Research map / Label-efficient and robust learning / Semi-supervised learning
Safe-Student for Safe Deep Semi-Supervised Learning With Unseen-Class Unlabeled Data
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 energy-discrepancy scoring (ablation) | SAFE-STUDENT · CIFAR-10, mismatch ratio=0.6, m=400×6 | accuracy: 82.0±0.2 -> 83.8±0.1 | Helped |
| Add data augmentation (ablation) | SAFE-STUDENT · CIFAR-10, mismatch ratio=0.6, m=400×6 | accuracy: 82.3±0.2 -> 83.8±0.1 | Helped |
| Add confirmation bias elimination loss (ablation) | SAFE-STUDENT · CIFAR-10, mismatch ratio=0.6, m=400×6 | accuracy: 82.6±0.2 -> 83.8±0.1 | Helped |
| Add unseen-class label distribution learning (ablation) | SAFE-STUDENT · CIFAR-10, mismatch ratio=0.6, m=400×6 | accuracy: 81.5±0.3 -> 83.8±0.1 | Helped |
| Add iterative optimization (ablation) | SAFE-STUDENT · CIFAR-10, mismatch ratio=0.6, m=400×6 | accuracy: 81.8±0.4 -> 83.8±0.1 | Helped |
| Add exponential weighting (ablation) | SAFE-STUDENT · CIFAR-10, mismatch ratio=0.6, m=400×6 | accuracy: 82.9±0.3 -> 83.8±0.1 | Helped |
| Use energy-discrepancy instead of confidence, entropy, or energy for identification | SAFE-STUDENT · MNIST, unseen-class identification, mismatch ratio=0.6 | AUC: 91.7±0.3; 91.7±0.3; 92.6±0.2 -> 93.8±0.2 | Helped |
Closest papers by meaning
- Safe Deep Semi-Supervised Learning for Unseen-Class Unlabeled Data (ICML 2020 · similarity 0.94)
- Not All Parameters Should Be Treated Equally: Deep Safe Semi-supervised Learning under Class Distribution Mismatch (AAAI 2022 · similarity 0.91)
- Re-Evaluating the Impact of Unseen-Class Unlabeled Data on Semi-Supervised Learning Model (ICLR 2025 · similarity 0.88)
- OwMatch: Conditional Self-Labeling with Consistency for Open-World Semi-Supervised Learning (NeurIPS 2024 · similarity 0.85)
- Unlocking the Potential of Unlabeled Data in Semi-Supervised Domain Generalization (CVPR 2025 · similarity 0.85)
- Contrastive Credibility Propagation for Reliable Semi-supervised Learning (AAAI 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.