LEARNING VIRTUAL EXEMPLARS FOR LABEL-EFFICIENT SATELLITE IMAGE CHANGE DETECTION

Hichem Sahbi (1) , Sébastien Deschamps (1)

1 SYEL - Systèmes Electroniques

In this paper, we devise a novel interactive satellite image change detection algorithm based on active learning. The proposed framework is iterative and relies on a question & answer model which asks the oracle (user) questions about the most informative display (subset of critical images), and according to the user's responses, updates change detections. The contribution of our framework resides in a novel display model which selects the most representative and diverse virtual exemplars that adversely challenge the learned change detection functions, thereby leading to highly discriminating functions in the subsequent iterations of active learning. Experiments, conducted on the challenging task of interactive satellite image change detection, show the superiority of the proposed virtual display model against the related work.

Mots clés: active learning; virtual exemplar learning; satellite image change detection

Domaines: Intelligence artificielle [cs.AI]; Traitement des images [eess.IV]; Vision par ordinateur et reconnaissance de formes [cs.CV]

Hichem Sahbi, Sébastien Deschamps. LEARNING VIRTUAL EXEMPLARS FOR LABEL-EFFICIENT SATELLITE IMAGE CHANGE DETECTION. IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Jul 2022, Kuala Lumpur, Malaysia. pp.1197-1200, ⟨10.1109/IGARSS46834.2022.9883936⟩. ⟨hal-03838832⟩