Research map / Label-efficient and robust learning / Domain adaptation and generalization
MADG: Margin-based Adversarial Learning for Domain Generalization
Aveen Dayal, Vimal K B, Linga Reddy Cenkeramaddi, C Krishna Mohan, Abhinav Kumar, Vineeth N. Balasubramanian
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 |
|---|---|---|---|
| use margin-based MDD adversarial alignment (MADG) instead of 0-1 loss DANN/CDANN | DomainBed · average over 5 datasets | accuracy (%): 63.8 -> 66.0 | Improved |
| MADG versus ERM | DomainBed · average over 5 datasets | accuracy (%): 65.0 -> 66.0 | Improved |
| MADG versus best baselines per dataset | DomainNet · DomainNet | accuracy (%): 43.4 -> 39.9 | Hurt |
| set margin rho_hat to 1.5 instead of 3 (ablation) | MADG · PACS | accuracy (%): 85.7 -> 86.5 | Improved |
| set margin rho_hat to 1.5 instead of 1 (ablation) | MADG · VLCS | accuracy (%): 78.4 -> 78.7 | No clear effect |
| use all pairwise MDD classifiers (j=C(N_S,2)) instead of N_S-1 (ablation) | MADG · TerraIncognita | accuracy (%): 51.1 -> 53.7 | Improved |
| use all pairwise MDD classifiers instead of N_S-1 (ablation) | MADG · VLCS and PACS | accuracy (%): 78.5 -> 78.7; 86.4 -> 86.5 | No clear effect |
| use unit weights on MDD losses instead of average or dynamic weights (ablation) | MADG · PACS | accuracy (%): 86.1 -> 86.5 | Improved |
| MADG versus ERM on Colored MNIST | ERM · ColoredMNIST | accuracy (%): 57.8 -> 65.6 | Improved |
| MADG versus MIRO on OfficeHome | MIRO · OfficeHome | accuracy (%): 71.1 -> 71.3 | No clear effect |
Closest papers by meaning
- Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization (AAAI 2024 · similarity 0.89)
- Is Large-scale Pretraining the Secret to Good Domain Generalization? (ICLR 2025 · similarity 0.87)
- One-Step Generalization Ratio Guided Optimization for Domain Generalization (ICML 2025 · similarity 0.87)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.87)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.87)
- PracticalDG: Perturbation Distillation on Vision-Language Models for Hybrid Domain Generalization (CVPR 2024 · 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.
