Research map / Label-efficient and robust learning / Domain adaptation and generalization
Confident Anchor-Induced Multi-Source Free Domain Adaptation
Jiahua Dong, Zhen Fang, Anjin Liu, Gan Sun, Tongliang Liu
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 L_ent loss (ablation) | CAiDA · Office-31 (avg of 3 tasks) | accuracy (%): 90.3 -> 91.6 | Improved |
| add L_ent loss (ablation) | CAiDA · Office-Home (avg of 4 tasks) | accuracy (%): 74.6 -> 76.2 | Improved |
| add L_ent loss (ablation) | CAiDA · Digits-Five (avg of 5 tasks) | accuracy (%): 92.5 -> 94.6 | Improved |
| add L_div loss (ablation) | CAiDA · Office-31 (avg of 3 tasks) | accuracy (%): 89.8 -> 91.6 | Improved |
| add L_div loss (ablation) | CAiDA · Office-Home (avg of 4 tasks) | accuracy (%): 74.3 -> 76.2 | Improved |
| add L_div loss (ablation) | CAiDA · Digits-Five (avg of 5 tasks) | accuracy (%): 92.8 -> 94.6 | Improved |
| add L_cls loss (ablation) | CAiDA · Office-31 (avg of 3 tasks) | accuracy (%): 89.4 -> 91.6 | Improved |
| add L_cls loss (ablation) | CAiDA · Office-Home (avg of 4 tasks) | accuracy (%): 73.8 -> 76.2 | Improved |
| add L_cls loss (ablation) | CAiDA · Digits-Five (avg of 5 tasks) | accuracy (%): 92.1 -> 94.6 | Improved |
| add L_crc loss (ablation) | CAiDA · Office-31 (avg of 3 tasks) | accuracy (%): 91.2 -> 91.6 | Improved |
| add L_crc loss (ablation) | CAiDA · Office-Home (avg of 4 tasks) | accuracy (%): 75.6 -> 76.2 | Improved |
| add L_crc loss (ablation) | CAiDA · Digits-Five (avg of 5 tasks) | accuracy (%): 93.9 -> 94.6 | Improved |
Closest papers by meaning
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.90)
- A Comprehensive Survey on Source-Free Domain Adaptation (TPAMI 2024 · similarity 0.90)
- Generalized Source-Free Domain Adaptation (ICCV 2021 · 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)
- Distinguish Then Exploit: Source-free Open Set Domain Adaptation via Weight Barcode Estimation and Sparse Label Assignment (CVPR 2025 · similarity 0.89)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 2025 · similarity 0.88)
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.
