Research map / Label-efficient and robust learning / Domain adaptation and generalization
Generalizable Decision Boundaries: Dualistic Meta-Learning for Open Set Domain Generalization
Xiran Wang, Jian Zhang, Lei Qi, Yinghuan Shi
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 class-wise gradient matching to domain-wise matching (MEDIC versus MLDG) with multi-binary classifier (ablation) | MEDIC · PACS ResNet50 | H-score average: 79.9 -> 83.0 | Improved |
| add class-wise gradient matching to domain-wise matching (MEDIC versus MLDG) (ablation) | MEDIC · PACS ResNet50 | OSCR average: 82.5 -> 84.9 | Improved |
| add multi-binary classifier to training and use it at inference (ablation) | MEDIC · PACS ResNet50 | H-score average: 80.1 -> 83.0 | Improved |
| add multi-binary classifier to ERM (ablation) | ERM · PACS ResNet50 | H-score average: 77.2 -> 79.9 | Improved |
| share parameters between close set and multi-binary classifier (ablation) | MEDIC · PACS ResNet50 | H-score average: 83.0 -> 82.5 | No clear effect |
| use class-wise matching only without domain-wise matching (ablation) | MEDIC · PACS ResNet50 | H-score average: 83.0 -> 80.3 | Hurt |
| MEDIC versus DAML on PACS ResNet18 | MEDIC · PACS ResNet18 | OSCR average: 73.69 -> 77.89 | Improved |
| MEDIC versus MVDG on PACS ResNet18 | MEDIC · PACS ResNet18 | OSCR average: 75.82 -> 77.89 | Improved |
| MEDIC versus SWAD on close set accuracy | MEDIC · PACS ResNet50 close set | accuracy: 88.1 -> 88.3 | No clear effect |
| MEDIC versus MVDG close set accuracy on PACS ResNet18 | MEDIC · PACS ResNet18 | accuracy average: 86.41 -> 86.20 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.
- MVDG — MVDG: A Unified Multi-View Framework for Domain Generalization (ECCV 2022) · better on 4 of 5 shared results
- SWAD — SWAD: Domain Generalization by Seeking Flat Minima (NeurIPS 2021) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler (NeurIPS 2024 · similarity 0.88)
- Balanced Direction from Multifarious Choices: Arithmetic Meta-Learning for Domain Generalization (CVPR 2025 · similarity 0.88)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.87)
- Set Valued Predictions For Robust Domain Generalization (ICML 2025 · similarity 0.86)
- Rethinking Multi-domain Generalization with A General Learning Objective (CVPR 2024 · similarity 0.86)
- One-Step Generalization Ratio Guided Optimization for Domain Generalization (ICML 2025 · 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.
