Unconditional Image Generation on CIFAR-100 10% (train)
19.13FIDVision-aided Adversarial training
Evaluation results
| Method | Links | |
|---|---|---|
| Vision-aided Adversarial trainingBase Architecture=BigGAN, Number of Vision-Aided Discriminators=32021.12 | 19.13 | |
| Vision-aided Adversarial trainingBase Architecture=BigGAN, Number of Vision-Aided Discriminators=22021.12 | 20.89 | |
| Vision-aided Adversarial trainingBase Architecture=BigGAN, Number of Vision-Aided Discriminators=12021.12 | 25.13 | |
| DiffAugmentBase Architecture=BigGAN, Data Augmentation=DiffAugment2021.12 | 33.75 |