Research map / Image generation / GANs
Diffusion-GAN: Training GANs with Diffusion
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 diffusion-based instance noise to StyleGAN2 | StyleGAN2 · CIFAR-10 | Recall: 0.41 -> 0.58 | Helped |
| Add diffusion-based instance noise to StyleGAN2 | StyleGAN2 · CelebA | FID: 2.32 -> 1.69 | Helped |
| Add diffusion-based instance noise to StyleGAN2 | StyleGAN2 · LSUN-Bedroom | Recall: 0.32 -> 0.32 | No clear effect |
| Add diffusion-based instance noise to ProjectedGAN features | ProjectedGAN · CIFAR-10 | FID: 3.10 -> 2.54 | Helped |
| Add diffusion-based instance noise to ProjectedGAN features | ProjectedGAN · STL-10 | Recall: 0.35 -> 0.35 | No clear effect |
| Add diffusion-based instance noise to InsGen | InsGen · FFHQ (200 images) | FID: 102.58 -> 63.34 | Helped |
| Use priority rather than uniform timestep sampling (ablation) | Diffusion-GAN · Most evaluated cases | generation performance | Helped |
| Use priority rather than uniform timestep sampling (ablation) | Diffusion-GAN · FFHQ | generation performance | Hurt |
| Set d_target to 0.8 rather than 0.6 (ablation) | Diffusion StyleGAN2 · FFHQ | FID | Helped |
Closest papers by meaning
- Revisiting Diffusion Models: From Generative Pre-training to One-Step Generation (ICML 2025 · similarity 0.93)
- You Only Sample Once: Taming One-Step Text-to-Image Synthesis by Self-Cooperative Diffusion GANs (ICLR 2025 · similarity 0.90)
- Bridging Data Gaps in Diffusion Models with Adversarial Noise-Based Transfer Learning (ICML 2024 · similarity 0.89)
- Consistency-GAN: Training GANs with Consistency Model (AAAI 2024 · similarity 0.89)
- E$^2$GAN: Efficient Training of Efficient GANs for Image-to-Image Translation (ICML 2024 · similarity 0.88)
- Structure-Guided Adversarial Training of Diffusion Models (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.