mlsanityData to 14 Oct 2026

OTMatch: Improving Semi-Supervised Learning with Optimal Transport

arXiv 2310.17455 ↗First posted 26 Oct 2023cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

Semi-supervised learning has made remarkable strides by effectively utilizing a limited amount of labeled data while capitalizing on the abundant information present in unlabeled data. However, current algorithms often prioritize aligning image predictions with specific classes generated through self-training techniques, thereby neglecting the inherent relationships that exist within these classes. In this paper, we present a new approach called OTMatch, which leverages semantic relationships among classes by employing an optimal transport loss function to match distributions. We conduct experiments on many standard vision and language datasets. The empirical results show improvements in our method above baseline, this demonstrates the effectiveness and superiority of our approach in harnessing semantic relationships to enhance learning performance in a semi-supervised setting.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Builds on 48 of its 56 references that are in the map. First posted on arXiv 26 Oct 2023.

Builds on

48 of 56 references.

References · 48

  1. 2017Attention Is All You Needcited by 60,361
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,513
  5. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  6. 2020Bootstrap your own latent: A new approach to self-supervised Learningcited by 4,750
  7. 2020Exploring Simple Siamese Representation Learningcited by 2,866
  8. 2020Unsupervised Learning of Visual Features by Contrasting Cluster Assignmentscited by 2,857
  9. 2020Supervised Contrastive Learningcited by 2,829
  10. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,316
  11. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,085
  12. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,391
36 more
  1. 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,380
  2. 2019Contrastive Multiview Codingcited by 1,301
  3. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,060
  4. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,057
  5. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 920
  6. 2021FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labelingcited by 540
  7. 2020Meta Pseudo Labelscited by 374
  8. 2019ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoringcited by 349
  9. 2019On Mutual Information Maximization for Representation Learningcited by 316
  10. 2015Semi-Supervised Learning with Ladder Networkscited by 247
  11. 2022FreeMatch: Self-adaptive Thresholding for Semi-supervised Learningcited by 232
  12. 2015Learning with a Wasserstein Losscited by 196
  13. 2020CoMatch: Semi-supervised Learning with Contrastive Graph Regularizationcited by 167
  14. 2021Dash: Semi-Supervised Learning with Dynamic Thresholdingcited by 148
  15. 2023SoftMatch: Addressing the Quantity-Quality Trade-off in Semi-supervised Learningcited by 133
  16. 2022SimMatch: Semi-supervised Learning with Similarity Matchingcited by 118
  17. 2021Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samplescited by 114
  18. 2022USB: A Unified Semi-supervised Learning Benchmark for Classificationcited by 95
  19. 2022Debiased Learning from Naturally Imbalanced Pseudo-Labelscited by 85
  20. 2021ReSSL: Relational Self-Supervised Learning with Weak Augmentationcited by 84
  21. 2021SimPLE: Similar Pseudo Label Exploitation for Semi-Supervised Classificationcited by 68
  22. 2021Sinkhorn Label Allocation: Semi-Supervised Classification via Annealed Self-Trainingcited by 32
  23. 2021All Labels Are Not Created Equal: Enhancing Semi-supervision via Label Grouping and Co-trainingcited by 32
  24. 2019Inverse optimal transportcited by 26
  25. 2023Boosting Semi-Supervised Learning by Exploiting All Unlabeled Datacited by 26
  26. 2022NP-Match: When Neural Processes meet Semi-Supervised Learningcited by 25
  27. 2023Contrastive Learning Is Spectral Clustering On Similarity Graphcited by 25
  28. 2018Learning to Match via Inverse Optimal Transportcited by 23
  29. 2020AlphaMatch: Improving Consistency for Semi-supervised Learning with Alpha-divergencecited by 22
  30. 2023Matrix Information Theory for Self-Supervised Learningcited by 21
  31. 2023Information Flow in Self-Supervised Learningcited by 16
  32. 2021Semi-Supervised Learning with Multi-Head Co-Trainingcited by 15
  33. 2023ProtoCon: Pseudo-label Refinement via Online Clustering and Prototypical Consistency for Efficient Semi-supervised Learningcited by 13
  34. 2022MaxMatch: Semi-Supervised Learning with Worst-Case Consistencycited by 9
  35. 2023RelationMatch: Matching In-batch Relationships for Semi-supervised Learningcited by 8
  36. 2023SEAL: Simultaneous Label Hierarchy Exploration And Learningcited by 6

Built on by

Cited by year

Citing papers per year: 2024: 4; 2025: 2.

6 papers.

  1. 2024UniMatch V2: Pushing the Limit of Semi-Supervised Semantic Segmentationcited by 54
  2. 2024Provable Contrastive Continual Learningcited by 13
  3. 2024Unveiling the Dynamics of Information Interplay in Supervised Learningcited by 3
  4. 2025FATE: A Prompt-Tuning-Based Semi-Supervised Learning Framework for Extremely Limited Labeled Datacited by 2
  5. 2024Exploring Information-Theoretic Metrics Associated with Neural Collapse in Supervised Trainingcited by 1
  6. 2025Knowledge Consultation for Semi-Supervised Semantic Segmentationcited by 1