Research map / Learning theory and algorithms / Kernels and regression theory
Model-Based Domain Generalization
Alexander Robey, George J. Pappas, Hamed Hassani
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 |
|---|---|---|---|
| enforce prediction invariance to learned domain transformations with primal-dual training | MBDG · Camelyon17-WILDS OOD validation | accuracy: 73.3 ± 9.9 -> 94.8 ± 0.4 | Improved |
| enforce prediction invariance to learned domain transformations with primal-dual training | MBDG · FMoW-WILDS OOD validation | accuracy: 51.3 (0.4) -> 52.3 ± 0.5 | Improved |
| enforce invariance to learned image transformations | MBDG · ColoredMNIST Avg | accuracy: 40.7 -> 68.5 | Improved |
| enforce invariance to learned image transformations | MBDG · ColoredMNIST -90% | accuracy: 23.1 ± 10.7 -> 63.5 ± 0.0 | Improved |
| enforce prediction invariance using learned domain transformations | MBDG · PACS Avg | accuracy: 83.7 -> 85.6 | Improved |
| enforce prediction invariance using learned domain transformations | MBDG · PACS Sketch (S) | accuracy: 78.6 ± 1.4 -> 85.2 ± 0.2 | Improved |
| replace primal-dual invariance training with ERM plus generated-image augmentation (ablation) | MBDG · ColoredMNIST Avg | accuracy: 68.5 -> 48.3 | Hurt |
| use generated-image augmentation in the training objective instead of primal-dual constraint enforcement (ablation) | MBDG · ColoredMNIST Avg | accuracy: 68.5 -> 59.0 | Hurt |
| replace adaptive dual updates with a fixed regularization weight (ablation) | MBDG · ColoredMNIST Avg | accuracy: 68.5 -> 58.1 | Hurt |
| use a fixed regularization weight rather than dual ascent (ablation) | MBDG · ColoredMNIST G-invariance constraint satisfaction | distReg | Hurt |
Closest papers by meaning
- Improving Generalization With Domain Convex Game (CVPR 2023 · similarity 0.91)
- In Search of Lost Domain Generalization (ICLR 2021 · similarity 0.91)
- Set Valued Predictions For Robust Domain Generalization (ICML 2025 · similarity 0.89)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.89)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.89)
- Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains (AAAI 2024 · similarity 0.89)
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.
