Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Generalization via Entropy Regularization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 entropy regularization + Lcel to adversarial DG (Ours vs Basic-Adv) | AlexNet · PACS | accuracy: 75.31 -> 75.67 | Helped |
| Ours vs DeepAll | AlexNet · PACS | accuracy: 73.57 -> 75.67 | Helped |
| Ours vs Basic-Adv | AlexNet · VLCS E2E | accuracy: 74.26 -> 74.38 | No clear effect |
| Ours vs Basic-Adv | ResNet-18 · PACS | accuracy: 80.77 -> 81.38 | Helped |
| Ours vs Basic-Adv | ResNet-50 · PACS | accuracy: 85.11 -> 85.34 | Helped |
| add domain adversarial loss with alpha1=0.5 (ablation) | DeepAll · PACS | accuracy: 73.57 -> 75.31 | Helped |
| raise adversarial weight to 1.0 (ablation) | DeepAll · PACS | accuracy: 73.57 -> 69.68 | Hurt |
| add entropy regularization (alpha2=0.01) to full objective (ablation) | adv + Lcel · PACS | accuracy: 74.99 -> 75.67 | Helped |
| add entropy regularization alone to adversarial model (ablation) | Basic-Adv · PACS | accuracy: 75.31 -> 75.21 | No clear effect |
| add Lcel auxiliary classifier loss (ablation) | adv + ER · PACS | accuracy: 75.21 -> 75.67 | Helped |
| use class-weighted cross-entropy (ablation) | Ours · PACS | accuracy: 75.58% -> 75.67% | No clear effect |
Closest papers by meaning
- Domain Generalization via Conditional Invariant Representations (AAAI 2018 · similarity 0.91)
- Domain Invariant Representation Learning with Domain Density Transformations (NeurIPS 2021 · similarity 0.91)
- Failure Modes of Domain Generalization Algorithms (CVPR 2022 · similarity 0.91)
- Domain Generalization With Adversarial Feature Learning (CVPR 2018 · similarity 0.91)
- Robust Domain Generalization under Divergent Marginal and Conditional Distributions (NeurIPS 2026 · similarity 0.90)
- Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization (AAAI 2024 · similarity 0.90)
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.