Research map / Label-efficient and robust learning / Semi-supervised learning
Propagation Regularizer for Semi-Supervised Learning With Extremely Scarce Labeled Samples
Check 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 model selection and propagation regularizer to FixMatch | FixMatch · CIFAR-10, 1 label/class | accuracy: 60.01 -> 70.87 | Helped |
| Add model selection and propagation regularizer to UDA | UDA · CIFAR-100, 1 label/class | accuracy: 24.96 -> 30.30 | Helped |
| Add model selection to UDA (ablation) | UDA · SVHN, 1 label/class | accuracy: 24.02 -> 78.91 | Helped |
| Add model selection and propagation regularizer to UDA | UDA · SVHN, 1 label/class | accuracy: 24.02 -> 77.98 | Helped |
| Add model selection and propagation regularizer to FixMatch | FixMatch · STL-10, 1 label/class | accuracy: 30.82 -> 37.91 | Helped |
| Add model selection without propagation regularizer (ablation) | FixMatch · CIFAR-10, 1 label/class | accuracy: 60.01 -> 65.73 | Helped |
| Add propagation regularizer to FixMatch + Sel (ablation) | FixMatch + Sel · CIFAR-10, 1 label/class | accuracy: 65.73 -> 70.87 | Helped |
| Add model selection without propagation regularizer (ablation) | UDA · CIFAR-10, 1 label/class | accuracy: 51.82 -> 59.71 | Helped |
| Add propagation regularizer to UDA + Sel (ablation) | UDA + Sel · CIFAR-10, 1 label/class | accuracy: 59.71 -> 69.87 | Helped |
| Add model selection and propagation regularizer to FixMatch | FixMatch · CIFAR-10, 2 labels/class | accuracy: 94.62 -> 88.20 | Hurt |
| Add model selection and propagation regularizer to FixMatch | FixMatch · CIFAR-10, 4 labels/class | accuracy: 94.86 -> 91.52 | Hurt |
| Add model selection and propagation regularizer to UDA | UDA · CIFAR-100, 4 labels/class | accuracy: 48.98 -> 50.61 | Helped |
Closest papers by meaning
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.89)
- Towards Realistic Model Selection for Semi-supervised Learning (ICML 2024 · similarity 0.89)
- Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection (NeurIPS 2024 · similarity 0.88)
- Contrastive Credibility Propagation for Reliable Semi-supervised Learning (AAAI 2024 · similarity 0.88)
- Erasing the Bias: Fine-Tuning Foundation Models for Semi-Supervised Learning (ICML 2024 · similarity 0.87)
- Rethinking Confidence Scores and Thresholds in Pseudolabeling-based SSL (ICML 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.