mlsanityData to 14 Oct 2026

MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins

arXiv 2308.09037 ↗First posted 17 Aug 2023cs.CVcited by 10

Not on the map. Why?

Abstract (arXiv)

We introduce MarginMatch, a new SSL approach combining consistency regularization and pseudo-labeling, with its main novelty arising from the use of unlabeled data training dynamics to measure pseudo-label quality. Instead of using only the model's confidence on an unlabeled example at an arbitrary iteration to decide if the example should be masked or not, MarginMatch also analyzes the behavior of the model on the pseudo-labeled examples as the training progresses, to ensure low quality predictions are masked out. MarginMatch brings substantial improvements on four vision benchmarks in low data regimes and on two large-scale datasets, emphasizing the importance of enforcing high-quality pseudo-labels. Notably, we obtain an improvement in error rate over the state-of-the-art of 3.25% on CIFAR-100 with only 25 labels per class and of 3.78% on STL-10 using as few as 4 labels per class. We make our code available at https://github.com/tsosea2/MarginMatch.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 32 of its 51 references that are in the map. First posted on arXiv 17 Aug 2023.

Builds on

32 of 51 references.

References · 32

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,599
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2015Distilling the Knowledge in a Neural Networkcited by 10,324
  5. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,442
  6. 2017On Calibration of Modern Neural Networkscited by 4,960
  7. 2014Going Deeper with Convolutionscited by 4,241
  8. 2016Wide Residual Networkscited by 3,070
  9. 2019RandAugment: Practical automated data augmentation with a reduced search spacecited by 2,269
  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
20 more
  1. 2019Self-training with Noisy Student improves ImageNet classificationcited by 1,311
  2. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  3. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  4. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  5. 2017Spectrally-normalized margin bounds for neural networkscited by 686
  6. 2018Exploring the Limits of Weakly Supervised Pretrainingcited by 605
  7. 2017Deep Learning Scaling is Predictable, Empiricallycited by 582
  8. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  9. 2019Pseudo-Labeling and Confirmation Bias in Deep Semi-Supervised Learningcited by 510
  10. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  11. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  12. 2016Adversarial Training Methods for Semi-Supervised Text Classificationcited by 280
  13. 2017WebVision Database: Visual Learning and Understanding from Web Datacited by 262
  14. 2020Identifying Mislabeled Data using the Area Under the Margin Rankingcited by 261
  15. 2019Interpolation Consistency Training for Semi-Supervised Learningcited by 251
  16. 2014Learning with Pseudo-Ensemblescited by 241
  17. 2018Predicting the Generalization Gap in Deep Networks with Margin Distributionscited by 113
  18. 2018Large Margin Deep Networks for Classificationcited by 112
  19. 2016Mutual Exclusivity Loss for Semi-Supervised Deep Learningcited by 22
  20. 2021OpenCoS: Contrastive Semi-supervised Learning for Handling Open-set Unlabeled Datacited by 22

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 4; 2025: 5; 2026: 1.

10 papers.

  1. 2025CGMatch: A Different Perspective of Semi-supervised Learningcited by 11
  2. 2024Foster Adaptivity and Balance in Learning with Noisy Labelscited by 9
  3. 2025Self-Reinforcing Prototype Evolution with Dual-Knowledge Cooperation for Semi-Supervised Lifelong Person Re-Identificationcited by 7
  4. 2024Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selectioncited by 6
  5. 2024Reinforcement Learning-Guided Semi-Supervised Learningcited by 2
  6. 2024Learning from True-False Labels via Multi-modal Prompt Retrievingcited by 1
  7. 2025SpikeMatch: Semi-Supervised Learning with Temporal Dynamics of Spiking Neural Networkscited by 0
  8. 2025Human-Corrected Labels Learning: Enhancing Labels Quality via Human Correction of VLMs Discrepanciescited by 0
  9. 2025Semi-Supervised Learning for Large Language Models Safety and Content Moderationcited by 0
  10. 2026MTSSL: Meta-Thresholding Semi-Supervised Learningcited by 0