A CLIP-based deepfake detector that adds conditional value-at-risk and AUC ranking losses reaches AUC 0.969 on the DFWild-Cup test set, modestly above two CLIP baselines.
Vb-kgn: Variational bayesian kernel generation networks for motion image deblurring,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Robust AI-Generated Face Detection with Imbalanced Data
A CLIP-based deepfake detector that adds conditional value-at-risk and AUC ranking losses reaches AUC 0.969 on the DFWild-Cup test set, modestly above two CLIP baselines.