Deepfake Detection on FaceForensics++ c23 FS
100AUROCPCL + I2G
Evaluation Results
| Method | Links | |
|---|---|---|
| PCL + I2GType of Model=Closed-set, Training Data=FF++c232025.03 | 100 | |
| S-MIL-TType of Model=Closed-set, Training Data=FF++c232025.03 | 99.61 | |
| ProposedType of Model=Open-set, Training Data=FF++c23, DF excluded2025.03 | 99.43 | |
| ProposedType of Model=Open-set, Training Data=FF++c232025.03 | 99.42 | |
| XN-avgType of Model=Closed-set, Training Data=FF++c232025.03 | 99.36 | |
| Face X-rayType of Model=Closed-set, Training Data=FF++c232025.03 | 99.09 | |
| ProposedType of Model=Open-set, Training Data=FF++c23, F2F excluded2025.03 | 98.47 | |
| ProposedType of Model=Open-set, Training Data=FF++c23, NT excluded2025.03 | 97.6 | |
| MILType of Model=Closed-set, Training Data=FF++c232025.03 | 94.86 |