Owing to their realistic features and continuous improvements, images manipulated by Generative Adversarial Network (GAN) have become a compelling research topic. In this paper, we apply detection and localization to GAN manipulated images by means of models, based on EfficientNet-B4 architectures. Detection is tested on multiple generated multi-spectral datasets from several world regions and different GAN architectures, whereas localization is tested on an inpainted images dataset of sizes 2048×2048×13. The results obtained for both detection and localization are shown to be promising.
Detection and Localization of GAN Manipulated Multi-spectral Satellite Images / L. Abady, G.M. Dimitri, M. Barni - In: ESANN 2022[s.l] : ESANN, 2022. - ISBN 9782875870841. - pp. 339-344 (( Intervento presentato al 30. convegno European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning tenutosi a Bruges nel 2022 [10.14428/esann/2022.ES2022-39].
Detection and Localization of GAN Manipulated Multi-spectral Satellite Images
G.M. Dimitri;
2022
Abstract
Owing to their realistic features and continuous improvements, images manipulated by Generative Adversarial Network (GAN) have become a compelling research topic. In this paper, we apply detection and localization to GAN manipulated images by means of models, based on EfficientNet-B4 architectures. Detection is tested on multiple generated multi-spectral datasets from several world regions and different GAN architectures, whereas localization is tested on an inpainted images dataset of sizes 2048×2048×13. The results obtained for both detection and localization are shown to be promising.
| File | Dimensione | Formato | |
|---|---|---|---|
|
ES2022-39.pdf
accesso aperto
Tipologia:
Publisher's version/PDF
Licenza:
Creative commons
Dimensione
1.73 MB
Formato
Adobe PDF
|
1.73 MB | Adobe PDF | Visualizza/Apri |
Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
