AI-generated image detection on SD-Turbo generator (test)
73.24AccuracyFreDect
Evaluation results
| Method | Links | ||
|---|---|---|---|
| FreDectTraining Dataset=ProGAN2026.01 | 73.24 | 82.09 | |
| Ours (ViT-B/32)Training Dataset=ProGAN, Backbone=ViT-B/322026.01 | 59.42 | 73.36 | |
| UnivFDTraining Dataset=ProGAN2026.01 | 56.64 | 77.56 | |
| FatFormerTraining Dataset=ProGAN2026.01 | 54.3 | 58.63 | |
| Ours (ViT-L/14)Training Dataset=ProGAN, Backbone=ViT-L/142026.01 | 51.29 | 78.48 | |
| SAFETraining Dataset=ProGAN2026.01 | 49.92 | 50.94 | |
| NPRTraining Dataset=ProGAN2026.01 | 49.46 | 39.08 | |
| CNNSpotTraining Dataset=ProGAN2026.01 | 48.57 | 52.64 | |
| LNPTraining Dataset=ProGAN2026.01 | 43.29 | 36.25 | |
| GramNetTraining Dataset=ProGAN2026.01 | 32.72 | 35.88 | |
| LGradTraining Dataset=ProGAN2026.01 | 30.98 | 31.72 |