Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection

Open paper
Benchmark Model Rank Results
deepfake-detection-on-fakeavcelebRealForensics#2ROC AUC: 97.1AP: 95.3
deepfake-detection-on-fakeavcelebAVBYOL#7ROC AUC: 59.2AP: 73.9

Rank counts only results with a code link.