LDR-Net detects AI-generated images by combining a gradient residual with a random-weight local pattern descriptor, reporting top accuracy across GAN and diffusion generators.
Exposing the deception: Uncovering more forgery clues for deep- fake detection
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
LDR-Net: A Novel Framework for AI-generated Image Detection via Localized Discrepancy Representation
LDR-Net detects AI-generated images by combining a gradient residual with a random-weight local pattern descriptor, reporting top accuracy across GAN and diffusion generators.