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.
Towards universal fake image detec- tors that generalize across generative models
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
A separable prompt learning strategy on CLIP's text encoder enables competitive or superior generalizable performance in cross-dataset and cross-method face forgery detection.
MAFL uses adversarial training to suppress pattern and content biases, guiding models to learn shared generative features for better cross-model generalization in detecting AI images.
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.
-
Generalizable Face Forgery Detection via Separable Prompt Learning
A separable prompt learning strategy on CLIP's text encoder enables competitive or superior generalizable performance in cross-dataset and cross-method face forgery detection.
-
Combating Pattern and Content Bias: Adversarial Feature Learning for Generalized AI-Generated Image Detection
MAFL uses adversarial training to suppress pattern and content biases, guiding models to learn shared generative features for better cross-model generalization in detecting AI images.