StyleGAN2 with DiffAugment

Reported on 6 benchmarks across 2 tasks · 1 paper · 4 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Medical3 results

Medical Image GenerationonSLIVER07
FID· 2023-11-22
4.62
SOTA
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend arXiv:2311.13717
Medical Image GenerationonChestX-ray14
FID· 2023-11-22
3.07
SOTA
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend arXiv:2311.13717
Medical Image GenerationonACDC
FID· 2023-11-22
21.42
best: 21.17 (StyleGAN2-ADA)
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend arXiv:2311.13717

Audio3 results

10-shot image generationonSLIVER07
FID· 2023-11-22
4.62
SOTA
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend arXiv:2311.13717
10-shot image generationonChestX-ray14
FID· 2023-11-22
3.07
SOTA
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend arXiv:2311.13717
10-shot image generationonACDC
FID· 2023-11-22
21.42
best: 21.17 (StyleGAN2-ADA)
Feature Extraction for Generative Medical Imaging Evaluation: New Evidence Against an Evolving Trend arXiv:2311.13717