Research map / Label-efficient and robust learning / Domain adaptation and generalization
Domain Re-Modulation for Few-Shot Generative Domain Adaptation
Yi Wu, Ziqiang Li, Chaoyue Wang, Heliang Zheng, Shanshan Zhao, Bin Li, Dacheng Tao
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 |
|---|---|---|---|
| remove the target mapping network (use frozen source mapping) (ablation) | DoRM · 10-shot FFHQ-Babies | FID: 30.31 -> 86.52 | Hurt |
| remove the target mapping network (use frozen source mapping) (ablation) | DoRM · 10-shot FFHQ-Sunglasses | FID: 17.31 -> 74.71 | Hurt |
| remove target affines in low-resolution layers (ablation) | DoRM · 10-shot FFHQ-Babies | FID: 30.31 -> 93.28 | Hurt |
| remove target affines in low-resolution layers (ablation) | DoRM · 10-shot FFHQ-Sunglasses | FID: 17.31 -> 92.42 | Hurt |
| remove target affines in high-resolution layers (ablation) | DoRM · 10-shot FFHQ-Babies | FID: 30.31 -> 37.16 | Hurt |
| remove target affines in high-resolution layers (ablation) | DoRM · 10-shot FFHQ-Sunglasses | FID: 17.31 -> 20.81 | Hurt |
| vary re-modulation weight alpha from 0.5 to 0.005 (ablation) | DoRM · 10-shot FFHQ-Baby | FID: 37.9 -> 30.3 | Improved |
| vary re-modulation weight alpha, sunglasses optimum at 0.2 (ablation) | DoRM · 10-shot FFHQ-Sunglasses | FID: 18.7 -> 17.3 | Mixed |
| use one-layer instead of two-layer target domain classifier (ablation) | DoRM · 10-shot FFHQ-Baby | FID: 30.31 -> 37.15 | Hurt |
| use three-layer instead of two-layer target domain classifier (ablation) | DoRM · 10-shot FFHQ-Baby | FID: 30.31 -> 33.25 | Hurt |
| use source-initialized instead of random-initialized classifier (two layers) (ablation) | DoRM · 10-shot FFHQ-Sunglasses | FID: 17.31 -> 20.40 | Hurt |
| replace full-generator fine-tuning with M&A modules for 10-domain generation | DoRM vs CDC · multi-domain generation | generator parameters: 240M -> 84M | Improved |
Closest papers by meaning
- Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks (NeurIPS 2022 · similarity 0.87)
- Few-shot Hybrid Domain Adaptation of Image Generator (ICLR 2024 · similarity 0.87)
- Maximum Structural Generation Discrepancy for Unsupervised Domain Adaptation (TPAMI 2022 · similarity 0.87)
- Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation (NeurIPS 2025 · similarity 0.86)
- Image is All You Need to Empower Large-scale Diffusion Models for In-Domain Generation (CVPR 2025 · similarity 0.86)
- A General Representation-Based Approach to Multi-Source Domain Adaptation (ICML 2025 · similarity 0.85)
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.
