Research map / Label-efficient and robust learning / Semi-supervised learning
ExMatch: Self-guided Exploitation for Semi-Supervised Learning with Scarce Labeled Samples
Noo-ri Kim, Jin-Seop Lee, Jee-Hyong Lee
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 |
|---|---|---|---|
| add self-guided exploitation loss selected by confidence and self-pseudo-label consistency, with weak augmentation (ablation) | FixMatch · CIFAR-10 (10 labels, 3 folds) | accuracy: 60.84 -> 74.83 | Improved |
| only add self-pseudo-label consistency to the FixMatch unsupervised loss (ablation) | FixMatch · CIFAR-10 (10 labels, 3 folds) | accuracy: 60.84 -> 64.86 | No clear effect |
| exploit all pseudo-labeled samples without selection (ablation) | ExMatch · CIFAR-10 (10 labels, 3 folds) | accuracy: 74.83 -> 12.31 | Hurt |
| select exploited samples by confidence only (ablation) | ExMatch · CIFAR-10 (10 labels, 3 folds) | accuracy: 74.83 -> 29.25 | Hurt |
| add confidence threshold on top of self-pseudo-label consistency (ablation) | ExMatch · CIFAR-10 (10 labels, 3 folds) | accuracy: 56.61 -> 74.83 | Improved |
| use weak instead of strong augmentation in the exploitation loss (ablation) | ExMatch · CIFAR-10 (10 labels, 3 folds) | accuracy: 50.07 -> 74.83 | Improved |
| use similarity-based self-pseudo-labels instead of fine-tuning the self-supervised model (ablation) | ExMatch · CIFAR-10 (10 labels) | accuracy: 67.82 -> 74.83 | Improved |
| use a weaker self-supervised model (RotNet NiN-4) (ablation) | ExMatch · CIFAR-10 (10 labels) | accuracy: 74.83 -> 57.91 | Hurt |
| use smaller self-supervised network or a model trained on ImageNet-32 (ablation) | ExMatch · CIFAR-10 (10 labels) | accuracy: 74.83 vs 74.72 (ResNet-18) and 74.85 (ImageNet-32) | No clear effect |
| replace FixMatch with ExMatch on CIFAR-100 with 100 labels | ExMatch · CIFAR-100 (100 labels) | accuracy: 24.11 -> 32.49 | Improved |
| replace FlexMatch/FreeMatch with ExMatch on CIFAR-10 with 20 and 40 labels | ExMatch · CIFAR-10 (20 and 40 labels) | accuracy: 94.62 vs 84.66 (20 labels); 94.88 vs 89.78 (40 labels) | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 4 on most shared results.
- FixMatch — FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020) · better on 7 of 7 shared results
- FreeMatch — FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning (ICLR 2023) · better on 0 of 1 shared result
- FlatMatch — FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning (NeurIPS 2023) · better on 1 of 1 shared result
- FlexMatch — FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling (NeurIPS 2021) · better on 0 of 1 shared result
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
- Barely-Supervised Learning: Semi-supervised Learning with Very Few Labeled Images (AAAI 2022 · similarity 0.91)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.88)
- OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning (NeurIPS 2024 · similarity 0.88)
- Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data (AAAI 2024 · similarity 0.88)
- OTMatch: Improving Semi-Supervised Learning with Optimal Transport (ICML 2024 · similarity 0.87)
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning (ICML 2024 · similarity 0.87)
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.
