Research map / Image generation / GANs
Differentiable Augmentation for Data-Efficient GAN Training
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 |
|---|---|---|---|
| Apply differentiable augmentation | StyleGAN2 · CIFAR-10, 20% data | recall: 0.24 -> 0.39 | Helped |
| Apply differentiable augmentation | BigGAN · CIFAR-10, 10% data | GAN-train: 53.1% -> 62.7% | Helped |
| Apply differentiable augmentation | BigGAN · CIFAR-10, 10% data | GAN-test: 72.4% -> 80.9% | Helped |
| Apply differentiable augmentation | BigGAN · CIFAR-10, 10% data, 10k iterations | discriminator training accuracy: 99% -> 90% | Mixed |
| Apply differentiable augmentation | BigGAN · CIFAR-10, 10% data, 10k iterations | discriminator validation accuracy: 18% -> 41% | Helped |
| Add Color to Translation + Cutout (ablation) | BigGAN + Translation + Cutout · CIFAR-10, 10% data | FID: 22 to 20 | Helped |
| Augment real samples only (ablation) | GAN training · CIFAR-10, limited data | GAN performance | Hurt |
| Apply augmentation to the discriminator only (ablation) | GAN training · CIFAR-10, limited data | GAN performance | Hurt |
| Use random scaling, rotations, shearing, smoothing, sharpening, or Gaussian noise (ablation) | GAN training · GAN experiments in the paper | GAN performance | No clear effect |
| Tune the level of each individual augmentation (ablation) | DiffAugment · GAN experiments in the paper | GAN performance | No clear effect |
Closest papers by meaning
- Augmentation-Aware Self-Supervision for Data-Efficient GAN Training (NeurIPS 2023 · similarity 0.90)
- Training Generative Adversarial Networks with Limited Data (NeurIPS 2020 · similarity 0.90)
- Distribution Augmentation for Generative Modeling (ICML 2020 · similarity 0.90)
- A Large-Scale Study on Regularization and Normalization in GANs (ICML 2019 · similarity 0.89)
- Progressive Augmentation of GANs (NeurIPS 2019 · similarity 0.89)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.87)
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.