Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning from Extrinsic and Intrinsic Supervisions for Domain Generalization
Shujun Wang, Lequan Yu, Caizi Li, Chi-Wing Fu, Pheng-Ann Heng
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 extrinsic momentum metric learning to baseline (ablation) | DeepAll ResNet-50 · PACS average | accuracy: 81.15 -> 84.14 | Improved |
| add intrinsic jigsaw self-supervision to baseline (ablation) | DeepAll ResNet-50 · PACS average | accuracy: 81.15 -> 83.88 | Improved |
| combine extrinsic and intrinsic supervision (ablation) | EISNet ResNet-50 · PACS average | accuracy: 84.14 -> 85.84 | Improved |
| use semi-hard negative selector instead of random (ablation) | EISNet AlexNet · PACS Sketch | accuracy: 65.38 -> 68.08 | Improved |
| use K-hard negative selector instead of semi-hard (ablation) | EISNet AlexNet · PACS Sketch | accuracy: 68.08 -> 70.25 | Improved |
| increase memory bank size from 128 to 1024 (K 32 to 256) (ablation) | EISNet AlexNet · PACS Sketch | accuracy: 67.93 -> 70.25 | Improved |
| increase K from 256 to 512 (ablation) | EISNet AlexNet · PACS Sketch | accuracy | Hurt |
| use large momentum coefficient 0.999 for MuEncoder (ablation) | EISNet AlexNet · PACS Sketch | accuracy | Improved |
| EISNet instead of MASF with ResNet-50 | MASF · PACS average | accuracy: 82.67 -> 85.84 | Improved |
| EISNet instead of MASF with AlexNet | MASF · VLCS average | accuracy: 74.11 -> 74.67 | Improved |
| EISNet instead of MASF with ResNet-18 | MASF · PACS average | accuracy: 81.04 -> 82.15 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MetaReg — MetaReg: Towards Domain Generalization using Meta-Regularization (NeurIPS 2018) · better on 1 of 1 shared result
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
- Domain Generalization by Solving Jigsaw Puzzles (CVPR 2019 · similarity 0.88)
- Domain Generalization via Model-Agnostic Learning of Semantic Features (NeurIPS 2019 · similarity 0.87)
- Object-Aware Domain Generalization for Object Detection (AAAI 2024 · similarity 0.84)
- When Domain Generalization meets Generalized Category Discovery: An Adaptive Task-Arithmetic Driven Approach (CVPR 2025 · similarity 0.84)
- Gradient-Guided Annealing for Domain Generalization (CVPR 2025 · similarity 0.84)
- G-NAS: Generalizable Neural Architecture Search for Single Domain Generalization Object Detection (AAAI 2024 · similarity 0.84)
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.
