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.
Wang, J., Alamayreh, O., Tondi, B., Barni, M. (2022). An Architecture for the detection of GAN-generated Flood Images with Localization Capabilities. In IVMSP 2022 - 2022 IEEE 14th Image, Video, and Multidimensional Signal Processing Workshop (pp.1-5). New York : Institute of Electrical and Electronics Engineers Inc. [10.1109/IVMSP54334.2022.9816324].
An Architecture for the detection of GAN-generated Flood Images with Localization Capabilities
Wang J.;Alamayreh O.;Tondi B.;Barni M.
2022-01-01
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.File | Dimensione | Formato | |
---|---|---|---|
An_Architecture_for_the_detection_of_GAN-generated_Flood_Images_with_Localization_Capabilities.pdf
non disponibili
Tipologia:
PDF editoriale
Licenza:
NON PUBBLICO - Accesso privato/ristretto
Dimensione
5.24 MB
Formato
Adobe PDF
|
5.24 MB | Adobe PDF | Visualizza/Apri Richiedi una copia |
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11365/1215135