mlsanityData to 7 Oct 2026

Instance-Dependent Noisy Label Learning via Graphical Modelling

arXiv 2209.00906 ↗First posted 2 Sep 2022cs.CV cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Noisy labels are unavoidable yet troublesome in the ecosystem of deep learning because models can easily overfit them. There are many types of label noise, such as symmetric, asymmetric and instance-dependent noise (IDN), with IDN being the only type that depends on image information. Such dependence on image information makes IDN a critical type of label noise to study, given that labelling mistakes are caused in large part by insufficient or ambiguous information about the visual classes present in images. Aiming to provide an effective technique to address IDN, we present a new graphical modelling approach called InstanceGM, that combines discriminative and generative models. The main contributions of InstanceGM are: i) the use of the continuous Bernoulli distribution to train the generative model, offering significant training advantages, and ii) the exploration of a state-of-the-art noisy-label discriminative classifier to generate clean labels from instance-dependent noisy-label samples. InstanceGM is competitive with current noisy-label learning approaches, particularly in IDN benchmarks using synthetic and real-world datasets, where our method shows better accuracy than the competitors in most experiments.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 62 of its 75 references that are in the map. First posted on arXiv 2 Sep 2022.

Builds on

62 of 75 references.

References · 62

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  7. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  8. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  9. 2013Auto-Encoding Variational Bayescited by 3,980
  10. 2022A ConvNet for the 2020scited by 3,545
  11. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,845
  12. 2016Identity Mappings in Deep Residual Networkscited by 1,960
38 more
  1. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  2. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  3. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  4. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  5. 2017A Closer Look at Memorization in Deep Networkscited by 936
  6. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  7. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  8. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  9. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  10. 2017Exploring Generalization in Deep Learningcited by 595
  11. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  12. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  13. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  14. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  15. 2017Decoupling "when to update" from "how to update"cited by 230
  16. 2018Using Trusted Data to Train Deep Networks on Labels Corrupted by Severe Noisecited by 216
  17. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  18. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  19. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  20. 2019Deep Self-Learning From Noisy Labelscited by 122
  21. 2017Learning From Noisy Large-Scale Datasets With Minimal Supervisioncited by 115
  22. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  23. 20213D Object Detection for Autonomous Driving: A Surveycited by 106
  24. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  25. 2018Masking: A New Perspective of Noisy Supervisioncited by 93
  26. 2020A Second-Order Approach to Learning with Instance-Dependent Label Noisecited by 90
  27. 2021FINE Samples for Learning with Noisy Labelscited by 82
  28. 2021Sample Selection with Uncertainty of Losses for Learning with Noisy Labelscited by 79
  29. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  30. 2021Clusterability as an Alternative to Anchor Points When Learning with Noisy Labelscited by 65
  31. 2020Confidence Scores Make Instance-dependent Label-noise Learning Possiblecited by 63
  32. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  33. 2021Open-set Label Noise Can Improve Robustness Against Inherent Label Noisecited by 58
  34. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  35. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  36. 2018Deep Bilevel Learningcited by 48
  37. 2021Active label cleaning for improved dataset quality under resource constraintscited by 44
  38. 2019How does Early Stopping Help Generalization against Label Noise?cited by 41

50 most cited of 62 All 62 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 6; 2024: 7; 2025: 2; 2026: 2.

17 papers.

Sort:

  1. 2024CLIPCleaner: Cleaning Noisy Labels with CLIPcited by 16
  2. 2024Estimating Noisy Class Posterior with Part-level Labels for Noisy Label Learningcited by 7
  3. 2024Learning to Complement and to Defer to Multiple Userscited by 7
  4. 2023Combating Label Noise With A General Surrogate Model For Sample Selectioncited by 6
  5. 2023Learning to Complement with Multiple Humanscited by 5
  6. 2025Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimizationcited by 5
  7. 2025SelectMix: Enhancing Label Noise Robustness through Targeted Sample Mixingcited by 5
  8. 2023Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimationcited by 4
  9. 2024Learning with Noisy Labels: Interconnection of Two Expectation-Maximizationscited by 4
  10. 2024From Biased Selective Labels to Pseudo-Labels: An Expectation-Maximization Framework for Learning from Biased Decisionscited by 4
  11. 2024ANNE: Adaptive Nearest Neighbors and Eigenvector-based Sample Selection for Robust Learning with Noisy Labelscited by 3
  12. 2023Asymmetric Co-teaching with Multi-view Consensus for Noisy Label Learningcited by 1
5 more
  1. 2023PASS: Peer-Agreement based Sample Selection for training with Noisy Labelscited by 1
  2. 2023Bridging Generative and Discriminative Noisy-Label Learning via Direction-Agnostic EM Formulationcited by 1
  3. 2024NoisyAG-News: A Benchmark for Addressing Instance-Dependent Noise in Text Classificationcited by 1
  4. 2026SLT: Robust Quantum Neural Networks for Noisy-Label Medical Image Classification via Supermartingale-based Label Transitioncited by 0
  5. 2026Particle Competition and Cooperation for Robust Graph Convolutional Network Learning Under Label Noisecited by 0