mlsanityData to 7 Oct 2026

ScanMix: Learning from Severe Label Noise via Semantic Clustering and Semi-Supervised Learning

arXiv 2103.11395 ↗First posted 21 Mar 2021cs.CV cs.LGcited by 13

Not on the map. Why?

Abstract (arXiv)

We propose a new training algorithm, ScanMix, that explores semantic clustering and semi-supervised learning (SSL) to allow superior robustness to severe label noise and competitive robustness to non-severe label noise problems, in comparison to the state of the art (SOTA) methods. ScanMix is based on the expectation maximisation framework, where the E-step estimates the latent variable to cluster the training images based on their appearance and classification results, and the M-step optimises the SSL classification and learns effective feature representations via semantic clustering. We present a theoretical result that shows the correctness and convergence of ScanMix, and an empirical result that shows that ScanMix has SOTA results on CIFAR-10/-100 (with symmetric, asymmetric and semantic label noise), Red Mini-ImageNet (from the Controlled Noisy Web Labels), Clothing1M and WebVision. In all benchmarks with severe label noise, our results are competitive to the current SOTA.

Key facts. Cited by 13 papers in the map (data through 7 Oct 2026). Builds on 46 of its 66 references that are in the map. First posted on arXiv 21 Mar 2021.

Builds on

46 of 66 references.

References · 46

  1. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  2. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
  3. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  6. 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
  7. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  8. 2016Understanding deep learning requires rethinking generalizationcited by 1,657
  9. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  10. 2017A Survey on Deep Learning in Medical Image Analysiscited by 1,182
  11. 2018Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labelscited by 1,053
  12. 2020DivideMix: Learning with Noisy Labels as Semi-supervised Learningcited by 691
34 more
  1. 2018Learning to Reweight Examples for Robust Deep Learningcited by 670
  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. 2019Symmetric Cross Entropy for Robust Learning with Noisy Labelscited by 499
  5. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
  6. 2020Early-Learning Regularization Prevents Memorization of Noisy Labelscited by 414
  7. 2019How does Disagreement Help Generalization against Label Corruption?cited by 390
  8. 2020SCAN: Learning to Classify Images without Labelscited by 351
  9. 2019Unsupervised Label Noise Modeling and Loss Correctioncited by 327
  10. 2018Joint Optimization Framework for Learning with Noisy Labelscited by 293
  11. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  12. 2017Decoupling "when to update" from "how to update"cited by 230
  13. 2019Probabilistic End-to-end Noise Correction for Learning with Noisy Labelscited by 210
  14. 2019Understanding and Utilizing Deep Neural Networks Trained with Noisy Labelscited by 209
  15. 2017CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noisecited by 181
  16. 2018Dimensionality-Driven Learning with Noisy Labelscited by 173
  17. 2017Deep Learning is Robust to Massive Label Noisecited by 164
  18. 2019SELF: Learning to Filter Noisy Labels with Self-Ensemblingcited by 164
  19. 2018Learning to Learn from Noisy Labeled Datacited by 160
  20. 2019NLNL: Negative Learning for Noisy Labelscited by 151
  21. 2019Deep Self-Learning From Noisy Labelscited by 122
  22. 2021Learning with Feature-Dependent Label Noise: A Progressive Approachcited by 102
  23. 2017Learning with Biased Complementary Labelscited by 93
  24. 2020Multi-Objective Interpolation Training for Robustness to Label Noisecited by 86
  25. 2019Robust Inference via Generative Classifiers for Handling Noisy Labelscited by 67
  26. 2019Addressing Semantic Drift in Question Generation for Semi-Supervised Question Answeringcited by 63
  27. 2021LongReMix: Robust Learning with High Confidence Samples in a Noisy Label Environmentcited by 40
  28. 2019IMAE for Noise-Robust Learning: Mean Absolute Error Does Not Treat Examples Equally and Gradient Magnitude's Variance Matterscited by 33
  29. 2018A Semi-Supervised Two-Stage Approach to Learning from Noisy Labelscited by 29
  30. 2020EvidentialMix: Learning with Combined Open-set and Closed-set Noisy Labelscited by 28
  31. 2019Towards Robust Learning with Different Label Noise Distributionscited by 14
  32. 2020Unsupervised Semantic Aggregation and Deformable Template Matching for Semi-Supervised Learningcited by 14
  33. 2019Photometric Transformer Networks and Label Adjustment for Breast Density Predictioncited by 10
  34. 2018Semi-Supervised Clustering with Neural Networkscited by 7

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 3; 2024: 6; 2025: 1.

13 papers.

Sort:

By area:

  1. 2022Is your noise correction noisy? PLS: Robustness to label noise with two stage detectioncited by 11
  2. 2024Tails Tell Tales: Chapter-Wide Manga Transcriptions with Character Namescited by 10
  3. 2023Manifold DivideMix: A Semi-Supervised Contrastive Learning Framework for Severe Label Noisecited by 9
  4. 2023Dynamics-Aware Loss for Learning with Label Noisecited by 8
  5. 2022Bootstrapping the Relationship Between Images and Their Clean and Noisy Labelscited by 7
  6. 2024Learning to Complement and to Defer to Multiple Userscited by 7
  7. 2022Embedding contrastive unsupervised features to cluster in- and out-of-distribution noise in corrupted image datasetscited by 6
  8. 2024PLReMix: Combating Noisy Labels with Pseudo-Label Relaxed Contrastive Representation Learningcited by 5
  9. 2023GANN: Graph Alignment Neural Network for Semi-Supervised Learningcited by 2
  10. 2024An Interpretable Power System Transient Stability Assessment Method with Expert Guiding Neural-Regression-Treecited by 0
  11. 2024A Multi-module Robust Method for Transient Stability Assessment against False Label Injection Cyberattackscited by 0
  12. 2024An accurate detection is not all you need to combat label noise in web-noisy datasetscited by 0
1 more
  1. 2025Prototype-Guided Pseudo-Labeling with Neighborhood-Aware Consistency for Unsupervised Adaptationcited by 0