Research map / Label-efficient and robust learning / Domain adaptation and generalization
Partial Feature Selection and Alignment for Multi-Source Domain Adaptation
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 PFSA instead of LtC-MSDA | MSDA on Digit-Five · Digit-Five | accuracy: 93.5 vs. 91.8 | Helped |
| Use PFSA instead of LtC-MSDA | MSDA on Office-31 · Office-31 | accuracy: 84.7 vs. 84.6 | Helped |
| Use PFSA instead of LtC-MSDA | MSDA on DomainNet · DomainNet | accuracy: 48.5 vs. 47.4 | Helped |
| Use PFSA rather than the strongest listed baseline | MSPDA Digit-Five · Digit-Five | accuracy: 84.5 vs. 70.1 | Helped |
| Use PFSA rather than the strongest listed baseline | MSPDA Office-31 · Office-31 | accuracy: 67.8 vs. 67.8 | No clear effect |
| Add the partial selection module (PSM) (ablation) | PFSA · Digit-Five, MSDA and MSPDA tasks | accuracy | Helped |
| Add the partial selection loss Lp (ablation) | PFSA · Digit-Five, MSDA and MSPDA tasks | accuracy | Helped |
| Add the class-level alignment loss Lc (ablation) | PFSA · Digit-Five, MSDA and MSPDA tasks | accuracy | Helped |
| Add the domain-level alignment loss Ldom (ablation) | PFSA · Digit-Five, MSDA and MSPDA tasks | accuracy | Helped |
| Add the discrimination loss Ldisc (ablation) | PFSA · Digit-Five, MSDA and MSPDA tasks | accuracy | Helped |
| Use all three alignment losses rather than removing all feature alignment (No FA) (ablation) | PFSA · Digit-Five, MSDA and MSPDA tasks | accuracy | Helped |
Closest papers by meaning
- Invertible Projection and Conditional Alignment for Multi-Source Blended-Target Domain Adaptation (AAAI 2025 · similarity 0.90)
- COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation (ICML 2025 · similarity 0.88)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.88)
- Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias (CVPR 2024 · similarity 0.88)
- Revisiting Source-Free Domain Adaptation: Insights into Representativeness, Generalization, and Variety (CVPR 2025 · similarity 0.88)
- Gradient-Based Sample Selection for Black-Box Universal 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.