LHSDet detects AI-generated images by fusing low-level texture features, SigLIP2 global features, and BLIP-2 captions in a visual question answering framework, reaching 96% average cross-model accuracy.
High-resolution image synthesis with latent diffusion models,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
LHSDet: High-Resolution AI-Generated Image Detection via Visual Question Answering
LHSDet detects AI-generated images by fusing low-level texture features, SigLIP2 global features, and BLIP-2 captions in a visual question answering framework, reaching 96% average cross-model accuracy.