Research map / Label-efficient and robust learning / Domain adaptation and generalization
Navigating the Flatlands: Dual Adaptive Sharpness-Aware Minimization for Domain Generalization
Junwen He, Yang He, Lebing Zheng, Zirui Yin, Hong-Yu Zhang, Yulong Wang
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 AMDF multi-directional flatness module to SAM (ablation) | SAM · DG average (5 datasets) | accuracy (%): 64.1 -> 65.1 | Improved |
| add DAS domain-adaptive scaling on top of AMDF (ablation) | DA-SAM · DG average (5 datasets) | accuracy (%): 65.1 -> 66.0 | Improved |
| add AMDF to SAM (ablation) | SAM · TerraInc | accuracy (%): 45.7 -> 48.7 | Improved |
| add DAS on top of AMDF (ablation) | DA-SAM · TerraInc | accuracy (%): 48.7 -> 50.0 | Improved |
| add DAS on top of AMDF (ablation) | DA-SAM · OfficeHome | accuracy (%): 68.2 -> 68.4 | No clear effect |
| use DA-SAM instead of SAM | SAM · OfficeHome | accuracy (%): 68.0 -> 68.4 | No clear effect |
| use DA-SAM instead of SAM | SAM · DG average (5 datasets) | accuracy (%): 64.1 -> 66.0 | Improved |
| probe every 30 iterations instead of every iteration (intermittent probing) (ablation) | DA-SAM · DG average (5 datasets) | accuracy (%): 66.0 -> 66.1 | Improved |
| probe every 10 iterations (ablation) | DA-SAM · DG average (5 datasets) | accuracy (%): 66.0 -> 65.4 | Hurt |
| probe every 60 iterations (ablation) | DA-SAM · DG average (5 datasets) | training time (s/iter): 0.425 -> 0.114 | Improved |
| replace Hessian-based AdaHessian with DA-SAM random probing | AdaHessian · memory (MB) | memory: 6785 -> 4970 | Improved |
Closest papers by meaning
- Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts (ICLR 2024 · similarity 0.92)
- Seeking Consistent Flat Minima for Better Domain Generalization via Refining Loss Landscapes (CVPR 2025 · similarity 0.92)
- Tilted Sharpness-Aware Minimization (ICML 2025 · similarity 0.90)
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · similarity 0.89)
- Sharpness-Aware Minimization Efficiently Selects Flatter Minima Late In Training (ICLR 2025 · similarity 0.89)
- Improving Sharpness-Aware Minimization by Lookahead (ICML 2024 · similarity 0.88)
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.
