mlsanityData to 14 Oct 2026

Instance-dependent Label Distribution Estimation for Learning with Label Noise

arXiv 2212.08380 ↗First posted 16 Dec 2022cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

Noise transition matrix (NTM) estimation is a promising approach for learning with label noise. It can infer clean posterior probabilities, known as Label Distribution (LD), based on noisy ones and reduce the impact of noisy labels. However, this estimation is challenging, since the ground truth labels are not always available. Most existing methods estimate a global NTM using either correctly labeled samples (anchor points) or detected reliable samples (pseudo anchor points). These methods heavily rely on the existence of anchor points or the quality of pseudo ones, and the global NTM can hardly provide accurate label transition information for each sample, since the label noise in real applications is mostly instance-dependent. To address these challenges, we propose an Instance-dependent Label Distribution Estimation (ILDE) method to learn from noisy labels for image classification. The method's workflow has three major steps. First, we estimate each sample's noisy posterior probability, supervised by noisy labels. Second, since mislabeling probability closely correlates with inter-class correlation, we compute the inter-class correlation matrix to estimate the NTM, bypassing the need for (pseudo) anchor points. Moreover, for a precise approximation of the instance-dependent NTM, we calculate the inter-class correlation matrix using only mini-batch samples rather than the entire training dataset. Third, we transform the noisy posterior probability into instance-dependent LD by multiplying it with the estimated NTM, using the resulting LD for enhanced supervision to prevent DCNNs from memorizing noisy labels. The proposed ILDE method has been evaluated against several state-of-the-art methods on two synthetic and three real-world noisy datasets. Our results indicate that the proposed ILDE method outperforms all competing methods, no matter whether the noise is synthetic or real noise.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 38 of its 58 references that are in the map. First posted on arXiv 16 Dec 2022.

Builds on

38 of 58 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  3. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  4. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  5. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 997
  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. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  9. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 582
  10. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 500
  11. 2017Robust Loss Functions under Label Noise for Deep Neural Networkscited by 443
  12. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
26 more
  1. 2020Are we done with ImageNet?cited by 333
  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. 2021A Survey on Deep Semi-supervised Learningcited by 251
  5. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  6. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  7. 2019Deep learning with noisy labels: exploring techniques and remedies in medical image analysiscited by 173
  8. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  9. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  10. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  11. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  12. 2019Image Classification with Deep Learning in the Presence of Noisy Labels: A Surveycited by 101
  13. 2017Learning with Biased Complementary Labelscited by 93
  14. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 88
  15. 2019Combating Label Noise in Deep Learning Using Abstentioncited by 86
  16. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  17. 2021To Smooth or Not? When Label Smoothing Meets Noisy Labelscited by 70
  18. 2020Confidence Scores Make Instance-dependent Label-noise Learning Possiblecited by 63
  19. 2020Semi-supervised Medical Image Classification with Relation-driven Self-ensembling Modelcited by 59
  20. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  21. 2021Asymmetric Loss Functions for Learning with Noisy Labelscited by 46
  22. 2021Learning with Noisy Labels via Sparse Regularizationcited by 39
  23. 2022Uncertainty-Aware Learning Against Label Noise on Imbalanced Datasetscited by 28
  24. 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
  25. 2020Meta Transition Adaptation for Robust Deep Learning with Noisy Labelscited by 17
  26. 2022Scalable Penalized Regression for Noise Detection in Learning with Noisy Labelscited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 1; 2026: 8.

10 papers.

  1. 2026CausalRM: Causal-Theoretic Reward Modeling for RLHF from Observational User Feedbackscited by 7
  2. 2025Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlookcited by 3
  3. 2026ImplicitRM: Unbiased Reward Modeling from Implicit Preference Data for LLM alignmentcited by 3
  4. 2026Optimal Transport for LLM Reward Modeling from Noisy Preferencecited by 3
  5. 2024Unleashing the Potential of Open-set Noisy Samples Against Label Noise for Medical Image Classificationcited by 1
  6. 2026MOLAR: Learning Multimodal Molecular Representations from Noisy Labelscited by 1
  7. 2026DREAM: Dual-Standard Semantic Homogeneity with Dynamic Optimization for Graph Learning with Label Noisecited by 0
  8. 2026GAMR: Geometric-Aware Manifold Regularization with Virtual Outlier Synthesis for Learning with Noisy Labelscited by 0
  9. 2026Beyond Performance Metrics: Uncertainty Mapping of Label Ambiguity in Fazekas Score Predictioncited by 0
  10. 2026Noise2Match: Self-Supervised Low-Dose CT Denoising via Adaptive Inter-Slice Matchingcited by 0