Research map / Label-efficient and robust learning / Domain adaptation and generalization
Aligning Domain-Specific Distribution and Classifier for Cross-Domain Classification from Multiple Sources
Read the paperCheck 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 |
|---|---|---|---|
| multi-source domain-specific alignment (MFSAN) vs source-combine baselines | ResNet-50 UDA · Office-31 | accuracy: 88.5 -> 90.2 | Helped |
| add MMD domain-specific alignment loss (ablation) | MFSAN · Office-31 | accuracy: 88.6 -> 90.2 | Helped |
| add classifier discrepancy (disc) loss (ablation) | MFSAN · Office-31 | accuracy: 89.9 -> 90.2 | Helped |
| add classifier discrepancy (disc) loss (ablation) | MFSAN · Office-Home | accuracy: 73.3 -> 74.1 | Helped |
| add MMD domain-specific alignment loss (ablation) | MFSAN · Image-CLEF | accuracy: 88.5 -> 89.4 | Helped |
| combine all sources into one source vs single best source | DAN · Office-Home | accuracy: 70.2 -> 72.4 | Helped |
Closest papers by meaning
- Distributionally Robust Classification for Multi-source Unsupervised Domain Adaptation (ICLR 2026 · similarity 0.90)
- Progressive Feature Alignment for Unsupervised Domain Adaptation (CVPR 2019 · similarity 0.90)
- FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation (CVPR 2021 · similarity 0.90)
- Co-regularized Alignment for Unsupervised Domain Adaptation (NeurIPS 2018 · similarity 0.89)
- CASUAL: Conditional Support Alignment for Domain Adaptation with Label Shift (AAAI 2025 · similarity 0.89)
- Can We Evaluate Domain Adaptation Models Without Target-Domain Labels? (ICLR 2024 · 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.