Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Generalization without Excess Empirical Risk
Ozan Sener, Vladlen Koltun
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 |
|---|---|---|---|
| Apply SDG instead of standard optimization to CORAL | CORAL · iWildCam | Macro-F1: 32.8 \pm 0.1 -> 34.6 \pm 1.2 | Improved |
| Apply SDG instead of standard optimization to CORAL | CORAL · Camelyon17 | Avg Acc: 59.5 \pm 7.7 -> 75.2 \pm 4.4 | Improved |
| Apply SDG instead of standard optimization to CORAL | CORAL · OGB-MolPCBA | AP: 17.9 \pm 0.5 -> 25.8 \pm 0.1 | Improved |
| Apply SDG instead of standard optimization to CORAL | CORAL · FMoW | WorstR Acc: 31.0 \pm 0.4 -> 33.9 \pm 0.9 | Improved |
| Apply SDG instead of standard optimization to CORAL | CORAL · Amazon | 10th-tile Acc: 52.9 \pm 0.8 -> 53.7 \pm 0.6 | Improved |
| Apply SDG instead of standard optimization to CORAL | CORAL · py150 | MethodClass: 65.9 \pm 0.1 -> 68.3 \pm 0.1 | Improved |
| Apply SDG instead of standard optimization to CORAL | CORAL · PovertyMap | WstPearsonR: 0.44 \pm 0.06 -> 0.49 \pm 0.05 | Improved |
| Apply SDG to FISH | FISH · iWildCam | Macro-F1: 22.0 \pm 1.8 -> 32.9 \pm 0.2 | Improved |
| Apply SDG to FISH | FISH · Camelyon17 | Avg Acc: 74.7 \pm 7.1 -> 76.2 \pm 8.4 | Improved |
| Apply SDG to FISH | FISH · OGB-MolPCBA | AP: 22.6 \pm 0.3 -> 26.1 \pm 0.5 | Improved |
| Apply SDG to FISH | FISH · FMoW | WorstR Acc: 34.6 \pm 0.2 -> 34.6 \pm 0.3 | No clear effect |
| Apply SDG to FISH | FISH · PovertyMap | WstPearsonR: 0.35 \pm 0.03 -> 0.46 \pm 0.03 | Improved |
Closest papers by meaning
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.90)
- Understanding Domain Generalization: A Noise Robustness Perspective (ICLR 2024 · similarity 0.89)
- Lost Domain Generalization Is a Natural Consequence of Lack of Training Domains (AAAI 2024 · similarity 0.89)
- Set Valued Predictions For Robust Domain Generalization (ICML 2025 · similarity 0.88)
- Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization (AAAI 2024 · similarity 0.88)
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · 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.
