Research map / Label-efficient and robust learning / Semi-supervised learning
CaliMatch: Adaptive Calibration for Improving Safe Semi-supervised Learning
Jinsoo Bae, Seoung Bum Kim, Hyungrok Do
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 multiclass calibration (adaptive label smoothing + temperature scaling) (ablation) | CaliMatch · CIFAR-100 (kappa 60%) | accuracy (%): 66.16 -> 68.56 | Improved |
| add OOD detector calibration (ablation) | CaliMatch · CIFAR-10 (kappa 60%) | accuracy (%): 87.57 -> 87.62 | No clear effect |
| add OOD detector calibration (ablation) | CaliMatch · CIFAR-100 (kappa 60%) | accuracy (%): 66.96 -> 68.56 | Improved |
| add OOD detector calibration (ablation) | CaliMatch · TinyImageNet unseen detection ECE | ECE: 0.238 vs 0.189 (w/o multiclass calibration) | Mixed |
| add both calibrations (CaliMatch) vs OpenMatch (ablation) | OpenMatch · CIFAR-100 (kappa 60%) | accuracy (%): 65.65 -> 68.56 | Improved |
| add calibration to OpenMatch on ImageNet | OpenMatch · ImageNet (kappa 60%) | top-1 accuracy (%): +1.24% over OpenMatch | Improved |
| add calibration to OpenMatch on ImageNet | OpenMatch · ImageNet (kappa 60%) | OOD ECE: 0.121 -> 0.070 | Improved |
| raise OOD threshold tau_1 from 0.7 to 0.8 (ablation) | CaliMatch · CIFAR-10 | accuracy | Hurt |
| use CaliMatch vs best baseline on CIFAR-10 kappa 30% | CaliMatch · CIFAR-10 (kappa 30%) | top-1 accuracy (%): 90.30 (SCOMatch) vs 90.25 | No clear effect |
| vary lambda_O and lambda_OCal (ablation) | CaliMatch · CIFAR-10 (kappa 60%) | accuracy | No clear effect |
Later papers that compared with this method
2 later accepted papers report CaliMatch as a baseline in their results tables; 2 of them report a better number on most of the results they share with it.
- Beyond Distribution Estimation: Simplex Anchored Structural Inference Towards Universal Semi-Supervised Learning (ICML 2026 · better on 1 of 1 shared result)
- PAF: Perturbation-Aware Filtering for Open-Set Semi-Supervised Learning (CVPR 2026 · better on 1 of 1 shared result)
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 4 on most shared results.
- OpenMatch — OpenMatch: Open-Set Semi-supervised Learning with Open-set Consistency Regularization (NeurIPS 2021) · better on 8 of 8 shared results
- SCOMatch — SCOMatch: Alleviating Overtrusting in Open-set Semi-supervised Learning (ECCV 2024) · better on 1 of 2 shared results
- IOMatch — IOMatch: Simplifying Open-Set Semi-Supervised Learning with Joint Inliers and Outliers Utilization (ICCV 2023) · better on 1 of 1 shared result
- FixMatch — FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020) · better on 1 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
- On the Calibration of Image Semi-Supervised Learning Models (AAAI 2026 · similarity 0.90)
- Mitigating Confidence Miscalibration in Open-World Semi-Supervised Learning (NeurIPS 2026 · similarity 0.89)
- Don’t fear the unlabelled: safe semi-supervised learning via debiasing (ICLR 2023 · similarity 0.87)
- FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence (NeurIPS 2020 · similarity 0.87)
- Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning (CVPR 2022 · similarity 0.87)
- Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL (ICML 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.
