Sequential training of GANs against GAN-classifiers reveals correlated "knowledge gaps" present among independently trained GAN instances

no code implementations • CVPR 2023 • Arkanath Pathak, Nicholas Dufour

We iteratively train GAN-classifiers and train GANs that "fool" the classifiers (in an attempt to fill the knowledge gaps), and examine the effect on GAN training dynamics, output quality, and GAN-classifier generalization.

TruFor: Leveraging all-round clues for trustworthy image forgery detection and localization

no code implementations • CVPR 2023 • Fabrizio Guillaro, Davide Cozzolino, Avneesh Sud, Nicholas Dufour, Luisa Verdoliva

In this paper we present TruFor, a forensic framework that can be applied to a large variety of image manipulation methods, from classic cheapfakes to more recent manipulations based on deep learning.

Image Forgery Detection Image Manipulation +2