Research map / Image generation / GANs
DigGAN: Discriminator gradIent Gap Regularization for GAN Training 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 DigGAN regularization to BigGAN | BigGAN · CIFAR-100, 10% data | FID: 73.01 -> 27.61 | Helped |
| Add DigGAN regularization to BigGAN | BigGAN · CIFAR-100, 20% data | FID: 33.64 -> 21.79 | Helped |
| Add DigGAN regularization to BigGAN | BigGAN · CIFAR-100, 100% data | FID: 13.54 -> 12.93 | Helped |
| Add DigGAN regularization to BigGAN | BigGAN · CIFAR-10, 10% data | FID: 36.35 -> 23.75 | Helped |
| Add DigGAN regularization to BigGAN | BigGAN · Tiny-ImageNet, 10% data | FID: 130.77 -> 84.27 | Helped |
| Add DigGAN regularization to StyleGAN+ADA | StyleGAN2+ADA · 100-shot Obama | FID: 49.78 -> 41.34 | Helped |
| Add DiffAug alongside DigGAN | BigGAN + DiffAug · CIFAR-100, 10% data | FID: 33.70 -> 24.59 | Helped |
| Use same-class pairing instead of random pairing (ablation) | BigGAN + DigGAN · CIFAR-100, 10% data | FID: 27.61 -> 28.08 | Hurt |
| Use same-class pairing instead of random pairing (ablation) | BigGAN + DigGAN · CIFAR-10, 10% data | FID: 23.75 -> 21.53 | Helped |
| Use gradient-magnitude pairing instead of random pairing (ablation) | BigGAN + DigGAN · CIFAR-100, 10% data | FID: 27.61 -> 47.75 | Hurt |
| Use gradient-magnitude pairing instead of random pairing (ablation) | BigGAN + DigGAN · CIFAR-10, 10% data | FID: 23.75 -> 27.64 | Hurt |
| Increase DigGAN regularization strength (ablation) | BigGAN + DigGAN · CIFAR-100, 10% data | FID | Mixed |
Closest papers by meaning
- A Large-Scale Study on Regularization and Normalization in GANs (ICML 2019 · similarity 0.90)
- AdaGAN: Boosting Generative Models (NeurIPS 2017 · similarity 0.90)
- Improving GAN with Neighbors Embedding and Gradient Matching (AAAI 2019 · similarity 0.90)
- Training Generative Adversarial Networks with Limited Data (NeurIPS 2020 · similarity 0.90)
- MCGAN: Enhancing GAN Training with Regression-Based Generator Loss (AAAI 2025 · similarity 0.89)
- MS$^3$D: A RG Flow-Based Regularization for GAN Training with Limited Data (ICML 2024 · similarity 0.89)
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.