Research map / Label-efficient and robust learning / Domain adaptation and generalization
Bridging Theory and Practice in Source-Free Domain Adaptation via Adversarial Proxy Perturbation
Dexuan Zhang, Qianyu Zhou, Thomas Westfechtel, Yusuke Mukuta, Tatsuya Harada
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 proxy perturbation and consistency losses (Ldis + Lce) (ablation) | APP · Office-Home Ar->Cl | accuracy (%): 57.6 -> 61.6 | Improved |
| add adversarial loss Ladv (ablation) | APP · DomainNet P->S | accuracy (%): 68.6 -> 72.2 | Improved |
| add self-supervised regularizers Lssl (ablation) | APP · DomainNet P->R | accuracy (%): 79.7 -> 81.3 | Improved |
| add Lssl (ablation) | APP · Office-Home Ar->Cl | accuracy (%): 60.2 -> 61.6 | Improved |
| add adversarial loss Ladv (ablation) | APP · Office-Home Ar->Rw | accuracy (%): 81.9 -> 82.9 | Improved |
| co-train with CLIP via mutual distillation (APP -> APPM) | APP · DomainNet (avg) | accuracy (%): 73.8 -> 84.5 | Improved |
| APP vs strongest prior unimodal SFDA | APP · Office-Home (avg) | accuracy (%): 74.1 -> 74.6 | Improved |
| APP vs strongest prior unimodal SFDA | APP · VisDA-C | accuracy (%): 89.1 -> 89.5 | Improved |
| APPM vs DIFO on open-set SFDA | APPM · Office-Home open-set SFDA | accuracy (%): 75.9 -> 85.2 | Improved |
| APPM vs DIFO on partial-set SFDA | APPM · Office-Home partial-set SFDA | accuracy (%): 85.6 -> 88.3 | Improved |
Closest papers by meaning
- Adaptive Adversarial Network for Source-Free Domain Adaptation (ICCV 2021 · similarity 0.92)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.92)
- Proxy Denoising for Source-Free Domain Adaptation (ICLR 2025 · similarity 0.90)
- Understanding and Improving Source-free Domain Adaptation from a Theoretical Perspective (CVPR 2024 · similarity 0.90)
- SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation (ICLR 2024 · similarity 0.89)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 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.
