StyleGAN (DINOv2)

Reported on 3 benchmarks across 1 task

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

Medical3 results

Image GenerationonLSUN Bedroom 256 x 256
FD
239.79
best: 636.35 (Projected GAN (DINOv2))
Image GenerationonLSUN Bedroom 256 x 256
Precision
0.85
Image GenerationonLSUN Bedroom 256 x 256
Recall
0.41
best: 0.75 (ADM (dropout, DINOv2))