Conditional Image Generation on CIFAR100 (10 classes, 300 samples per class)
35.23FIDcGANTransfer
Evaluation results
| Method | Links | |
|---|---|---|
| cGANTransferBackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes)2021.02 | 35.23 | |
| BSABackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes), Iteration=full2021.02 | 35.62 | |
| BSABackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes), Iteration=early2021.02 | 40.34 | |
| TransferGANBackbone=BigGAN, Pre-training dataset=CIFAR100 (80 classes)2021.02 | 40.74 | |
| ScratchBackbone=BigGAN, Pre-training dataset=None2021.02 | 62.17 |