Initializing a frozen vision-language encoder's linear probe with text-derived prototypes ('AI art' vs 'a real photo') and calibrating on one source improves cross-generator, in-the-wild, and post-processing AI-generated image detection.
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
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unleashing the Potential of Vision-Language Models for Generalizable AI-Generated Image Detection
Initializing a frozen vision-language encoder's linear probe with text-derived prototypes ('AI art' vs 'a real photo') and calibrating on one source improves cross-generator, in-the-wild, and post-processing AI-generated image detection.