Research map / Label-efficient and robust learning / Domain adaptation and generalization
Learning to Generate Novel Domains for Domain Generalization
Kaiyang Zhou, Yongxin Yang, Timothy Hospedales, Tao Xiang
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 L2A-OT novel-domain generation | Vanilla · Digits-DG avg | accuracy (%): 73.7 -> 78.1 | Improved |
| add L2A-OT novel-domain generation | Vanilla · PACS avg | accuracy (%): 79.5 -> 82.8 | Improved |
| add L2A-OT novel-domain generation | Vanilla · Office-Home avg | accuracy (%): 64.7 -> 65.6 | Improved |
| add L2A-OT novel-domain generation | Vanilla · Duke->Market1501 re-ID | mAP (%): 26.1 -> 30.2 | Improved |
| add L2A-OT instead of CrossGrad perturbation | CrossGrad · Digits-DG avg | accuracy (%): 75.8 -> 78.1 | Improved |
| add CrossGrad | Vanilla · Market1501->Duke re-ID | mAP (%): 26.7 -> 27.1 | No clear effect |
| generate novel domains instead of source-to-source mapping (StarGAN) (ablation) | L2A-OT · Digits-DG avg | accuracy (%): 73.8 -> 78.1 | Improved |
| use source-to-source StarGAN data augmentation (ablation) | Vanilla · Digits-DG avg | accuracy (%): 73.7 -> 73.8 | No clear effect |
| add semantic constraint (cycle-consistency and cross-entropy) (ablation) | L2A-OT · Digits-DG avg | accuracy (%): 73.9 -> 78.1 | Improved |
| add diversity loss (ablation) | L2A-OT · Digits-DG avg | accuracy (%): around 1% | Improved |
| vary number of novel domains Kn (ablation) | L2A-OT · Digits-DG avg | accuracy (%) | No clear effect |
| use three source domains instead of two (ablation) | L2A-OT · Digits-DG MNIST-M | accuracy (%): 60.9 -> 62.5 | Improved |
Closest papers by meaning
- Learning To Diversify for Single Domain Generalization (ICCV 2021 · similarity 0.90)
- Bringing Equity to Classification: Domain Generalization for Domain-Linked Classes (TPAMI 2025 · similarity 0.90)
- Adaptive Methods for Real-World Domain Generalization (CVPR 2021 · similarity 0.90)
- Improving Domain Generalization with Domain Relations (ICLR 2024 · similarity 0.89)
- Unknown Domain Inconsistency Minimization for Domain Generalization (ICLR 2024 · similarity 0.89)
- Towards Generalizing to Unseen Domains with Few Labels (CVPR 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.
