Research map / Image generation / GANs
Improved Techniques for Training Score-Based Generative Models
Yang Song, Stefano Ermon
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| Use NCSNv2 techniques instead of vanilla NCSN | Score-based generative modeling · CelebA 64×64 | HYPE∞ (%): 19.8 -> 37.3 | Improved |
| Add EMA to the original NCSN (ablation) | NCSN · CIFAR-10 and CelebA | FID stability | Improved |
| Add EMA and the noise-scale, conditioning, and sampler-configuration technique group (ablation) | NCSN · CIFAR-10 and CelebA | sample quality (visual inspection) | Improved |
| Use all proposed techniques together rather than vanilla NCSN (ablation) | NCSN · CIFAR-10 and CelebA | FID | Improved |
| Use NCSNv2 rather than NCSN | Score-based generative modeling · CIFAR-10 | Inception score | Hurt |
| Use NCSNv2 rather than NCSN | Score-based generative modeling · CelebA 64×64 | HYPE∞ (%): 19.8 -> 37.3 | Improved |
Closest papers by meaning
- ScoreMix: A Scalable Augmentation Strategy for Training GANs With Limited Data (TPAMI 2022 · similarity 0.90)
- Large Scale GAN Training for High Fidelity Natural Image Synthesis (ICLR 2019 · similarity 0.90)
- Classification Accuracy Score for Conditional Generative Models (NeurIPS 2019 · similarity 0.89)
- SMaRt: Improving GANs with Score Matching Regularity (ICML 2024 · similarity 0.89)
- Adversarial Score Distillation: When score distillation meets GAN (CVPR 2024 · similarity 0.88)
- Anomaly Score: Evaluating Generative Models and Individual Generated Images based on Complexity and Vulnerability (CVPR 2024 · 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.
