FASA bridges low-level forensic frequency signals and high-level semantic consistency to achieve state-of-the-art localization of both conventional and diffusion-generated image manipulations.
Title resolution pending
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2representative citing papers
Frozen features from vision foundation models enable a linear probe to outperform specialized AIGI detectors by over 30% on in-the-wild data due to emergent forgery knowledge from pre-training.
citing papers explorer
-
Bridging the Micro--Macro Gap: Frequency-Aware Semantic Alignment for Image Manipulation Localization
FASA bridges low-level forensic frequency signals and high-level semantic consistency to achieve state-of-the-art localization of both conventional and diffusion-generated image manipulations.
-
Simplicity Prevails: The Emergence of Generalizable AIGI Detection in Visual Foundation Models
Frozen features from vision foundation models enable a linear probe to outperform specialized AIGI detectors by over 30% on in-the-wild data due to emergent forgery knowledge from pre-training.