mlsanityData to 7 Oct 2026

Joint Optimization Framework for Learning with Noisy Labels

arXiv 1803.11364 ↗First posted 30 Mar 2018cs.CV cs.LG stat.MLcited by 293

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) trained on large-scale datasets have exhibited significant performance in image classification. Many large-scale datasets are collected from websites, however they tend to contain inaccurate labels that are termed as noisy labels. Training on such noisy labeled datasets causes performance degradation because DNNs easily overfit to noisy labels. To overcome this problem, we propose a joint optimization framework of learning DNN parameters and estimating true labels. Our framework can correct labels during training by alternating update of network parameters and labels. We conduct experiments on the noisy CIFAR-10 datasets and the Clothing1M dataset. The results indicate that our approach significantly outperforms other state-of-the-art methods.

Key facts. Cited by 293 papers in the map (data through 7 Oct 2026). First posted on arXiv 30 Mar 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 79; 2022: 76; 2023: 48; 2024: 49; 2025: 31; 2026: 10.

293 papers.

Sort:

By area:

  1. 2021Open-World Semi-Supervised Learningcited by 165
  2. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  3. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  4. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  5. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  6. 2022Robust Training under Label Noise by Over-parameterizationcited by 93
  7. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  8. 2021Breaking the Dilemma of Medical Image-to-image Translationcited by 82
  9. 2021Jo-SRC: A Contrastive Approach for Combating Noisy Labelscited by 80
  10. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  11. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  12. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
38 more
  1. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  2. 2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
  3. 2021Adaptive Early-Learning Correction for Segmentation from Noisy Annotationscited by 61
  4. 2022FedCorr: Multi-Stage Federated Learning for Label Noise Correctioncited by 61
  5. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  6. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  7. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  8. 2021Co-learning: Learning from Noisy Labels with Self-supervisioncited by 50
  9. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  10. 2021Hard Sample Aware Noise Robust Learning for Histopathology Image Classificationcited by 48
  11. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  12. 2022Investigating Why Contrastive Learning Benefits Robustness Against Label Noisecited by 46
  13. 2022Mitigating Memorization of Noisy Labels by Clipping the Model Predictioncited by 40
  14. 2021Faster Meta Update Strategy for Noise-Robust Deep Learningcited by 38
  15. 2022Large Loss Matters in Weakly Supervised Multi-Label Classificationcited by 38
  16. 2021Contrastive Learning Improves Model Robustness Under Label Noisecited by 36
  17. 2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
  18. 2021Joint Negative and Positive Learning for Noisy Labelscited by 34
  19. 2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
  20. 2021Boosting Co-teaching with Compression Regularization for Label Noisecited by 31
  21. 2022Refign: Align and Refine for Adaptation of Semantic Segmentation to Adverse Conditionscited by 31
  22. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  23. 2022Uncertainty-aware Label Distribution Learning for Facial Expression Recognitioncited by 30
  24. 2022Joint-Modal Label Denoising for Weakly-Supervised Audio-Visual Video Parsingcited by 29
  25. 2021Uncertainty Estimation via Response Scaling for Pseudo-mask Noise Mitigation in Weakly-supervised Semantic Segmentationcited by 28
  26. 2022Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasetscited by 28
  27. 2023Twin Contrastive Learning with Noisy Labelscited by 28
  28. 2024Vision Superalignment: Weak-to-Strong Generalization for Vision Foundation Modelscited by 28
  29. 2021Continual Learning on Noisy Data Streams via Self-Purified Replaycited by 27
  30. 2023BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistencycited by 27
  31. 2022Towards Federated Learning against Noisy Labels via Local Self-Regularizationcited by 26
  32. 2023Semi-Supervised Domain Adaptation with Source Label Adaptationcited by 26
  33. 2022SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labelscited by 24
  34. 2023Noise-Robust Fine-Tuning of Pretrained Language Models via External Guidancecited by 24
  35. 2022Neighborhood Collective Estimation for Noisy Label Identification and Correctioncited by 22
  36. 2022Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noisecited by 22
  37. 2023LION: Implicit Vision Prompt Tuningcited by 22
  38. 2023Cross-modal Active Complementary Learning with Self-refining Correspondencecited by 22

50 most cited of 293 All 293 (JSON)