mlsanityData to 7 Oct 2026

Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation

arXiv 2305.19486 ↗First posted 31 May 2023cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep learning faces a formidable challenge when handling noisy labels, as models tend to overfit samples affected by label noise. This challenge is further compounded by the presence of instance-dependent noise (IDN), a realistic form of label noise arising from ambiguous sample information. To address IDN, Label Noise Learning (LNL) incorporates a sample selection stage to differentiate clean and noisy-label samples. This stage uses an arbitrary criterion and a pre-defined curriculum that initially selects most samples as noisy and gradually decreases this selection rate during training. Such curriculum is sub-optimal since it does not consider the actual label noise rate in the training set. This paper addresses this issue with a new noise-rate estimation method that is easily integrated with most state-of-the-art (SOTA) LNL methods to produce a more effective curriculum. Synthetic and real-world benchmark results demonstrate that integrating our approach with SOTA LNL methods improves accuracy in most cases.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 43 of its 61 references that are in the map. First posted on arXiv 31 May 2023.

Builds on

43 of 61 references.

References · 43

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2020Supervised Contrastive Learningcited by 2,803
  5. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  6. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  7. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  8. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  9. 2017A Closer Look at Memorization in Deep Networkscited by 936
  10. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  11. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  12. 2017Exploring Generalization in Deep Learningcited by 595
31 more
  1. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  2. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  3. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  4. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  5. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  6. 2022Transformers in Medical Imaging: A Surveycited by 245
  7. 2017Decoupling "when to update" from "how to update"cited by 230
  8. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  9. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  10. 2020A Second-Order Approach to Learning with Instance-Dependent Label Noisecited by 90
  11. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  12. 2020Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noisecited by 82
  13. 2021FINE Samples for Learning with Noisy Labelscited by 82
  14. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  15. 2021Learning Fast Sample Re-weighting Without Reward Datacited by 69
  16. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  17. 2021Instance-dependent Label-noise Learning under a Structural Causal Modelcited by 50
  18. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  19. 2021Faster Meta Update Strategy for Noise-Robust Deep Learningcited by 38
  20. 2022Identifiability of Label Noise Transition Matrixcited by 34
  21. 2021Estimating Instance-dependent Bayes-label Transition Matrix using a Deep Neural Networkcited by 30
  22. 2022Neighborhood Collective Estimation for Noisy Label Identification and Correctioncited by 22
  23. 2022From Noisy Prediction to True Label: Noisy Prediction Calibration via Generative Modelcited by 21
  24. 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
  25. 2021PropMix: Hard Sample Filtering and Proportional MixUp for Learning with Noisy Labelscited by 17
  26. 2022Instance-Dependent Noisy Label Learning via Graphical Modellingcited by 17
  27. 2022Unsupervised Image-to-Image Translation with Generative Priorcited by 16
  28. 2022Centrality and Consistency: Two-Stage Clean Samples Identification for Learning with Instance-Dependent Noisy Labelscited by 16
  29. 2021SSR: An Efficient and Robust Framework for Learning with Unknown Label Noisecited by 13
  30. 2022Bootstrapping the Relationship Between Images and Their Clean and Noisy Labelscited by 7
  31. 2022DebtFree: Minimizing Labeling Cost in Self-Admitted Technical Debt Identification using Semi-Supervised Learningcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 0; 2026: 3.

4 papers.

  1. 2024Co-Supervised Learning: Improving Weak-to-Strong Generalization with Hierarchical Mixture of Expertscited by 28
  2. 2026L2CU: Learning to Complement Unseen Userscited by 2
  3. 2026Combating Noisy Labels through Fostering Self- and Neighbor-Consistencycited by 0
  4. 2026Robust Multi-View Classification under Noisy Supervision via Global Anchor Consensuscited by 0