Research map / Label-efficient and robust learning / Domain adaptation and generalization
Partial disentanglement for domain adaptation
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 |
|---|---|---|---|
| add entropy minimization loss L_ent on target domain (on top of classification loss) (ablation) | iMSDA · PACS | average accuracy: 82.11 -> 92.01 | Helped |
| add entropy minimization loss L_ent on target domain (on top of classification loss) (ablation) | iMSDA · Office-Home | average accuracy: 67.2 -> 75.77 | Helped |
| add VAE alignment loss (full L) on top of Lcls + L_ent (ablation) | iMSDA · PACS | average accuracy: 92.01 -> 93.48 | Helped |
| add VAE alignment loss (full L) on top of Lcls + L_ent (ablation) | iMSDA · Office-Home | average accuracy: 75.77 -> 76.19 | Helped |
| vary changing-part dimension ns (ns=8 vs 4 vs 2) (ablation) | iMSDA · PACS | average accuracy: ns=4 best at 93.48; ns=8 92.05; ns=2 92.66 | Mixed |
| full iMSDA vs DANN baseline on PACS | iMSDA · PACS | average accuracy: 81.5 -> 93.48 | Helped |
| full iMSDA vs strongest baseline on Office-Home | iMSDA · Office-Home | average accuracy: 74.11 -> 76.19 | Helped |
| iMSDA on Office-Home Clipart target task | iMSDA · Office-Home (→Clipart) | accuracy: 61.4 vs MIAN-γ 64.20 | Hurt |
Closest papers by meaning
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.90)
- U$^3$CF: Unbiased, Unconfounding, and Unified Causal Framework for Multi-Target Domain Adaptation (ICML 2026 · similarity 0.90)
- Pseudo-Labeling for Unsupervised Domain Adaptation with Kernel GLMs (NeurIPS 2026 · similarity 0.88)
- Theoretical Performance Guarantees for Partial Domain Adaptation via Partial Optimal Transport (ICML 2025 · similarity 0.88)
- COSDA: Counterfactual-based Susceptibility Risk Framework for Open-Set Domain Adaptation (ICML 2025 · similarity 0.88)
- Open-Set Heterogeneous Domain Adaptation: Theoretical Analysis and Algorithm (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.