mlsanityData to 14 Oct 2026

Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning

arXiv 2403.02690 ↗First posted 5 Mar 2024cs.LG cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

For learning with noisy labels, the transition matrix, which explicitly models the relation between noisy label distribution and clean label distribution, has been utilized to achieve the statistical consistency of either the classifier or the risk. Previous researches have focused more on how to estimate this transition matrix well, rather than how to utilize it. We propose good utilization of the transition matrix is crucial and suggest a new utilization method based on resampling, coined RENT. Specifically, we first demonstrate current utilizations can have potential limitations for implementation. As an extension to Reweighting, we suggest the Dirichlet distribution-based per-sample Weight Sampling (DWS) framework, and compare reweighting and resampling under DWS framework. With the analyses from DWS, we propose RENT, a REsampling method with Noise Transition matrix. Empirically, RENT consistently outperforms existing transition matrix utilization methods, which includes reweighting, on various benchmark datasets. Our code is available at urlhttps://github.com/BaeHeeSun/RENT.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 41 of its 58 references that are in the map. First posted on arXiv 5 Mar 2024.

Builds on

41 of 58 references.

References · 41

  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. 2019Learning Imbalanced Datasets with Label-Distribution-Aware Margin Losscited by 989
  5. 2017A Closer Look at Memorization in Deep Networkscited by 942
  6. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  7. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  8. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  9. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  10. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  11. 2018Not All Samples Are Created Equal: Deep Learning with Importance Samplingcited by 328
  12. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
29 more
  1. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  2. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  3. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 256
  4. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  5. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  6. 2015Adding Gradient Noise Improves Learning for Very Deep Networkscited by 145
  7. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  8. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  9. 2021FINE Samples for Learning with Noisy Labelscited by 82
  10. 2020Error-Bounded Correction of Noisy Labelscited by 74
  11. 2019Robust Inference via Generative Classifiers for Handling Noisy Labelscited by 68
  12. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  13. 2020Confidence Scores Make Instance-dependent Label-noise Learning Possiblecited by 63
  14. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  15. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 59
  16. 2021Detecting Corrupted Labels Without Training a Model to Predictcited by 58
  17. 2020Deep k-NN for Noisy Labelscited by 55
  18. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  19. 2020Why resampling outperforms reweighting for correcting sampling bias with stochastic gradientscited by 34
  20. 2022Identifiability of Label Noise Transition Matrixcited by 34
  21. 2020ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networkscited by 33
  22. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  23. 2022Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasetscited by 28
  24. 2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 22
  25. 2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
  26. 2020Combined Cleaning and Resampling Algorithm for Multi-Class Imbalanced Data with Label Noisecited by 18
  27. 2024Label-Noise Robust Diffusion Modelscited by 16
  28. 2019Generalization Bounds for Neural Networks via Approximate Description Lengthcited by 15
  29. 2022Do We Need to Penalize Variance of Losses for Learning with Label Noise?cited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Robust Classification with Noisy Labels Based on Posterior Maximizationcited by 2
  2. 2025Learning to Forget with Information Divergence Reweighted Objectives for Noisy Labelscited by 0
  3. 2025Revisiting Meta-Learning with Noisy Labels: Reweighting Dynamics and Theoretical Guaranteescited by 0
  4. 2026On Revisiting Entropy for Identifying Mislabeled Imagescited by 0