Conditional Image Generation on CIFAR100 (10 classes, 100 samples per class)
54.95FIDcGANTransfer
Evaluation results
| Method | Links | |
|---|---|---|
| cGANTransferBackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes)2021.02 | 54.95 | |
| BSABackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes), Iteration=full2021.02 | 56.48 | |
| TransferGANBackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes)2021.02 | 64.75 | |
| BSABackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes), Iteration=early2021.02 | 66.76 | |
| ScratchBackbone=BigGAN, Pre-training dataset=None2021.02 | 83.68 |