Siamese-GAN: Learning Invariant Representations for Aerial Vehicle Image Categorization

• Published in: Remote sensing (Basel, Switzerland) Vol. 10; no. 2; p. 351
• Main Authors: Bashmal, Laila, Bazi, Yakoub, AlHichri, Haikel, AlRahhal, Mohamad, Ammour, Nassim, Alajlan, Naif
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 01.02.2018
• Subjects: Classification; Coding; distribution mismatch; extremely high resolution (EHR) images; Generative adversarial networks; generative adversarial networks (GANs); Image acquisition; Image classification; Image resolution; Invariants; manned/unmanned aerial vehicles (MAV/UAV); Military technology; Remote sensing; Representations; Siamese encoder–decoder; Unmanned aerial vehicles
• ISSN: 2072-4292; 2072-4292
• DOI: 10.3390/rs10020351

In this paper, we present a new algorithm for cross-domain classification in aerial vehicle images based on generative adversarial networks (GANs). The proposed method, called Siamese-GAN, learns invariant feature representations for both labeled and unlabeled images coming from two different domains. To this end, we train in an adversarial manner a Siamese encoder–decoder architecture coupled with a discriminator network. The encoder–decoder network has the task of matching the distributions of both domains in a shared space regularized by the reconstruction ability, while the discriminator seeks to distinguish between them. After this phase, we feed the resulting encoded labeled and unlabeled features to another network composed of two fully-connected layers for training and classification, respectively. Experiments on several cross-domain datasets composed of extremely high resolution (EHR) images acquired by manned/unmanned aerial vehicles (MAV/UAV) over the cities of Vaihingen, Toronto, Potsdam, and Trento are reported and discussed.