mlsanityData to 7 Oct 2026

DivideMix: Learning with Noisy Labels as Semi-supervised Learning

arXiv 2002.07394 ↗First posted 18 Feb 2020cs.CVcited by 691

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by exploiting unlabeled data. In this work, we propose DivideMix, a novel framework for learning with noisy labels by leveraging semi-supervised learning techniques. In particular, DivideMix models the per-sample loss distribution with a mixture model to dynamically divide the training data into a labeled set with clean samples and an unlabeled set with noisy samples, and trains the model on both the labeled and unlabeled data in a semi-supervised manner. To avoid confirmation bias, we simultaneously train two diverged networks where each network uses the dataset division from the other network. During the semi-supervised training phase, we improve the MixMatch strategy by performing label co-refinement and label co-guessing on labeled and unlabeled samples, respectively. Experiments on multiple benchmark datasets demonstrate substantial improvements over state-of-the-art methods. Code is available at https://github.com/LiJunnan1992/DivideMix .

Key facts. Cited by 691 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 113; 2022: 132; 2023: 137; 2024: 138; 2025: 92; 2026: 79.

691 papers.

Sort:

By area:

  1. 2021Align before Fuse: Vision and Language Representation Learning with Momentum Distillationcited by 1,612
  2. 2023Weak-to-Strong Generalization: Eliciting Strong Capabilities With Weak Supervisioncited by 445
  3. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  4. 2021A Survey on Deep Semi-supervised Learningcited by 250
  5. 2023Query-Dependent Video Representation for Moment Retrieval and Highlight Detectioncited by 166
  6. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 147
  7. 2024CoR-GS: Sparse-View 3D Gaussian Splatting via Co-Regularizationcited by 120
  8. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  9. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  10. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  11. 2021Mutual Consistency Learning for Semi-supervised Medical Image Segmentationcited by 107
  12. 2021SPICE: Semantic Pseudo-labeling for Image Clusteringcited by 104
38 more
  1. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  2. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  3. 2022Robust Training under Label Noise by Over-parameterizationcited by 93
  4. 2021Dive into Ambiguity: Latent Distribution Mining and Pairwise Uncertainty Estimation for Facial Expression Recognitioncited by 89
  5. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  6. 2021FINE Samples for Learning with Noisy Labelscited by 82
  7. 2021Breaking the Dilemma of Medical Image-to-image Translationcited by 82
  8. 2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
  9. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  10. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  11. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  12. 2021NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphscited by 73
  13. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  14. 2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
  15. 2022Learn From All: Erasing Attention Consistency for Noisy Label Facial Expression Recognitioncited by 67
  16. 2024Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefitscited by 65
  17. 2023Guiding Pseudo-labels with Uncertainty Estimation for Source-free Unsupervised Domain Adaptationcited by 63
  18. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  19. 2022Debiased Self-Training for Semi-Supervised Learningcited by 62
  20. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
  21. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  22. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  23. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  24. 2021Detecting Corrupted Labels Without Training a Model to Predictcited by 57
  25. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  26. 2023Noisy-Correspondence Learning for Text-to-Image Person Re-identificationcited by 55
  27. 2024SoftPatch: Unsupervised Anomaly Detection with Noisy Datacited by 55
  28. 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
  29. 2022RLIP: Relational Language-Image Pre-training for Human-Object Interaction Detectioncited by 54
  30. 2023A Survey on Time-Series Pre-Trained Modelscited by 52
  31. 2021Co-learning: Learning from Noisy Labels with Self-supervisioncited by 50
  32. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  33. 2023Soft Contrastive Learning for Time Seriescited by 49
  34. 2021Hard Sample Aware Noise Robust Learning for Histopathology Image Classificationcited by 48
  35. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  36. 2022Investigating Why Contrastive Learning Benefits Robustness Against Label Noisecited by 46
  37. 2021Active label cleaning for improved dataset quality under resource constraintscited by 44
  38. 2022Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationcited by 43

50 most cited of 691 All 691 (JSON)