Image To Image Translation On Cityscapes 1
評価指標
Class IOU
Per-class Accuracy
Per-pixel Accuracy
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 | Class IOU | Per-class Accuracy | Per-pixel Accuracy | Paper Title | Repository |
|---|---|---|---|---|---|
| CoGAN | 0.08 | 11% | 45% | Coupled Generative Adversarial Networks | |
| SimGAN | 0.07 | 11% | 47% | Learning from Simulated and Unsupervised Images through Adversarial Training | |
| CycleGAN | 0.16 | 22% | 58% | Unpaired Image-to-Image Translation using Cycle-Consistent Adversarial Networks | |
| pix2pix | 0.32 | 40.0% | 85.0% | Image-to-Image Translation with Conditional Adversarial Networks | |
| BiGAN | 0.07 | 13% | 41% | Adversarially Learned Inference |
0 of 5 row(s) selected.