Change detection across domains using GAN-based image translation

Abstract

The problem of visual change detection becomes a challenging one when query and reference images involve different domains (e.g., time of the day, weather, and season) due to variations in object appearance and a limited amount of training examples. In this study, we address the above issue by training a GAN-based image translator that maps a reference image to a virtual image that cannot be discriminated from query domain images, and experimentally verify efficacy of the approach.