mlsanityData to 7 Oct 2026

A Unified Framework for Connecting Noise Modeling to Boost Noise Detection

arXiv 2312.00827 ↗First posted 30 Nov 2023cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Noisy labels can impair model performance, making the study of learning with noisy labels an important topic. Two conventional approaches are noise modeling and noise detection. However, these two methods are typically studied independently, and there has been limited work on their collaboration. In this work, we explore the integration of these two approaches, proposing an interconnected structure with three crucial blocks: noise modeling, source knowledge identification, and enhanced noise detection using noise source-knowledge-integration methods. This collaboration structure offers advantages such as discriminating hard negatives and preserving genuinely clean labels that might be suspiciously noisy. Our experiments on four datasets, featuring three types of noise and different combinations of each block, demonstrate the efficacy of these components' collaboration. Our collaborative structure methods achieve up to a 10% increase in top-1 classification accuracy in synthesized noise datasets and 3-5% in real-world noisy datasets. The results also suggest that these components make distinct contributions to overall performance across various noise scenarios. These findings provide valuable insights for designing noisy label learning methods customized for specific noise scenarios in the future. Our code is accessible to the public.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 57 references that are in the map. First posted on arXiv 30 Nov 2023.

Builds on

35 of 57 references.

References · 35

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  3. 2022A ConvNet for the 2020scited by 3,545
  4. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  5. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  6. 2018Generalized Cross Entropy Loss for Training Deep Neural Networks with Noisy Labelscited by 994
  7. 2017A Closer Look at Memorization in Deep Networkscited by 936
  8. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
  9. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  10. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  11. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  12. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
23 more
  1. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  2. 2020Normalized Loss Functions for Deep Learning with Noisy Labelscited by 257
  3. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  4. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  5. 2019Gradient Descent with Early Stopping is Provably Robust to Label Noise for Overparameterized Neural Networkscited by 158
  6. 2020Dual T: Reducing Estimation Error for Transition Matrix in Label-noise Learningcited by 142
  7. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  8. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  9. 2021Provably End-to-end Label-Noise Learning without Anchor Pointscited by 97
  10. 2022Robust Training under Label Noise by Over-parameterizationcited by 93
  11. 2021FINE Samples for Learning with Noisy Labelscited by 82
  12. 2020A Topological Filter for Learning with Label Noisecited by 76
  13. 2021Learning Noise Transition Matrix from Only Noisy Labels via Total Variation Regularizationcited by 62
  14. 2022Learning with Neighbor Consistency for Noisy Labelscited by 55
  15. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  16. 2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
  17. 2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
  18. 2021Learning with Noisy Labels by Efficient Transition Matrix Estimation to Combat Label Miscorrectioncited by 20
  19. 2023CHAMMI: A benchmark for channel-adaptive models in microscopy imagingcited by 18
  20. 2016Embracing Error to Enable Rapid Crowdsourcingcited by 15
  21. 2020P-DIFF: Learning Classifier with Noisy Labels based on Probability Difference Distributionscited by 7
  22. 2022Label Noise-Robust Learning using a Confidence-Based Sieving Strategycited by 6
  23. 2023LNL+K: Enhancing Learning with Noisy Labels Through Noise Source Knowledge Integrationcited by 2

Built on by

Not cited yet.