Training deepfake detectors on both original and online-synthesized fakes degrades performance due to gradient conflict, and CS-DFD mitigates this with an update-vector search and a conflict-reduction loss.
Dcface: Synthetic face generation with dual condition diffusion model,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Suppressing Gradient Conflict for Generalizable Deepfake Detection
Training deepfake detectors on both original and online-synthesized fakes degrades performance due to gradient conflict, and CS-DFD mitigates this with an update-vector search and a conflict-reduction loss.