AIGC Detection on GenImage v1 (test)
65.5Midjourney AccuracySICA
Evaluation results
| Method | Links | |||||||||
|---|---|---|---|---|---|---|---|---|---|---|
| SICATraining Set=Stable Diffusion v1.42026.02 | 65.5 | 100 | 99.9 | 51.1 | 66.1 | 99.7 | 64.4 | 55.6 | 75.3 | |
| Swin-TTraining Set=Stable Diffusion v1.42026.02 | 62.1 | 99.9 | 99.8 | 49.8 | 67.6 | 99.1 | 62.3 | 57.6 | 74.8 | |
| DeiT-STraining Set=Stable Diffusion v1.42026.02 | 55.6 | 99.9 | 99.8 | 49.8 | 58.1 | 98.9 | 56.9 | 53.5 | 71.6 | |
| ResNet-50Training Set=Stable Diffusion v1.42026.02 | 54.9 | 99.9 | 99.7 | 53.5 | 61.9 | 98.2 | 56.6 | 52 | 72.1 | |
| GramNetTraining Set=Stable Diffusion v1.42026.02 | 54.2 | 99.2 | 99.1 | 50.3 | 54.6 | 98.9 | 50.8 | 51.7 | 69.9 | |
| CNNSpotTraining Set=Stable Diffusion v1.42026.02 | 52.8 | 96.3 | 95.9 | 50.1 | 39.8 | 78.6 | 53.4 | 46.8 | 64.2 | |
| SpecTraining Set=Stable Diffusion v1.42026.02 | 52 | 99.4 | 99.2 | 49.7 | 49.8 | 94.8 | 55.6 | 49.8 | 68.8 | |
| F3NetTraining Set=Stable Diffusion v1.42026.02 | 50.1 | 99.9 | 99.9 | 49.9 | 50 | 99.9 | 49.9 | 49.9 | 68.7 |