mlsanityData to 14 Oct 2026

Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Network

arXiv 2105.13001 ↗First posted 27 May 2021cs.LGcited by 30

Not on the map. Why?

Abstract (arXiv)

In label-noise learning, estimating the transition matrix is a hot topic as the matrix plays an important role in building statistically consistent classifiers. Traditionally, the transition from clean labels to noisy labels (i.e., clean-label transition matrix (CLTM)) has been widely exploited to learn a clean label classifier by employing the noisy data. Motivated by that classifiers mostly output Bayes optimal labels for prediction, in this paper, we study to directly model the transition from Bayes optimal labels to noisy labels (i.e., Bayes-label transition matrix (BLTM)) and learn a classifier to predict Bayes optimal labels. Note that given only noisy data, it is ill-posed to estimate either the CLTM or the BLTM. But favorably, Bayes optimal labels have less uncertainty compared with the clean labels, i.e., the class posteriors of Bayes optimal labels are one-hot vectors while those of clean labels are not. This enables two advantages to estimate the BLTM, i.e., (a) a set of examples with theoretically guaranteed Bayes optimal labels can be collected out of noisy data; (b) the feasible solution space is much smaller. By exploiting the advantages, we estimate the BLTM parametrically by employing a deep neural network, leading to better generalization and superior classification performance.

Key facts. Cited by 30 papers in the map (data through 14 Oct 2026). Builds on 44 of its 65 references that are in the map. First posted on arXiv 27 May 2021.

Builds on

44 of 65 references.

References · 44

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  3. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  4. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  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. 2018Learning to Reweight Examples for Robust Deep Learningcited by 675
  8. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  9. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  10. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  11. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  12. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
32 more
  1. 2017Decoupling "when to update" from "how to update"cited by 230
  2. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  3. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  4. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  5. 2021Free Lunch for Few-shot Learning: Distribution Calibrationcited by 165
  6. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  7. 2017Learning from Noisy Labels with Distillationcited by 161
  8. 2019Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networkscited by 159
  9. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  10. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  11. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  12. 2018CurriculumNet: Weakly Supervised Learning from Large-Scale Web Imagescited by 126
  13. 2017Learning From Noisy Large-Scale Datasets With Minimal Supervisioncited by 115
  14. 2019Meta Label Correction for Noisy Label Learningcited by 108
  15. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  16. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  17. 2017Learning with Biased Complementary Labelscited by 93
  18. 2018Masking: A New Perspective of Noisy Supervisioncited by 93
  19. 2020A Second-Order Approach to Learning with Instance-Dependent Label Noisecited by 90
  20. 2019Curriculum Loss: Robust Learning and Generalization against Label Corruptioncited by 88
  21. 2017Toward Robustness against Label Noise in Training Deep Discriminative Neural Networkscited by 78
  22. 2020Error-Bounded Correction of Noisy Labelscited by 74
  23. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  24. 2020Confidence Scores Make Instance-dependent Label-noise Learning Possiblecited by 63
  25. 2017Learning with Bounded Instance- and Label-dependent Label Noisecited by 57
  26. 2017Learning with Confident Examples: Rank Pruning for Robust Classification with Noisy Labelscited by 52
  27. 2020Part-dependent Label Noise: Towards Instance-dependent Label Noisecited by 40
  28. 2017Algorithmic stability and hypothesis complexitycited by 39
  29. 2020ProSelfLC: Progressive Self Label Correction for Training Robust Deep Neural Networkscited by 33
  30. 2018Robustness of Conditional GANs to Noisy Labelscited by 27
  31. 2020Meta Transition Adaptation for Robust Deep Learning with Noisy Labelscited by 17
  32. 2017Transfer Learning with Label Noisecited by 4

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 12; 2024: 5; 2025: 7; 2026: 5.

30 papers.

Sort:

By area:

  1. 2023Towards Label-free Scene Understanding by Vision Foundation Modelscited by 54
  2. 2023BiCro: Noisy Correspondence Rectification for Multi-modality Data via Bi-directional Cross-modal Similarity Consistencycited by 27
  3. 2023Robust T-Loss for Medical Image Segmentationcited by 14
  4. 2023InstanT: Semi-supervised Learning with Instance-dependent Thresholdscited by 13
  5. 2023Transferring Annotator- and Instance-dependent Transition Matrix for Learning from Crowdscited by 11
  6. 2023Dynamics-Aware Loss for Learning with Label Noisecited by 9
  7. 2023Federated Learning with Instance-Dependent Noisy Labelcited by 9
  8. 2024Slight Corruption in Pre-training Data Makes Better Diffusion Modelscited by 9
  9. 2024Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learningcited by 7
  10. 2025Probabilistic Machine Learning for Noisy Labels in Earth Observationcited by 6
  11. 2023Collaborative Noisy Label Cleaner: Learning Scene-aware Trailers for Multi-modal Highlight Detection in Moviescited by 4
  12. 2023Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimationcited by 4
18 more
  1. 2024Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learningcited by 4
  2. 2022Do We Need to Penalize Variance of Losses for Learning with Label Noise?cited by 2
  3. 2023LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integrationcited by 2
  4. 2025Noise-Aware Generalization: Robustness to In-Domain Noise and Out-of-Domain Generalizationcited by 2
  5. 2025UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptationcited by 2
  6. 2023Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulationcited by 1
  7. 2024Mislabeled examples detection viewed as probing machine learning models: concepts, survey and extensive benchmarkcited by 1
  8. 2025Correcting Noisy Multilabel Predictions: Modeling Label Noise through Latent Space Shiftscited by 1
  9. 2025From Noisy Labels to Intrinsic Structure: A Geometric-Structural Dual-Guided Framework for Noise-Robust Medical Image Segmentationcited by 1
  10. 2023Rethinking the Value of Labels for Instance-Dependent Label Noise Learningcited by 0
  11. 2024EchoAlign: Bridging Generative and Discriminative Learning under Noisy Labelscited by 0
  12. 2025Corporate Fraud Detection in Rich-yet-Noisy Financial Graphcited by 0
  13. 2025Tackling the Noisy Elephant in the Room: Label Noise-robust Out-of-Distribution Detection via Loss Correction and Low-rank Decompositioncited by 0
  14. 2026Combating Noisy Labels through Fostering Self- and Neighbor-Consistencycited by 0
  15. 2026Model-agnostic information transfer and fusion for classification with label noisecited by 0
  16. 2026MIND: Decoupling Model-Induced Label Noise via Latent Manifold Disentanglementcited by 0
  17. 2026Learning Robust Recommenders from Noisy Implicit Feedback via GMM-Weighted Bayesian Transition Matrixcited by 0
  18. 2026SLT: Robust Quantum Neural Networks for Noisy-Label Medical Image Classification via Supermartingale-based Label Transitioncited by 0