Research map / Label-efficient and robust learning / Semi-supervised learning
Bidirectional Adaptation for Robust Semi-Supervised Learning with Inconsistent Data Distributions
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 |
|---|---|---|---|
| Bidirectional Adaptation (decoupled pseudo-label and target predictors, DA-debiased pseudo labels, soft-weighted unlabeled samples) vs. classical SSL and robust SSL baselines | ResNet-50 SSL with inconsistent distributions · Image-CLEF, Office-31, VisDA-2017 (Tables 1-3) | accuracy | Helped |
| Classical SSL methods (FixMatch, FlexMatch, Mean Teacher) under inconsistent distributions | SSL baselines · Office-31 and VisDA-2017 | accuracy | Hurt |
| Uni-adaptation (DA on pseudo-label predictor only) vs. Bi-adaptation (DA on both predictors) on Office-Caltech feature study (ablation) | JDOT-SVM pseudo-label and target predictors · Office-Caltech DECAF features, 20-50 labels | accuracy | Helped |
Closest papers by meaning
- Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation (NeurIPS 2023 · similarity 0.89)
- DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning (CVPR 2022 · similarity 0.89)
- Contrastive Credibility Propagation for Reliable Semi-supervised Learning (AAAI 2024 · similarity 0.87)
- Semi-Supervised Regression with Heteroscedastic Pseudo-Labels (NeurIPS 2025 · similarity 0.87)
- Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling (AAAI 2024 · similarity 0.86)
- Keep It on a Leash: Controllable Pseudo-label Generation Towards Realistic Long-Tailed Semi-Supervised Learning (NeurIPS 2025 · 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.