Research map / Label-efficient and robust learning / Domain adaptation and generalization
One-Shot Generative Domain Adaptation
Ceyuan Yang, Yujun Shen, Zhiyi Zhang, Yinghao Xu, Jiapeng Zhu, Zhirong Wu, Bolei Zhou
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 lightweight attribute adaptor to FreezeD+ADA baseline (ablation) | FreezeD+ADA · 10-shot Babies | FID: 109.87 -> 53.59 | Improved |
| add attribute classifier (ablation) | GenDA · 10-shot Babies | FID: 53.59 -> 50.37 | Improved |
| add diversity-constraint strategy (ablation) | GenDA · 10-shot Babies | FID: 50.37 -> 47.05 | Improved |
| add attribute adaptor (ablation) | FreezeD+ADA · 10-shot Babies | precision: 0.80 -> 0.57 | Hurt |
| replace lightweight attribute adaptor with two-layer MLP (ablation) | GenDA · Babies one-shot | FID: 80.16 -> 290.22 | Hurt |
| replace lightweight attribute classifier with two-layer MLP (ablation) | GenDA · Babies one-shot | FID: 80.16 -> 132.14 | Hurt |
| use GenDA instead of Cross-Domain on 10-shot | 10-shot adaptation · 10-shot Sketches | FID: 45.67 -> 31.97 | Improved |
| use GenDA instead of FreezeD in one-shot on sunglasses | one-shot adaptation · Sunglasses one-shot | precision: 0.93 -> 0.76 | Hurt |
Closest papers by meaning
- Transferring GANs: generating images from limited data (ECCV 2018 · similarity 0.94)
- Generalized One-shot Domain Adaptation of Generative Adversarial Networks (NeurIPS 2022 · similarity 0.94)
- Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks (NeurIPS 2022 · similarity 0.93)
- Unsupervised Pixel-Level Domain Adaptation With Generative Adversarial Networks (CVPR 2017 · similarity 0.92)
- Few-shot Cross-domain Image Generation via Inference-time Latent-code Learning (ICLR 2023 · similarity 0.91)
- Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks (ICLR 2022 · similarity 0.91)
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.
