Research map / Label-efficient and robust learning / Semi-supervised learning
FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 curriculum pseudo labeling (class-wise flexible thresholds) | FixMatch · CIFAR-100 400 labels | error rate: 46.42 -> 39.94 | Helped |
| add CPL | FixMatch · STL-10 40 labels | error rate: 35.97 -> 29.15 | Helped |
| add CPL | FixMatch · SVHN | error rate: 1.96 -> 6.72 | Hurt |
| add CPL | FixMatch · CIFAR-10 250 labels | error rate: 4.86 -> 4.98 | No clear effect |
| add CPL | UDA · STL-10 40 labels | error rate: 37.42 -> 29.53 | Helped |
| add CPL | Pseudo-Labeling · STL-10 40 labels | error rate: 74.68 -> 73.42 | Helped |
| add CPL | FixMatch · ImageNet-1K | top-1 error: 43.66 -> 41.85 | Helped |
| add threshold warm-up (ablation) | FlexMatch · CIFAR-10 40 / CIFAR-100 400 | accuracy: +0.2% / +1% | Helped |
| convex mapping function instead of linear/concave (ablation) | FlexMatch · CIFAR-10 40 labels | error rate | Helped |
| threshold upper bound tau away from 0.95 (ablation) | FlexMatch · CIFAR-10 40 labels | error rate | Hurt |
| add lower threshold limit 0.5 (ablation) | FlexMatch · CIFAR-10 | performance | Helped |
Closest papers by meaning
- OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning (NeurIPS 2024 · similarity 0.89)
- RegMixMatch: Optimizing Mixup Utilization in Semi-Supervised Learning (AAAI 2025 · similarity 0.88)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.88)
- Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning (ICML 2024 · similarity 0.88)
- Scaling Up Semi-supervised Learning with Unconstrained Unlabelled Data (AAAI 2024 · similarity 0.87)
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · 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.