Research map / Image generation / GANs
Training Generative Adversarial Networks with Limited Data
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 adaptive discriminator augmentation | StyleGAN2 · CIFAR-10 | FID: 5.59 -> 2.42 | Helped |
| add adaptive discriminator augmentation | StyleGAN2 · FFHQ / LSUN Cat subsets | FID | Helped |
| adapt augmentation strength p instead of best fixed p from grid search (ablation) | stochastic discriminator augmentation · FFHQ subsets | FID | Helped |
| add image-space filtering, noise, and cutout augmentations (ablation) | discriminator augmentation · FFHQ 2k | FID | No clear effect |
| add pixel blitting and geometric augmentations (ablation) | discriminator augmentation · FFHQ 2k | FID | Helped |
| apply fixed discriminator augmentations with 140k training images (ablation) | StyleGAN2 · FFHQ 140k | FID | Hurt |
| reduce discriminator capacity | StyleGAN2 · FFHQ subsets | FID | Hurt |
| add bCR on top of ADA | StyleGAN2 + ADA · FFHQ / LSUN Cat | FID | Helped |
| add Freeze-D to ADA in transfer learning | StyleGAN2 + ADA · FFHQ/LSUN transfer | FID | Helped |
Closest papers by meaning
- On Leveraging Pretrained GANs for Generation with Limited Data (ICML 2020 · similarity 0.92)
- Improving Generalization and Stability of Generative Adversarial Networks (ICLR 2019 · similarity 0.92)
- On Stabilizing Generative Adversarial Training With Noise (CVPR 2019 · similarity 0.92)
- Training Generative Adversarial Networks in One Stage (CVPR 2021 · similarity 0.92)
- Progressive Growing of GANs for Improved Quality, Stability, and Variation (ICLR 2018 · similarity 0.91)
- Mixed batches and symmetric discriminators for GAN training (ICML 2018 · similarity 0.91)
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.