"Low Supervision" Deep Cluster Change Detection (CDCluster) On Remote Sensing RGB Data: Towards The Unsupervising Clustering Framework

Garcia Fernandez Guglielmo, Iris de Gélis, Thomas Corpetti, Sébastien Lefèvre, Arnaud Le Bris

Abstract: This paper is concerned with the change detection issue in remote sensing images. This problem is not trivial since the notion of change depends on the application. Moreover, classical supervised deep learning methods have to deal with the limited amount of labelled data available. Based on existing deep learning techniques that exploit unsupervised clustering to assign labels to entire images, we adapt them to the change detection problem by using siamese backbones and extracting pixel-wise results. As fully unsupervised experiments lead to unstable results, we suggest "low supervision" strategy composed of a warm-up stage with few labeled data able to drive the following unsupervised learning through reliable solutions. Preliminary experiments show reliable change maps.