μFlow trains a normalizing flow on averaged real-image features to detect deepfakes via likelihood in a fully out-of-distribution setting.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
$\mu$Flow: Leveraging Average Images for Improving Generalisation of Deepfake Faces Detectors
μFlow trains a normalizing flow on averaged real-image features to detect deepfakes via likelihood in a fully out-of-distribution setting.