mlsanityData to 14 Oct 2026

CoDiM: Learning with Noisy Labels via Contrastive Semi-Supervised Learning

arXiv 2111.11652 ↗First posted 23 Nov 2021cs.LG cs.CVcited by 3

Not on the map. Why?

Abstract (arXiv)

Labels are costly and sometimes unreliable. Noisy label learning, semi-supervised learning, and contrastive learning are three different strategies for designing learning processes requiring less annotation cost. Semi-supervised learning and contrastive learning have been recently demonstrated to improve learning strategies that address datasets with noisy labels. Still, the inner connections between these fields as well as the potential to combine their strengths together have only started to emerge. In this paper, we explore further ways and advantages to fuse them. Specifically, we propose CSSL, a unified Contrastive Semi-Supervised Learning algorithm, and CoDiM (Contrastive DivideMix), a novel algorithm for learning with noisy labels. CSSL leverages the power of classical semi-supervised learning and contrastive learning technologies and is further adapted to CoDiM, which learns robustly from multiple types and levels of label noise. We show that CoDiM brings consistent improvements and achieves state-of-the-art results on multiple benchmarks.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 38 of its 48 references that are in the map. First posted on arXiv 23 Nov 2021.

Builds on

38 of 48 references.

References · 38

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  3. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  8. 2020Supervised Contrastive Learningcited by 2,829
  9. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,287
  10. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  11. 2016Understanding deep learning requires rethinking generalizationcited by 1,674
  12. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
26 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  2. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  3. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,059
  4. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 692
  5. 2016Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approachcited by 665
  6. 2017MentorNet: Learning Data-Driven Curriculum for Very Deep Neural Networks on Corrupted Labelscited by 653
  7. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 416
  8. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  9. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 328
  10. 2014Training Deep Neural Networks on Noisy Labels with Bootstrappingcited by 322
  11. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  12. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  13. 2017Decoupling "when to update" from "how to update"cited by 230
  14. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  15. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  16. 2020Theoretical Analysis of Self-Training with Deep Networks on Unlabeled Datacited by 180
  17. 2018Not-so-supervised: a survey of semi-supervised, multi-instance, and transfer learning in medical image analysiscited by 179
  18. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  19. 2018Learning to Learn from Noisy Labeled Datacited by 160
  20. 2019Deep Self-Learning From Noisy Labelscited by 122
  21. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  22. 2021Augmentation Strategies for Learning with Noisy Labelscited by 86
  23. 2021Generalized Jensen-Shannon Divergence Loss for Learning with Noisy Labelscited by 74
  24. 2021Contrast to Divide: Self-Supervised Pre-Training for Learning with Noisy Labelscited by 69
  25. 2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
  26. 2021Boosting Co-teaching with Compression Regularization for Label Noisecited by 31

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 0; 2025: 1.

3 papers.

  1. 2022Is one annotation enough? A data-centric image classification benchmark for noisy and ambiguous label estimationcited by 43
  2. 2023Improving Medical Image Classification in Noisy Labels Using Only Self-supervised Pretrainingcited by 8
  3. 2025Sample Selection via Contrastive Fragmentation for Noisy Label Regressioncited by 4