Research map / Label-efficient and robust learning / Domain adaptation and generalization
Progressive Few-Shot Adaptation of Generative Model with Align-Free Spatial Correlation
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 |
|---|---|---|---|
| Use progressive align-free spatial correlation adaptation | StyleGAN2 adaptation · Face→Anime 5-shot | FID: 86.83 vs 84.34 | Helped |
| Use progressive align-free spatial correlation adaptation | StyleGAN2 adaptation · Face→Sunglasses 5-shot | FID: 65.87 -> 44.46 | Helped |
| Use progressive align-free spatial correlation adaptation | StyleGAN2 adaptation · Face→Babies 5-shot | FID: 89.97 -> 78.70 | Helped |
| Use progressive align-free spatial correlation adaptation | StyleGAN2 adaptation · Face→Sketches 5-shot | FID: 56.71 -> 67.72 | Hurt |
| Use progressive align-free spatial correlation adaptation | StyleGAN2 adaptation · Face→Amedeo 5-shot | IS-mean: 3.73 -> 3.97 | Helped |
| Use progressive align-free spatial correlation adaptation | StyleGAN2 adaptation · Face→Anime 5-shot | IS-mean: 1.59 -> 2.30 | Helped |
| Add align-free spatial correlation loss (LASC) (ablation) | Baseline (IDC) · Face→Anime 5-shot | FID: 95.13 -> 93.19 | Helped |
| Add progressive adaptation (ablation) | LASC adaptation · Face→Anime 5-shot | FID: 93.19 -> 86.26 | Helped |
| Add edge-based importance sampling (ablation) | LASC with progressive adaptation · Face→Anime 5-shot | FID: 86.26 -> 84.34 | Helped |
| Use the full method instead of IDC | StyleGAN2 adaptation · Face→Amedeo 5-shot | IC-LPIPS: 0.56 -> 0.61 | Helped |
| Use the full method instead of IDC | StyleGAN2 adaptation · Face→Sketches 5-shot | IC-LPIPS: 0.41 -> 0.45 | Helped |
| Use the full method instead of IDC | StyleGAN2 adaptation · Face→Babies 5-shot | IC-LPIPS: 0.51 -> 0.54 | Helped |
Closest papers by meaning
- Few Shot Generative Model Adaption via Relaxed Spatial Structural Alignment (CVPR 2022 · similarity 0.89)
- Few-shot Image Generation via Adaptation-Aware Kernel Modulation (NeurIPS 2022 · similarity 0.87)
- Few-shot Hybrid Domain Adaptation of Image Generator (ICLR 2024 · similarity 0.87)
- ProKeR: A Kernel Perspective on Few-Shot Adaptation of Large Vision-Language Models (CVPR 2025 · similarity 0.85)
- DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning (NeurIPS 2024 · similarity 0.85)
- FouRA: Fourier Low-Rank Adaptation (NeurIPS 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.