  3. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  4. 2022Decoupled Knowledge Distillationcited by 380
  5. 2021Understanding Dataset Difficulty with V-Usable Informationcited by 288
  6. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  7. 2021A Survey on Deep Semi-supervised Learningcited by 250
  8. 2023CLIP2Scene: Towards Label-efficient 3D Scene Understanding by CLIPcited by 178
  9. 2021A Fine-Grained Analysis on Distribution Shiftcited by 171
  10. 2024WARM: On the Benefits of Weight Averaged Reward Modelscited by 145
  11. 2022Federated Learning from Pre-Trained Models: A Contrastive Learning Approachcited by 141
  12. 2022The 'Problem' of Human Label Variation: On Ground Truth in Data, Modeling and Evaluationcited by 133
38 more
  1. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
  2. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  3. 2021Deep Learning with Label Differential Privacycited by 113
  4. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  5. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  6. 2021Regularizing Generative Adversarial Networks under Limited Datacited by 105
  7. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  8. 2021Semi-Supervised Medical Image Segmentation via Cross Teaching between CNN and Transformercited by 99
  9. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  10. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  11. 2021WRENCH: A Comprehensive Benchmark for Weak Supervisioncited by 95
  12. 2022Robust Training under Label Noise by Over-parameterizationcited by 93
  13. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  14. 2022Self-Training: A Surveycited by 85
  15. 2021FINE Samples for Learning with Noisy Labelscited by 82
  16. 2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
  17. 2021Robust Audio-Visual Instance Discriminationcited by 80
  18. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  19. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  20. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  21. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  22. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  23. 2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
  24. 2022Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognitioncited by 67
  25. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  26. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  27. 2022Understanding and Improving Graph Injection Attack by Promoting Unnoticeabilitycited by 62
  28. 2023Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Reviewcited by 62
  29. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  30. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  31. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  32. 2021Detecting Corrupted Labels Without Training a Model to Predictcited by 57
  33. 2021Exploring Memorization in Adversarial Trainingcited by 55
  34. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  35. 2022Robust Cross-Modal Representation Learning with Progressive Self-Distillationcited by 55
  36. 2023Noisy-Correspondence Learning for Text-to-Image Person Re-identificationcited by 55
  37. 2022DrugOOD: Out-of-Distribution (OOD) Dataset Curator and Benchmark for AI-aided Drug Discovery -- A Focus on Affinity Prediction Problems with Noise Annotationscited by 54
  38. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54

50 most cited of 1,053 All 1,053 (JSON)