Research map / Label-efficient and robust learning / Semi-supervised learning
SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning
Zerun Wang, Liuyu Xiang, Lang Huang, Jiafeng Mao, Ling Xiao, Toshihiko Yamasaki
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 a single (K+1)-class head instead of two separate heads (ablation) | SCOMatch · CIFAR-10 (6 ID classes, 25 labels) | open-set accuracy: 54.3 -> 95.4 | Improved |
| use a single head instead of two separate heads (ablation) | SCOMatch · CIFAR-100 (55 ID classes, 25 labels) | AUC: 72.1 -> 90.6 | Improved |
| add close-set self-training on first K dimensions (ablation) | SCOMatch · CIFAR-100 (55 ID classes, 25 labels) | close-set accuracy: 68.7 -> 73.3 | Improved |
| add close-set self-training (ablation) | SCOMatch · CIFAR-10 (6 ID classes, 25 labels) | close-set accuracy: 93.2 -> 94.4 | Improved |
| add open-set self-training (ablation) | SCOMatch · CIFAR-10 (6 ID classes, 25 labels) | open-set accuracy: 80.6 -> 95.4 | Improved |
| add open-set self-training (ablation) | SCOMatch · CIFAR-100 (55 ID classes, 25 labels) | AUC: 75.0 -> 90.6 | Improved |
| add OOD memory queue with (K+1)-class SSL over FixMatch (ablation) | FixMatch · CIFAR-10 (6 ID classes, 25 labels) | AUC: 37.1 -> 99.3 | Improved |
| SCOMatch versus strongest prior OSSL method | Ma et al. · TinyImageNet (mismatch 0.3) | close-set accuracy: 40.8 -> 54.2 | Improved |
| SCOMatch versus OpenMatch on CIFAR-100 80/20 with 50 labels | OpenMatch · CIFAR-100 (80/20 classes, 50 labels) | AUC: 86.2 -> 85.4 | Hurt |
| treat OOD as a single extra class rather than multiple categories | SCOMatch · OSSL benchmarks | close-set accuracy | Improved |
Later papers that compared with this method
2 later accepted papers report SCOMatch as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- PAF: Perturbation-Aware Filtering for Open-Set Semi-Supervised Learning (CVPR 2026 · better on 2 of 2 shared results)
- CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning (ICCV 2025 · better on 1 of 2 shared results)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 0 of 1 on most shared results.
- OpenMatch — OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization (NeurIPS 2021) · better on 1 of 2 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
- Robust Semi-Supervised Learning by Wisely Leveraging Open-Set Data (TPAMI 2024 · similarity 0.90)
- Exploration and Exploitation of Unlabeled Data for Open-Set Semi-supervised Learning (IJCV 2024 · similarity 0.89)
- OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization (NeurIPS 2021 · similarity 0.88)
- OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning (NeurIPS 2024 · similarity 0.87)
- Binary Decomposition: A Problem Transformation Perspective for Open-Set Semi-Supervised Learning (ICML 2024 · similarity 0.86)
- Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning (ICML 2024 · similarity 0.85)
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.
