Research map / Label-efficient and robust learning / Knowledge distillation
Adversarial Teacher-Student Representation Learning for Domain Generalization
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 |
|---|---|---|---|
| replace hand-crafted random augmentation with learned adversarial novel-domain augmenter (ablation) | Ours · PACS ResNet-50 avg | top-1 accuracy (%): 82.8 -> 88.1 | Helped |
| replace jigsaw puzzle with learned augmenter (ablation) | Ours · PACS ResNet-50 avg | top-1 accuracy (%): 85.5 -> 88.1 | Helped |
| teacher-student with EMA teacher instead of Siamese shared-parameter architecture (ablation) | Ours · PACS ResNet-50 avg | top-1 accuracy (%): 85.8 -> 88.1 | Helped |
| deploy EMA teacher instead of student (ablation) | Ours · PACS ResNet-50 avg | top-1 accuracy (%): 86.0 -> 88.1 | Helped |
| update teacher with EMA while training student (vs fixed teacher) (ablation) | student network · PACS ResNet-50 avg | top-1 accuracy (%): 84.9 -> 86.0 | Helped |
| increase EMA momentum tau from 0.9 to 0.999 (ablation) | Ours · Office-Home ResNet-50 avg | top-1 accuracy (%): 70.6 -> 73.3 | Helped |
| use proposed method instead of MixStyle | PACS ResNet-18 · PACS avg | top-1 accuracy (%): 83.7 -> 85.3 | Helped |
| use proposed method instead of DeepAll in single-source DG | ResNet-50 · Single-source DomainNet avg | top-1 accuracy (%): 24.1 -> 34.1 | Helped |
Closest papers by meaning
- Domain Invariant Representation Learning with Domain Density Transformations (NeurIPS 2021 · similarity 0.89)
- Learning to Learn Single Domain Generalization (CVPR 2020 · similarity 0.89)
- Sharpness-Aware Model-Agnostic Long-Tailed Domain Generalization (AAAI 2024 · similarity 0.86)
- Impartial Adversarial Distillation: Addressing Biased Data-Free Knowledge Distillation via Adaptive Constrained Optimization (AAAI 2024 · similarity 0.86)
- Hybrid Data-Free Knowledge Distillation (AAAI 2025 · similarity 0.86)
- Adversarial Domain Prompt Tuning and Generation for Single Domain Generalization (CVPR 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.