Conditional Image Generation on CIFAR100 (20 classes 600 samples per class)
25.35FIDScratch
Evaluation results
| Method | Links | |
|---|---|---|
| ScratchBackbone=BigGAN, Pre-training dataset=None2021.02 | 25.35 | |
| TransferGANBackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes)2021.02 | 27.67 | |
| BSABackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes), Iteration=full2021.02 | 28.03 | |
| cGANTransferBackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes)2021.02 | 29.1 | |
| BSABackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes), Iteration=early2021.02 | 37.12 |