Research map / Label-efficient and robust learning / Semi-supervised learning
Semi-Supervised Learning by Augmented Distribution Alignment
Qin Wang, Wen Li, Luc Van Gool
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 adversarial distribution alignment (ablation) | baseline CNN · CIFAR10 | error rate (%): 19.97% -> 18.67% | Improved |
| add adversarial distribution alignment (ablation) | baseline CNN · SVHN | error rate (%): 13.80% -> 10.76% | Improved |
| add cross-set sample augmentation (ablation) | baseline CNN · CIFAR10 | error rate (%): 19.97% -> 13.79% | Improved |
| add cross-set sample augmentation (ablation) | baseline CNN · SVHN | error rate (%): 13.80% -> 10.74% | Improved |
| add distribution alignment on top of cross-set augmentation (ablation) | ADA-Net · CIFAR10 | error rate (%): 13.79% -> 8.87% | Improved |
| add cross-set augmentation on top of distribution alignment (ablation) | ADA-Net · CIFAR10 | error rate (%): 18.67% -> 8.87% | Improved |
| add distribution alignment on top of cross-set augmentation (ablation) | ADA-Net · SVHN | error rate (%): 10.74% -> 5.90% | Improved |
| add cross-set augmentation on top of distribution alignment (ablation) | ADA-Net · SVHN | error rate (%): 10.76% -> 5.90% | Improved |
| add ADA-Net modules to VAT+Ent | VAT+Ent · SVHN | error rate (%): 3.86% -> 3.54% | Improved |
| add ADA-Net modules to VAT+Ent | VAT+Ent · CIFAR10 | error rate (%): 10.55% -> 10.09% | Improved |
| use larger translation range (4 instead of 2) and no ZCA whitening | ADA-Net · CIFAR10 | error rate (%): 10.30% -> 8.72% | Improved |
| fewer labeled samples (1000 down to 200) | baseline CNN · SVHN | error rate (%) | Hurt |
Closest papers by meaning
- Flexible Distribution Alignment: Towards Long-tailed Semi-supervised Learning with Proper Calibration (ECCV 2024 · similarity 0.89)
- Distribution Aligning Refinery of Pseudo-label for Imbalanced Semi-supervised Learning (NeurIPS 2020 · similarity 0.88)
- ReMixMatch: Semi-Supervised Learning with Distribution Matching and Augmentation Anchoring (ICLR 2020 · similarity 0.88)
- Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning (NeurIPS 2024 · similarity 0.87)
- Three Heads Are Better than One: Complementary Experts for Long-Tailed Semi-supervised Learning (AAAI 2024 · similarity 0.86)
- Out-Of-Domain Unlabeled Data Improves Generalization (ICLR 2024 · 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.
