Research map / Image generation / GANs
Quality Aware 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 SSIM-based quality aware distance penalty | WGAN-GP · CIFAR-10 | FID: 40.2 -> 13.91 | Helped |
| add NIQE-based gradient penalty | WGAN-GP · CIFAR-10 | FID: 40.2 -> 12.4697 | Helped |
| add SSIM-based quality aware distance penalty | WGAN-GP · CIFAR-10 | IS: 7.86 -> 8.37 | Helped |
| add NIQE-based gradient penalty | WGAN-GP · CIFAR-10 | IS: 7.86 -> 7.87 | No clear effect |
| add SSIM-based quality aware distance penalty | WGAN-GP · STL-10 48x48 | FID: 55.1 -> 19.77 | Helped |
| add NIQE-based gradient penalty | WGAN-GP · CelebA 64x64 | FID: 12.89 -> 6.504 | Helped |
| add SSIM-based quality aware distance penalty | WGAN-GP · CelebA 64x64 | FID: 12.89 -> 6.421 | Helped |
| add SSIM-based regularizer to PGGAN | PGGAN · CelebA 256x256 | FID: 62.86 -> 40.83 | Helped |
| add NIQE-based regularizer to PGGAN | PGGAN · CelebA 128x128 | FID: 64.50 -> 49.80 | Helped |
Closest papers by meaning
- Improved Consistency Regularization for GANs (AAAI 2021 · similarity 0.88)
- Progressive Growing of GANs for Improved Quality, Stability, and Variation (ICLR 2018 · similarity 0.88)
- NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs (NeurIPS 2023 · similarity 0.88)
- Geometry Score: A Method For Comparing Generative Adversarial Networks (ICML 2018 · similarity 0.88)
- Analyzing and Improving the Image Quality of StyleGAN (CVPR 2020 · similarity 0.88)
- SMaRt: Improving GANs with Score Matching Regularity (ICML 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.
