Research map / Label-efficient and robust learning / Semi-supervised learning
CoMatch: Semi-Supervised Learning With Contrastive Graph Regularization
Junnan Li, Caiming Xiong, Steven C.H. Hoi
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use CoMatch instead of FixMatch w. DA | FixMatch w. DA · CIFAR-10 (40 labels) | accuracy (%): 86.98 -> 93.09 | Improved |
| use CoMatch instead of FixMatch w. DA | FixMatch w. DA · STL-10 (1000 labels) | accuracy (%): 66.53 -> 79.80 | Improved |
| use CoMatch instead of FixMatch w. DA | FixMatch w. DA · ImageNet (1% labels, no pre-training) | top-1 accuracy (%): 53.4 -> 66.0 | Improved |
| use CoMatch instead of FixMatch w. DA | FixMatch w. DA · ImageNet (10% labels, no pre-training) | top-1 accuracy (%): 70.8 -> 73.6 | Improved |
| add distribution alignment to FixMatch | FixMatch · CIFAR-10 (40 labels) | accuracy (%): 86.12 -> 86.98 | No clear effect |
| add distribution alignment to FixMatch | FixMatch · STL-10 (1000 labels) | accuracy (%): 65.38 -> 66.53 | Improved |
| add MoCov2 pre-training to CoMatch | CoMatch · ImageNet (1% labels) | top-1 accuracy (%): 66.0 -> 67.1 | Improved |
| add graph-based pseudo-label connections (T<1) instead of self-loops only (T=1) (ablation) | CoMatch · ImageNet (1% labels, 100 epochs) | top-1 accuracy (%): decreases the performance by 2.8% | Improved |
| add memory smoothing (alpha=0.9) instead of EMA prediction only (alpha=1) (ablation) | CoMatch · ImageNet (1% labels, 100 epochs) | top-1 accuracy (%): accuracy decreases by 2.1% | Improved |
| use alpha below 0.9 (stronger smoothing) (ablation) | CoMatch · ImageNet (1% labels, 100 epochs) | top-1 accuracy (%) | Hurt |
| increase memory bank and queue size K from 10k to 30k (ablation) | CoMatch · ImageNet (1% labels, 100 epochs) | top-1 accuracy (%) | Improved |
| use larger contrastive loss weight (10) with fewer labels (ablation) | CoMatch · ImageNet (1% labels, 100 epochs) | top-1 accuracy (%) | Improved |
Later papers that compared with this method
15 later accepted papers report CoMatch as a baseline in their results tables; 11 of them report a better number on most of the results they share with it.
- Bi-Level Optimization for Semi-Supervised Learning with Pseudo-Labeling (AAAI 2025 · better on 1 of 1 shared result)
- Unknown-Aware Graph Regularization for Robust Semi-supervised Learning from Uncurated Data (AAAI 2024 · better on 5 of 5 shared results)
- Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data (AAAI 2024 · better on 1 of 1 shared result)
- Systematic Comparison of Semi-supervised and Self-supervised Learning for Medical Image Classification (CVPR 2024 · better on 0 of 1 shared result)
- Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations (NeurIPS 2024 · better on 1 of 1 shared result)
- CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning (CVPR 2023 · better on 5 of 5 shared results)
- DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning (CVPR 2022 · better on 10 of 10 shared results)
- RDA: Reciprocal Distribution Alignment for Robust Semi-Supervised Learning (ECCV 2022 · better on 8 of 8 shared results)
7 more not listed.
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- FixMatch — FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020) · better on 5 of 5 shared results
- MixMatch — MixMatch: A Holistic Approach to Semi-Supervised Learning (NeurIPS 2019) · better on 5 of 5 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Big Self-Supervised Models are Strong Semi-Supervised Learners (NeurIPS 2020 · similarity 0.88)
- Label Efficient Semi-Supervised Learning via Graph Filtering (CVPR 2019 · similarity 0.87)
- Variational Supervised Contrastive Learning (NeurIPS 2025 · similarity 0.86)
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning (ICML 2024 · similarity 0.86)
- Weakly-Supervised Contrastive Learning for Imprecise Class Labels (ICML 2025 · similarity 0.86)
- HiGDA: Hierarchical Graph of Nodes to Learn Local-to-Global Topology for Semi-Supervised Domain Adaptation (AAAI 2025 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
