mlsanityData to 7 Oct 2026

Learning with Noisy Labels: Interconnection of Two Expectation-Maximizations

arXiv 2401.04390 ↗First posted 9 Jan 2024cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

Labor-intensive labeling becomes a bottleneck in developing computer vision algorithms based on deep learning. For this reason, dealing with imperfect labels has increasingly gained attention and has become an active field of study. We address learning with noisy labels (LNL) problem, which is formalized as a task of finding a structured manifold in the midst of noisy data. In this framework, we provide a proper objective function and an optimization algorithm based on two expectation-maximization (EM) cycles. The separate networks associated with the two EM cycles collaborate to optimize the objective function, where one model is for distinguishing clean labels from corrupted ones while the other is for refurbishing the corrupted labels. This approach results in a non-collapsing LNL-flywheel model in the end. Experiments show that our algorithm achieves state-of-the-art performance in multiple standard benchmarks with substantial margins under various types of label noise.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 45 of its 60 references that are in the map. First posted on arXiv 9 Jan 2024.

Builds on

45 of 60 references.

References · 45

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  4. 2022Generative Adversarial Networkscited by 5,603
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 4,993
  7. 2020Supervised Contrastive Learningcited by 2,803
  8. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,261
  9. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  10. 2016Inception-v4, Inception-ResNet and the Impact of Residual Connections on Learningcited by 1,509
  11. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  12. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
33 more
  1. 2017A Closer Look at Memorization in Deep Networkscited by 936
  2. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 663
  3. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 652
  4. 2020Learning from Noisy Labels with Deep Neural Networks: A Surveycited by 580
  5. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  6. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  7. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  8. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  9. 2020Combating noisy labels by agreement: A joint training method with co-regularizationcited by 289
  10. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  11. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  12. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  13. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  14. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  15. 2020Learning with Instance-Dependent Label Noise: A Sample Sieve Approachcited by 158
  16. 2017Active Bias: Training More Accurate Neural Networks by Emphasizing High Variance Samplescited by 147
  17. 2019Peer Loss Functions: Learning from Noisy Labels without Knowing Noise Ratescited by 142
  18. 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
  19. 2021Understanding and Improving Early Stopping for Learning with Noisy Labelscited by 112
  20. 2022Selective-Supervised Contrastive Learning with Noisy Labelscited by 112
  21. 2018Iterative Learning with Open-set Noisy Labelscited by 108
  22. 2020A Second-Order Approach to Learning with Instance-Dependent Label Noisecited by 90
  23. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  24. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  25. 2020Error-Bounded Correction of Noisy Labelscited by 74
  26. 2021NGC: A Unified Framework for Learning with Open-World Noisy Datacited by 58
  27. 2022Instance-Dependent Label-Noise Learning with Manifold-Regularized Transition Matrix Estimationcited by 49
  28. 2015The Unreasonable Effectiveness of Noisy Data for Fine-Grained Recognitioncited by 48
  29. 2020Why resampling outperforms reweighting for correcting sampling bias with stochastic gradientscited by 34
  30. 2021Joint Negative and Positive Learning for Noisy Labelscited by 34
  31. 2022Self-Filtering: A Noise-Aware Sample Selection for Label Noise with Confidence Penalizationcited by 33
  32. 2022Instance-Dependent Noisy Label Learning via Graphical Modellingcited by 17
  33. 2020Noisy Concurrent Training for Efficient Learning under Label Noisecited by 13

Built on by

Cited by year

Citing papers per year: 2024: 2; 2025: 2.

4 papers.

  1. 2024Noisy Early Stopping for Noisy Labelscited by 1
  2. 2024An accurate detection is not all you need to combat label noise in web-noisy datasetscited by 0
  3. 2025Bridging Weakly-Supervised Learning and VLM Distillation: Noisy Partial Label Learning for Efficient Downstream Adaptationcited by 0
  4. 2025MANTRA: a Framework for Multi-stage Adaptive Noise TReAtment During Trainingcited by 0