StyleSwin (DINOv2)

Reported on 3 benchmarks across 1 task · 1 paper · 1 SOTA

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

Medical3 results

Image GenerationonFFHQ 256 x 256
Precision· 2021-12-20
0.79
best: 0.92 (LDM (DINOv2))
SOTA
StyleSwin: Transformer-based GAN for High-resolution Image Generation arXiv:2112.10762
Image GenerationonFFHQ 256 x 256
FD· 2021-12-20
300.18
best: 592.26 (Projected-GAN (DINOv2))
StyleSwin: Transformer-based GAN for High-resolution Image Generation arXiv:2112.10762
Image GenerationonFFHQ 256 x 256
Recall· 2021-12-20
0.28
best: 0.76 (LDM (DINOv2))
StyleSwin: Transformer-based GAN for High-resolution Image Generation arXiv:2112.10762