Conditional Image Generation On Artbench 10
評価指標
FID
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | FID | Paper Title | Repository |
|---|---|---|---|
| StyleGAN2 | 4.491 | Analyzing and Improving the Image Quality of StyleGAN | - |
| BigGAN + CR | 4.647 | Consistency Regularization for Generative Adversarial Networks | - |
| StyleGAN2 + ADA | 2.625 | Training Generative Adversarial Networks with Limited Data | - |
| BigGAN + DiffAug | 4.055 | Large Scale GAN Training for High Fidelity Natural Image Synthesis | - |
| ReACGAN + DiffAug | 3.175 | Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training | - |
| Projected GAN | 11.837 | Projected GANs Converge Faster | - |
0 of 6 row(s) selected.