Research map / Label-efficient and robust learning / Domain adaptation and generalization
Explore and Exploit the Diverse Knowledge in Model Zoo for Domain Generalization
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 both reweighting and HSIC penalization to the top-ranked model | ZooD top-1 model · PACS | accuracy: 96.0 -> 96.7 | Helped |
| Add both reweighting and HSIC penalization to the top-ranked model | ZooD top-1 model · VLCS | accuracy: 79.5 -> 81.4 | Helped |
| Add both reweighting and HSIC penalization to the top-ranked model | ZooD top-1 model · OfficeHome | accuracy: 84.6 -> 85.3 | Helped |
| Add both reweighting and HSIC penalization to the top-ranked model | ZooD top-1 model · TerraIncognita | accuracy: 37.3 -> 53.0 | Helped |
| Add both reweighting and HSIC penalization to the top-ranked model | ZooD top-1 model · DomainNet | accuracy: 48.2 -> 49.2 | Helped |
| Add HSIC independence penalization (ablation) | Single + Rew · PACS | accuracy: 96.3 -> 96.7 | Helped |
| Add reweighting (ablation) | Single + HSIC · VLCS | accuracy: 81.5 -> 81.4 | Hurt |
| Add reweighting (ablation) | Single + HSIC · OfficeHome | accuracy: 85.2 -> 85.3 | Helped |
| Add reweighting (ablation) | Single + HSIC · TerraIncognita | accuracy: 52.3 -> 53.0 | Helped |
| Add reweighting (ablation) | Single + HSIC · DomainNet | accuracy: 49.2 -> 49.2 | No clear effect |
| Add HSIC independence penalization to a Top-3 ensemble (ablation) | ZooD Top-3 ensemble with reweighting · OfficeHome | accuracy: 85.1 -> 86.0 | Helped |
| Add HSIC independence penalization to a Top-3 ensemble (ablation) | ZooD Top-3 ensemble with reweighting · DomainNet | accuracy: 50.6 -> 51.4 | Helped |
Closest papers by meaning
- Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning (NeurIPS 2025 · similarity 0.89)
- Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data (NeurIPS 2025 · similarity 0.87)
- Unraveling the Key Components of OOD Generalization via Diversification (ICLR 2024 · similarity 0.87)
- When can in-context learning generalize out of task distribution? (ICML 2025 · similarity 0.87)
- LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization (NeurIPS 2024 · similarity 0.87)
- Nexus: Same Pretraining Loss, Better Downstream Generalization via Common Minima (NeurIPS 2026 · 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.