CDN mixes feature statistics of genuine face images and reconstructs them to reduce false alarms in cross-domain deepfake detection, but the supporting theory is flawed and the artifacts are missing.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Contrastive Desensitization Learning for Cross Domain Face Forgery Detection
CDN mixes feature statistics of genuine face images and reconstructs them to reduce false alarms in cross-domain deepfake detection, but the supporting theory is flawed and the artifacts are missing.