Research map / Label-efficient and robust learning / Semi-supervised learning
On Data-Augmentation and Consistency-Based Semi-Supervised Learning
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 |
|---|---|---|---|
| Reduce the explored data-manifold dimensions (ablation) | Π-model · Hidden Manifold Model synthetic classification | test NLL | Hurt |
| Use too little augmentation (ε = 0.03) (ablation) | Π-model · Hidden Manifold Model synthetic classification | test NLL | Hurt |
| Use too much augmentation (ε = 1.0) (ablation) | Π-model · Hidden Manifold Model synthetic classification | test NLL | Hurt |
| Vary λ within reasonable bounds (ablation) | Π-model · Hidden Manifold Model synthetic classification | test NLL | No clear effect |
| Replace the Π-model target with an exponential-moving-average teacher (ablation) | Π-model · Hidden Manifold Model synthetic classification | generalization performance | No clear effect |
Closest papers by meaning
- Semi-supervised Learning with GANs: Manifold Invariance with Improved Inference (NeurIPS 2017 · similarity 0.88)
- Time-Consistent Self-Supervision for Semi-Supervised Learning (ICML 2020 · similarity 0.88)
- CGMatch: A Different Perspective of Semi-supervised Learning (CVPR 2025 · similarity 0.86)
- Not All Classes Stand on Same Embeddings: Calibrating a Semantic Distance with Metric Tensor (CVPR 2024 · similarity 0.86)
- Revisiting Semi-Supervised Learning in the Era of Foundation Models (NeurIPS 2025 · similarity 0.86)
- InterLUDE: Interactions between Labeled and Unlabeled Data to Enhance Semi-Supervised Learning (ICML 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.