mlsanityData to 7 Oct 2026

SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labels

arXiv 2205.01156 ↗First posted 2 May 2022cs.CV cs.LGcited by 24

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are prone to overfitting noisy labels, resulting in poor generalization performance. To overcome this problem, we present a simple and effective method self-ensemble label correction (SELC) to progressively correct noisy labels and refine the model. We look deeper into the memorization behavior in training with noisy labels and observe that the network outputs are reliable in the early stage. To retain this reliable knowledge, SELC uses ensemble predictions formed by an exponential moving average of network outputs to update the original noisy labels. We show that training with SELC refines the model by gradually reducing supervision from noisy labels and increasing supervision from ensemble predictions. Despite its simplicity, compared with many state-of-the-art methods, SELC obtains more promising and stable results in the presence of class-conditional, instance-dependent, and real-world label noise. The code is available at https://github.com/MacLLL/SELC.

Key facts. Cited by 24 papers in the map (data through 7 Oct 2026). Builds on 31 of its 44 references that are in the map. First posted on arXiv 2 May 2022.

Builds on

31 of 44 references.

References · 31

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2015Rethinking the Inception Architecture for Computer Visioncited by 5,451
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2016Wide Residual Networkscited by 3,057
  5. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  6. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  7. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  8. 2017A Closer Look at Memorization in Deep Networkscited by 936
  9. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  10. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  11. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  12. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
19 more
  1. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  2. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  3. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  4. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  5. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  6. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  7. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  8. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  9. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  10. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  11. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  12. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  13. 2019Combating Label Noise in Deep Learning Using Abstentioncited by 86
  14. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  15. 2020Error-Bounded Correction of Noisy Labelscited by 74
  16. 2021Towards Understanding Deep Learning from Noisy Labels with Small-Loss Criterioncited by 36
  17. 2021Boosting Co-teaching with Compression Regularization for Label Noisecited by 31
  18. 2020Coresets for Robust Training of Neural Networks against Noisy Labelscited by 24
  19. 2021Confidence Adaptive Regularization for Deep Learning with Noisy Labelscited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 5; 2023: 4; 2024: 6; 2025: 5; 2026: 4.

24 papers.

Sort:

By area:

  1. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  2. 2025Early Stopping Against Label Noise Without Validation Datacited by 21
  3. 2022CrossSplit: Mitigating Label Noise Memorization through Data Splittingcited by 12
  4. 2023Practical Edge Detection via Robust Collaborative Learningcited by 12
  5. 2023Mitigating Label Noise through Data Ambiguationcited by 10
  6. 2024Foster Adaptivity and Balance in Learning with Noisy Labelscited by 9
  7. 2024Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selectioncited by 6
  8. 2023Compensation Learning in Semantic Segmentationcited by 5
  9. 2023Differences Between Hard and Noisy-labeled Samples: An Empirical Studycited by 4
  10. 2022Leveraging Unlabeled Data to Track Memorizationcited by 2
  11. 2024May the Forgetting Be with You: Alternate Replay for Learning with Noisy Labelscited by 2
  12. 2025Efficient Adaptive Label Refinement for Label Noise Learningcited by 2
12 more
  1. 2022Neighbour Consistency Guided Pseudo-Label Refinement for Unsupervised Person Re-Identificationcited by 1
  2. 2025Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shiftscited by 1
  3. 2022On Robust Learning from Noisy Labels: A Permutation Layer Approachcited by 0
  4. 2024Group Benefits Instances Selection for Data Purificationcited by 0
  5. 2024Mitigating Noisy Supervision Using Synthetic Samples with Soft Labelscited by 0
  6. 2024SSP-RACL: Classification of Noisy Fundus Images with Self-Supervised Pretraining and Robust Adaptive Credal Losscited by 0
  7. 2025Dynamical Label Augmentation and Calibration for Noisy Electronic Health Recordscited by 0
  8. 2025PEdger++: Practical Edge Detection via Assembling Cross Informationcited by 0
  9. 2026Noise-aware few-shot learning through bi-directional multi-view prompt alignmentcited by 0
  10. 2026Noise-Aware Framework for Correcting Corrupted Labelscited by 0
  11. 2026XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Spacecited by 0
  12. 2026PaSta: Noisy Node Classification with Partial Label Learningcited by 0