LRD-Net achieves state-of-the-art cross-domain face forgery detection via a frequency-guided lightweight backbone and real-centered learning with only 2.63M parameters and substantially faster training and inference.
On the frequency bias of generative models,
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
-
LRD-Net: A Lightweight Real-Centered Detection Network for Cross-Domain Face Forgery Detection
LRD-Net achieves state-of-the-art cross-domain face forgery detection via a frequency-guided lightweight backbone and real-centered learning with only 2.63M parameters and substantially faster training and inference.