Research map / Label-efficient and robust learning / Domain adaptation and generalization
Towards Principled Disentanglement for Domain Generalization
Check 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 |
|---|---|---|---|
| use DDG instead of CORAL | RotatedMNIST domain generalization · RotatedMNIST | accuracy (%): 98.2 -> 98.4 | Helped |
| use DDG instead of MLDG | Camelyon17-WILDS domain generalization · Camelyon17-WILDS | accuracy (%): 96.1 -> 96.6 | Helped |
| use DDG instead of ERM | PACS domain generalization · PACS | accuracy (%): 87.2 -> 88.9 | Helped |
| use DDG instead of CDANN | VLCS domain generalization · VLCS | accuracy (%): 80.2 -> 80.0 | Hurt |
| add learned data augmentation to DDG (ablation) | DDG · RotatedMNIST | accuracy (%): 98.4 -> 98.4 | No clear effect |
| add learned data augmentation to DDG (ablation) | DDG · Camelyon17-WILDS | accuracy (%): 96.6 -> 96.9 | Helped |
| add learned data augmentation to DDG (ablation) | DDG · PACS | accuracy (%): 88.9 -> 89.3 | Helped |
| add learned data augmentation to DDG (ablation) | DDG · VLCS | accuracy (%): 80.0 -> 80.7 | Helped |
Closest papers by meaning
- Demystifying Inter-Class Disentanglement (ICLR 2020 · similarity 0.89)
- Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization (NeurIPS 2025 · similarity 0.87)
- Disentangled Prompt Representation for Domain Generalization (CVPR 2024 · similarity 0.87)
- Towards Generalizing to Unseen Domains with Few Labels (CVPR 2024 · similarity 0.86)
- AdvST: Revisiting Data Augmentations for Single Domain Generalization (AAAI 2024 · similarity 0.86)
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · similarity 0.86)
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.