ODP-Net uses instance-aware orthogonal decomposition, perturbation-based purification, and manifold alignment to separate universal forgery traces, generator fingerprints, and semantics, achieving SOTA on unseen architectures like Stable Diffusion 3.
Generalizing face forgery detec- tion with high-frequency features
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
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.
citing papers explorer
-
Decoupling Semantics and Fingerprints: A Universal Representation for AI-Generated Image Detection
ODP-Net uses instance-aware orthogonal decomposition, perturbation-based purification, and manifold alignment to separate universal forgery traces, generator fingerprints, and semantics, achieving SOTA on unseen architectures like Stable Diffusion 3.
-
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.