mlsanityData to 14 Oct 2026

Dynamics-Aware Loss for Learning with Label Noise

arXiv 2303.11562 ↗First posted 21 Mar 2023cs.LGcited by 9

Not on the map. Why?

Abstract (arXiv)

Label noise poses a serious threat to deep neural networks (DNNs). Employing robust loss functions which reconcile fitting ability with robustness is a simple but effective strategy to handle this problem. However, the widely-used static trade-off between these two factors contradicts the dynamics of DNNs learning with label noise, leading to inferior performance. Therefore, we propose a dynamics-aware loss (DAL) to solve this problem. Considering that DNNs tend to first learn beneficial patterns, then gradually overfit harmful label noise, DAL strengthens the fitting ability initially, then gradually improves robustness. Moreover, at the later stage, to further reduce the negative impact of label noise and combat underfitting simultaneously, we let DNNs put more emphasis on easy examples than hard ones and introduce a bootstrapping term. Both the detailed theoretical analyses and extensive experimental results demonstrate the superiority of our method. Our source code can be found in https://github.com/XiuchuanLi/DAL.

Key facts. Cited by 9 papers in the map (data through 14 Oct 2026). Builds on 34 of its 47 references that are in the map. First posted on arXiv 21 Mar 2023.

Builds on

34 of 47 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  3. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  4. 2017A Closer Look at Memorization in Deep Networkscited by 942
  5. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  6. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  7. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  8. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  9. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  10. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  11. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  12. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
22 more
  1. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  2. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  3. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  4. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  5. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  6. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  7. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  8. 2022Robust Training under Label Noise by Over-parameterizationcited by 93
  9. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  10. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  11. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  12. 2022PolyLoss: A Polynomial Expansion Perspective of Classification Loss Functionscited by 63
  13. 2019Robust Bi-Tempered Logistic Loss Based on Bregman Divergencescited by 61
  14. 2021Asymmetric Loss Functions for Learning with Noisy Labelscited by 46
  15. 2021Learning with Noisy Labels via Sparse Regularizationcited by 39
  16. 2020ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networkscited by 33
  17. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  18. 2022Beyond Images: Label Noise Transition Matrix Estimation for Tasks with Lower-Quality Featurescited by 27
  19. 2021ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learningcited by 13
  20. 2021Tackling Instance-Dependent Label Noise via a Universal Probabilistic Modelcited by 12
  21. 2021Learning to Rectify for Robust Learning with Noisy Labelscited by 12
  22. 2021Constrained Instance and Class Reweighting for Robust Learning under Label Noisecited by 12

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 2; 2025: 5; 2026: 2.

9 papers.

  1. 2025Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlookcited by 3
  2. 2025Efficient Adaptive Label Refinement for Label Noise Learningcited by 2
  3. 2024Robust Learning under Hybrid Noisecited by 1
  4. 2025From Noisy Labels to Intrinsic Structure: A Geometric-Structural Dual-Guided Framework for Noise-Robust Medical Image Segmentationcited by 1
  5. 2024Bayesian uncertainty-aware deep learning with noisy labels: Tackling annotation ambiguity in EEG seizure detectioncited by 0
  6. 2025FANoise: Singular Value-Adaptive Noise Modulation for Robust Multimodal Representation Learningcited by 0
  7. 2025Dual-level Modality Debiasing Learning for Unsupervised Visible-Infrared Person Re-Identificationcited by 0
  8. 2026Noise-Robust Tiny Object Localization with Flowscited by 0
  9. 2026Planning to Learncited by 0