Research map / Image generation / Editing and style transfer
Towards Diverse and Faithful One-shot Adaption of Generative Adversarial Networks
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 |
|---|---|---|---|
| add SCC loss to NADA-style baseline (ablation) | DiFa · FFHQ->Raphael | KID: 149.19 -> 119.36 | Helped |
| add SCC loss to baseline (ablation) | DiFa · FFHQ->Amedeo | KID: 131.03 -> 129.41 | Helped |
| add SCC loss to baseline (ablation) | DiFa · FFHQ->Fernand | FID: 257.27 -> 257.18 | No clear effect |
| add attentive style loss on top of SCC (ablation) | DiFa · FFHQ->Raphael | KID: 119.36 -> 112.72 | Helped |
| add attentive style loss on top of SCC (ablation) | DiFa · FFHQ->Raphael | FID: 180.61 -> 172.34 | Helped |
| add attentive style loss on top of SCC (ablation) | DiFa · FFHQ->Amedeo | KID: 129.41 -> 121.21 | Helped |
| DiFa instead of StyleGAN-NADA | StyleGAN2 · Cat->Wolf | KID: 47.96 -> 33.52 | Helped |
| DiFa instead of Mind The Gap | StyleGAN2 · Cat->Tiger | FID: 46.72 -> 16.26 | Helped |
| DiFa instead of Few-Shot Adaption | StyleGAN2 · FFHQ->Amedeo | FID: 171.56 -> 187.28 | Hurt |
| DiFa instead of Few-Shot Adaption | StyleGAN2 · FFHQ->Raphael | FID: 177.47 -> 172.34 | Helped |
| DiFa instead of FSGAN | StyleGAN2 · FFHQ->Amedeo | KID: 299.64 -> 121.21 | Helped |
Closest papers by meaning
- Generalized One-shot Domain Adaptation of Generative Adversarial Networks (NeurIPS 2022 · similarity 0.95)
- Mind the Gap: Domain Gap Control for Single Shot Domain Adaptation for Generative Adversarial Networks (ICLR 2022 · similarity 0.91)
- Few-Shot Image Generation via Cross-Domain Correspondence (CVPR 2021 · similarity 0.90)
- Unsupervised Pixel-Level Domain Adaptation With Generative Adversarial Networks (CVPR 2017 · similarity 0.89)
- Few-shot Hybrid Domain Adaptation of Image Generator (ICLR 2024 · similarity 0.88)
- Style Adaptation and Uncertainty Estimation for Multi-Source Blended-Target Domain Adaptation (NeurIPS 2024 · 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.