mlsanityData to 7 Oct 2026

Learning with Feature-Dependent Label Noise: A Progressive Approach

arXiv 2103.07756 ↗First posted 13 Mar 2021cs.LG cs.CV stat.APcited by 102

Not on the map. Why?

Abstract (arXiv)

Label noise is frequently observed in real-world large-scale datasets. The noise is introduced due to a variety of reasons; it is heterogeneous and feature-dependent. Most existing approaches to handling noisy labels fall into two categories: they either assume an ideal feature-independent noise, or remain heuristic without theoretical guarantees. In this paper, we propose to target a new family of feature-dependent label noise, which is much more general than commonly used i.i.d. label noise and encompasses a broad spectrum of noise patterns. Focusing on this general noise family, we propose a progressive label correction algorithm that iteratively corrects labels and refines the model. We provide theoretical guarantees showing that for a wide variety of (unknown) noise patterns, a classifier trained with this strategy converges to be consistent with the Bayes classifier. In experiments, our method outperforms SOTA baselines and is robust to various noise types and levels.

Key facts. Cited by 102 papers in the map (data through 7 Oct 2026). Builds on 32 of its 49 references that are in the map. First posted on arXiv 13 Mar 2021.

Builds on

32 of 49 references.

References · 32

  1. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  2. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  3. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  4. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  5. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  6. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  7. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  8. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 441
  9. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  10. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  11. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  12. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
20 more
  1. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  2. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  3. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  4. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  5. 2017Learning from Noisy Labels with Distillationcited by 160
  6. 2018Learning to Learn from Noisy Labeled Datacited by 160
  7. 2015Learning with Symmetric Label Noise: The Importance of Being Unhingedcited by 120
  8. 2017Learning From Noisy Large-Scale Datasets With Minimal Supervisioncited by 115
  9. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  10. 2019Combating Label Noise in Deep Learning Using Abstentioncited by 86
  11. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  12. 2017Toward Robustness against Label Noise in Training Deep Discriminative Neural Networkscited by 78
  13. 2020A Topological Filter for Learning with Label Noisecited by 76
  14. 2020Error-Bounded Correction of Noisy Labelscited by 74
  15. 2018A Topological Regularizer for Classifiers via Persistent Homologycited by 62
  16. 2019Robust Bi-Tempered Logistic Loss Based on Bregman Divergencescited by 61
  17. 2017Learning with Bounded Instance- and Label-dependent Label Noisecited by 57
  18. 2014Making Risk Minimization Tolerant to Label Noisecited by 54
  19. 2019On Symmetric Losses for Learning from Corrupted Labelscited by 53
  20. 2017Two-temperature logistic regression based on the Tsallis divergencecited by 14

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 22; 2022: 26; 2023: 19; 2024: 18; 2025: 10; 2026: 7.

102 papers.

Sort:

By area:

  1. 2021Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotationscited by 253
  2. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  3. 2021Survey of Low-Resource Machine Translationcited by 92
  4. 2022UNICON: Combating Label Noise Through Uniform Selection and Contrastive Learningcited by 77
  5. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  6. 2021Detecting Corrupted Labels Without Training a Model to Predictcited by 57
  7. 2021Co-learning: Learning from Noisy Labels with Self-supervisioncited by 50
  8. 2021Instance-Dependent Partial Label Learningcited by 49
  9. 2023C-SFDA: A Curriculum Learning Aided Self-Training Framework for Efficient Source Free Domain Adaptationcited by 49
  10. 2022ProMix: Combating Label Noise via Maximizing Clean Sample Utilitycited by 48
  11. 2023When Source-Free Domain Adaptation Meets Learning with Noisy Labelscited by 46
  12. 2021Multilingual Machine Translation Systems from Microsoft for WMT21 Shared Taskcited by 34
38 more
  1. 2021Boosting Co-teaching with Compression Regularization for Label Noisecited by 31
  2. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  3. 2022CMW-Net: Learning a Class-Aware Sample Weighting Mapping for Robust Deep Learningcited by 24
  4. 2022SELC: Self-Ensemble Label Correction Improves Learning with Noisy Labelscited by 24
  5. 2022Progressive Purification for Instance-Dependent Partial Label Learningcited by 23
  6. 2022Freeze then Train: Towards Provable Representation Learning under Spurious Correlations and Feature Noisecited by 22
  7. 2022On Learning Contrastive Representations for Learning with Noisy Labelscited by 21
  8. 2022Jigsaw-ViT: Learning Jigsaw Puzzles in Vision Transformercited by 21
  9. 2022When Noisy Labels Meet Long Tail Dilemmas: A Representation Calibration Methodcited by 21
  10. 2021Adaptive Sample Selection for Robust Learning under Label Noisecited by 20
  11. 2023Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labelscited by 20
  12. 2021Two Wrongs Don't Make a Right: Combating Confirmation Bias in Learning with Label Noisecited by 18
  13. 2022Instance-Dependent Noisy Label Learning via Graphical Modellingcited by 17
  14. 2023BadLabel: A Robust Perspective on Evaluating and Enhancing Label-noise Learningcited by 16
  15. 2023Learning to Segment from Noisy Annotations: A Spatial Correction Approachcited by 16
  16. 2024CLIPCleaner: Cleaning Noisy Labels with CLIPcited by 16
  17. 2022Scalable Penalized Regression for Noise Detection in Learning with Noisy Labelscited by 15
  18. 2021An Instance-Dependent Simulation Framework for Learning with Label Noisecited by 14
  19. 2021ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learningcited by 13
  20. 2021SSR: An Efficient and Robust Framework for Learning with Unknown Label Noisecited by 13
  21. 2023InstanT: Semi-supervised Learning with Instance-dependent Thresholdscited by 13
  22. 2021Learning to Rectify for Robust Learning with Noisy Labelscited by 12
  23. 2022CrossSplit: Mitigating Label Noise Memorization through Data Splittingcited by 12
  24. 2022Is your noise correction noisy? PLS: Robustness to label noise with two stage detectioncited by 11
  25. 2023Learning with Noisy labels via Self-supervised Adversarial Noisy Maskingcited by 10
  26. 2023Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learningcited by 8
  27. 2023Regularly Truncated M-estimators for Learning with Noisy Labelscited by 8
  28. 2024SURE: SUrvey REcipes for building reliable and robust deep networkscited by 8
  29. 2024Noisy Label Processing for Classification: A Surveycited by 8
  30. 2021Instance Correction for Learning with Open-set Noisy Labelscited by 7
  31. 2022Noise-Tolerant Learning for Audio-Visual Action Recognitioncited by 7
  32. 2022Compressing Features for Learning with Noisy Labelscited by 7
  33. 2022Bootstrapping the Relationship Between Images and Their Clean and Noisy Labelscited by 7
  34. 2022Dynamic Loss For Robust Learningcited by 6
  35. 2024Learning Linear Utility Functions From Pairwise Comparison Queriescited by 6
  36. 2022ProSelfLC: Progressive Self Label Correction Towards A Low-Temperature Entropy Statecited by 5
  37. 2023Algorithmic Censoring in Dynamic Learning Systemscited by 5
  38. 2021Rethinking Noisy Label Models: Labeler-Dependent Noise with Adversarial Awarenesscited by 4

50 most cited of 102 All 102 (JSON)