Styleformer

Reported on 2 benchmarks across 1 task · 1 paper

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

Medical2 results

Image GenerationonSTL-10
FID· 2021-06-13
15.17
best: 6.91 (Diffusion ProjectedGAN)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector arXiv:2106.07023
Image GenerationonSTL-10
Inception score· 2021-06-13
11.01
best: 13.43 (UNCSN++ (RVE) + ST)
Styleformer: Transformer based Generative Adversarial Networks with Style Vector arXiv:2106.07023