Deepfake Detection on Face2Face (F2F) (test)
98.94AUC (%)QAD-E
Evaluation Results
| Method | Links | |
|---|---|---|
| QAD-ESetting=Quality-agnostic, Compression=Video (raw + c23 + c40)2023.09 | 98.94 | |
| QAD-RSetting=Quality-agnostic, Compression=Video (raw + c23 + c40)2023.09 | 98.34 | |
| Rössler et al.Setting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=published code2023.09 | 97.89 | |
| Fang & LinSetting=Quality-agnostic, Compression=Video (raw + c23 + c40)2023.09 | 97.33 | |
| F3NetSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=published code2023.09 | 96.32 | |
| MATSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=published code2023.09 | 96.32 | |
| MesoNetSetting=Quality-agnostic, Compression=Video (raw + c23 + c40)2023.09 | 94.15 | |
| BZNetSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=pre-trained weights2023.09 | 94.1 | |
| ADDSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=pre-trained weights2023.09 | 90.62 | |
| SBIsSetting=Quality-agnostic, Compression=Video (raw + c23 + c40), Implementation source=pre-trained weights2023.09 | 79.74 |