Research map / Label-efficient and robust learning / Domain adaptation and generalization
Exploiting the Intrinsic Neighborhood Structure for Source-free Domain Adaptation
Shiqi Yang, Yaxing Wang, Joost van de weijer, Luis Herranz, SHANGLING JUI
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 |
|---|---|---|---|
| Use NRC instead of SHOT | source-free domain adaptation · Office-Home Avg | accuracy (%): 71.8 -> 72.2 | Improved |
| Use NRC instead of SHOT | source-free domain adaptation · VisDA-C Synthesis→Real Per-class | accuracy (%): 82.9 -> 85.9 | Improved |
| Use NRC instead of PointDAN | PointDA-10 · PointDA-10 Avg | accuracy (%): 48.7 -> 52.6 | Improved |
| Add nearest-neighbor consistency to diversity loss (ablation) | NRC · Office-Home Avg | accuracy: 62.1 -> 69.1 | Improved |
| Add reciprocal-neighbor affinity weighting (ablation) | NRC with nearest-neighbor consistency · Office-Home Avg | accuracy: 69.1 -> 71.1 | Improved |
| Add expanded neighbors with affinity weighting (ablation) | NRC with nearest-neighbor affinity · Office-Home Avg | accuracy: 71.1 -> 72.2 | Improved |
| Add expanded neighbors without affinity weighting (ablation) | NRC · Office-Home Avg | accuracy: 71.1 -> 65.2 | Hurt |
| Retain duplicate expanded neighbors (ablation) | NRC · Office-Home Avg | accuracy: 69.1 -> 72.2 | Improved |
| Replace expanded neighbors with a larger nearest-neighbor set (ablation) | NRC · VisDA-C Synthesis→Real | accuracy: 85.9 -> 84.0 | Hurt |
| Replace expanded neighbors with a larger nearest-neighbor set (ablation) | NRC · Office-Home Avg | accuracy: 72.2 -> 69.5 | Hurt |
| Use a smaller memory bank (ablation) | NRC · VisDA-C Synthesis→Real | per-class accuracy (%): 85.9 -> 85.3 | Hurt |
Closest papers by meaning
- Trust Your Good Friends: Source-Free Domain Adaptation by Reciprocal Neighborhood Clustering (TPAMI 2023 · similarity 0.97)
- SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation (ICLR 2024 · similarity 0.92)
- Source-Free Domain Adaptation via Distribution Estimation (CVPR 2022 · similarity 0.90)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.89)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.89)
- Dynamic Target Distribution Estimation for Source-Free Open-Set Domain Adaptation (AAAI 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.
