Research map / Label-efficient and robust learning / Domain adaptation and generalization
Semi-Supervised Domain Adaptation With Source Label Adaptation
Yu-Chu Yu, Hsuan-Tien Lin
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 source label adaptation to CDAC | CDAC · DomainNet 1-shot mean | accuracy: 73.6 -> 75.0 | Improved |
| Add source label adaptation to CDAC | CDAC · DomainNet 3-shot mean | accuracy: 76.0 -> 76.9 | Improved |
| Add source label adaptation to MME | MME · DomainNet 1-shot mean | accuracy: 66.4 -> 68.8 | Improved |
| Add source label adaptation to MME | MME · DomainNet 3-shot mean | accuracy: 68.9 -> 70.0 | Improved |
| Add source label adaptation to CDAC | CDAC · Office-Home 1-shot mean | accuracy: 71.0 -> 72.9 | Improved |
| Add source label adaptation to CDAC | CDAC · Office-Home 3-shot mean | accuracy: 74.8 -> 76.3 | Improved |
| Add source label adaptation to MME | MME · Office-Home 1-shot mean | accuracy: 70.4 -> 72.0 | Improved |
| Add source label adaptation to MME | MME · Office-Home 3-shot mean | accuracy: 73.1 -> 75.6 | Improved |
| Add source label adaptation to reproduced MCL | MCL* · Office-Home 3-shot mean | accuracy: 75.3 -> 75.6 | Improved |
| Use a self-prediction label correction model instead of the target-view label adaptation model (ablation) | S+T on Office-Home · Office-Home A→C | KL divergence | No clear effect |
| Set alpha to 0.9 rather than the selected 0.3 (ablation) | MME + SLA · Office-Home 3-shot mean test | accuracy: 75.57 -> 72.76 | Hurt |
| Increase warmup from 500 to 1000 iterations (ablation) | MME + SLA · Office-Home A→C 3-shot | accuracy: 65.90 -> 64.99 | Hurt |
Closest papers by meaning
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.92)
- Enhancing Semi-supervised Domain Adaptation via Effective Target Labeling (AAAI 2024 · similarity 0.91)
- Forget More to Learn More: Domain-specific Feature Unlearning for Semi-supervised and Unsupervised Domain Adaptation (ECCV 2024 · similarity 0.91)
- ECACL: A Holistic Framework for Semi-Supervised Domain Adaptation (ICCV 2021 · similarity 0.91)
- A Theory of Learning Unified Model via Knowledge Integration from Label Space Varying Domains (CVPR 2025 · similarity 0.89)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.89)
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.
