An Architecture for the detection of GAN-generated Flood Images with Localization Capabilities

TL;DR

This paper introduces a hybrid deep learning architecture that detects and localizes GAN-generated fake flood images, improving robustness and generalization in image forensics.

Contribution

The paper presents a novel hybrid detection and localization architecture specifically designed for identifying ClimateGAN-generated flood images, enhancing detection accuracy and interpretability.

Findings

Localization branch improves detection robustness

Architecture generalizes well across diverse datasets

Effective in identifying manipulated image regions

Abstract

In this paper, we address a new image forensics task, namely the detection of fake flood images generated by ClimateGAN architecture. We do so by proposing a hybrid deep learning architecture including both a detection and a localization branch, the latter being devoted to the identification of the image regions manipulated by ClimateGAN. Even if our goal is the detection of fake flood images, in fact, we found that adding a localization branch helps the network to focus on the most relevant image regions with significant improvements in terms of generalization capabilities and robustness against image processing operations. The good performance of the proposed architecture is validated on two datasets of pristine flood images downloaded from the internet and three datasets of fake flood images generated by ClimateGAN starting from a large set of diverse street images.