Research map / Label-efficient and robust learning / Domain adaptation and generalization
Quantifying and Improving Transferability in Domain Generalization
Guojun Zhang, Han Zhao, Yaoliang Yu, Pascal Poupart
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 |
|---|---|---|---|
| Train features with the Transfer algorithm's adversarial objective for low source error and low error variation among nearby classifiers | Domain generalization on RotatedMNIST, PACS, Office-Home, and WILDS-FMoW · RotatedMNIST, PACS, Office-Home, WILDS-FMoW | target accuracy | Improved |
| Perturb the learned classifier within a neighborhood | Mixup · PACS | target accuracy: more than 30% | Hurt |
| Perturb the learned classifier within a neighborhood | DANN · RotatedMNIST | target accuracy: ~10% | Hurt |
| Use the Transfer algorithm instead of existing domain-generalization algorithms | Domain generalization · Office-Home and WILDS-FMoW | target accuracy | Improved |
Closest papers by meaning
- Larger Norm More Transferable: An Adaptive Feature Norm Approach for Unsupervised Domain Adaptation (ICCV 2019 · similarity 0.90)
- Adversarially Robust Models may not Transfer Better: Sufficient Conditions for Domain Transferability from the View of Regularization (ICML 2022 · similarity 0.89)
- Domain Adaptation with Conditional Transferable Components (ICML 2016 · similarity 0.88)
- Wasserstein Transfer Learning (NeurIPS 2025 · similarity 0.88)
- Transportable Representations for Domain Generalization (AAAI 2024 · similarity 0.88)
- On Transferring Transferability: Towards a Theory for Size Generalization (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.
