Research map / Label-efficient and robust learning / Domain adaptation and generalization
Subspace Identification for Multi-Source Domain Adaptation
Zijian Li, Ruichu Cai, Guangyi Chen, Boyang Sun, Zhifeng Hao, Kun Zhang
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 |
|---|---|---|---|
| SIG instead of iMSDA | MSDA · Office-Home average | accuracy (%): 76.2 -> 77.8 | Improved |
| SIG instead of iMSDA | MSDA · ImageCLEF average | accuracy (%): 90.0 -> 90.3 | Improved |
| SIG instead of iMSDA | MSDA · PACS average | accuracy (%): 93.4 -> 93.9 | Improved |
| SIG instead of iMSDA | MSDA · DomainNet average | accuracy (%): 47.5 -> 53.0 | Improved |
| SIG instead of DRT+ST | MSDA · DomainNet Sketch | accuracy (%): 60.7 -> 59.5 | Hurt |
| remove class-aware alignment loss (ablation) | SIG · Office-Home | accuracy | Improved |
| add reconstruction and KL loss (ablation) | SIG · Office-Home | accuracy | Improved |
| reduce number of domains from 8 to 2 (ablation) | Subspace identification · simulation | accuracy: 0.9982 -> 0.5978 | Hurt |
| reduce number of domains from 8 to 3 (ablation) | SIG theory · simulation | RMSE: 0.0433 -> 0.0669 | Mixed |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- T-SVDNet — T-SVDNet: Exploring High-Order Prototypical Correlations for Multi-Source Domain Adaptation (ICCV 2021) · better on 1 of 1 shared result
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Invertible Projection and Conditional Alignment for Multi-Source Blended-Target Domain Adaptation (AAAI 2025 · 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 0.88)
- Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer (CVPR 2024 · similarity 0.87)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.87)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 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.
