Research map / Label-efficient and robust learning / Domain adaptation and generalization
Class Relationship Embedded Learning for Source-Free Unsupervised Domain Adaptation
Yixin Zhang, Zilei Wang, Weinan He
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 CR-CACo and CR-IDCo losses | AaD · Office-Home SUDA | accuracy (Avg): 72.7 -> 75.9 | Improved |
| Add CR-CACo and CR-IDCo losses | AaD · Office-31 SUDA | accuracy (Avg): 89.9 -> 91.1 | Improved |
| Add CR-CACo and CR-IDCo losses | AaD · VisDA S→R | accuracy: 88.0 -> 89.6 | Improved |
| Add CR-CACo and CR-IDCo losses | AaD · DomainNet MUDA | accuracy (Avg): 47.9 -> 51.3 | Improved |
| Add CR-CACo and CR-IDCo losses | AaD · Office-Home MUDA | accuracy (Avg): 75.6 -> 78.6 | Improved |
| Add CR-CACo and CR-IDCo losses | SHOT-IM · Office-Home PDA | accuracy (Avg): 76.8 -> 80.6 | Improved |
| Add CR-CACo and CR-IDCo losses | AaD · Office-Home ODA | accuracy (Avg): 71.8 -> 73.3 | Improved |
| Add CR-CACo and CR-IDCo losses | SHOT-IM with ViT-B · Office-Home SUDA | accuracy (Avg): 84.0 -> 88.3 | Improved |
| Add CR-IDCo (ablation) | IM · Office-Home SUDA | accuracy (Avg): 70.5 -> 72.5 | Improved |
| Add CR-CACo (ablation) | IM · Office-Home SUDA | accuracy (Avg): 70.5 -> 74.0 | Improved |
| Add CR-CACo and CR-IDCo (ablation) | IM · Office-Home SUDA | accuracy (Avg): 70.5 -> 75.5 | Improved |
| Use clustering-based rather than prediction-based pseudo labels in CR-CACo (ablation) | IM + CR-CACo · Office-Home SUDA | accuracy (Avg): 74.5 -> 74.8 | Improved |
Closest papers by meaning
- Hierarchical Unsupervised Relation Distillation for Source Free Domain Adaptation (ECCV 2024 · similarity 0.90)
- Uncertainty-guided Open-Set Source-Free Unsupervised Domain Adaptation with Target-private Class Segregation (IJCV 2026 · similarity 0.89)
- Divide and Contrast: Source-free Domain Adaptation via Adaptive Contrastive Learning (NeurIPS 2022 · similarity 0.89)
- Unveiling the Unknown: Unleashing the Power of Unknown to Known in Open-Set Source-Free Domain Adaptation (CVPR 2024 · similarity 0.89)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.88)
- SimProF: A Simple Probabilistic Framework for Unsupervised Domain Adaptation (AAAI 2025 · similarity 0.87)
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.
