Image Generation on CUB200
2.79FIDProjected GAN
Evaluation results
| Method | Links | |
|---|---|---|
| Projected GANResolution=256x2562021.11 | 2.79 | |
| SADM (full)Pre-training=ImageNet, Resolution=256x256, Tuning Strategy=Full Fine-tuning2024.02 | 4.69 | |
| SADM (parameter-efficient)Pre-training=ImageNet, Resolution=256x256, Tuning Strategy=Parameter-efficient2024.02 | 5.04 | |
| DiffFitPre-training=ImageNet, Resolution=256x256, Tuning Strategy=Parameter-efficient2024.02 | 5.48 | |
| Full Fine-tuning with DDPMPre-training=ImageNet, Resolution=256x256, Tuning Strategy=Full Fine-tuning2024.02 | 5.68 | |
| AdaptFormerPre-training=ImageNet, Resolution=256x256, Tuning Strategy=Parameter-efficient2024.02 | 7.73 | |
| BitFitPre-training=ImageNet, Resolution=256x256, Tuning Strategy=Parameter-efficient2024.02 | 8.81 | |
| FineGANResolution=256x2562021.11 | 11.25 | |
| VPTPre-training=ImageNet, Resolution=256x256, Tuning Strategy=Parameter-efficient2024.02 | 17.29 | |
| LoRAPre-training=ImageNet, Resolution=256x256, Tuning Strategy=Parameter-efficient2024.02 | 56.03 |