Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Generalization via Gradient Surgery
Lucas Mansilla, Rodrigo Echeveste, Diego H. Milone, Enzo Ferrante
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 |
|---|---|---|---|
| add Agr-Sum gradient agreement (zero conflicting components) | Deep-All · PACS average | accuracy (%): 63.89 -> 65.80 | Improved |
| add Agr-Rand gradient agreement (random conflicting components) | Deep-All · PACS average | accuracy (%): 63.89 -> 65.30 | Improved |
| add Agr-Sum gradient agreement | Deep-All · Office-Home average | accuracy (%): 44.71 -> 46.09 | Improved |
| add Agr-Rand gradient agreement | Deep-All · Office-Home average | accuracy (%): 44.71 -> 46.01 | Improved |
| add Agr-Sum gradient agreement | Deep-All · VLCS average | accuracy (%): 70.66 -> 70.61 | No clear effect |
| add PCGrad projection | Deep-All · PACS average | accuracy (%): 63.89 -> 63.77 | No clear effect |
| add PCGrad projection | Deep-All · Office-Home average | accuracy (%): 44.71 -> 44.74 | No clear effect |
| add Agr-Sum gradient agreement | Deep-All · PACS target Cartoon | accuracy (%): 57.80 -> 61.52 | Improved |
| add Agr-Sum gradient agreement | Deep-All · PACS target Photo | accuracy (%): 86.87 -> 86.18 | No clear effect |
| add Agr-Sum gradient agreement | Deep-All · Office-Home target Real-World | accuracy (%): 55.95 -> 58.29 | Improved |
| add Agr-Sum gradient agreement | Deep-All · VLCS target Sketch | accuracy (%): 63.96 -> 62.98 | Hurt |
| add IRM | Deep-All · Office-Home average | accuracy (%): 44.71 -> 43.59 | Hurt |
Closest papers by meaning
- Learning to Generalize: Meta-Learning for Domain Generalization (AAAI 2018 · similarity 0.90)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.89)
- Gradient Matching for Domain Generalization (ICLR 2022 · similarity 0.89)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.87)
- Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes (CVPR 2025 · similarity 0.87)
- Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization (CVPR 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.
