Multitask learning for large-scale semantic change detection

• Published in: Computer vision and image understanding Vol. 187; p. 102783
• Main Authors: Caye Daudt, Rodrigo, Le Saux, Bertrand, Boulch, Alexandre, Gousseau, Yann
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.10.2019; Elsevier
• Subjects: Computer Science; Computer Vision and Pattern Recognition; Fully convolutional networks; High resolution Earth observation; Multitask learning; Remote sensing; Semantic change detection; Multitask learning; Fully convolutional networks; 41A10; 65D05; High resolution Earth observation; 65D17; Semantic change detection; 41A05; Remote sensing; SEMANTIC CHANGE DETECTION; HIGH RESOLUTION EARTH OBSERVATION; REMOTE SENSING; FULLY CONVOLUTIONAL NETWORKS; MULTITASK LEARNING

Change detection is one of the main problems in remote sensing, and is essential to the accurate processing and understanding of the large scale Earth observation data available. Most of the recently proposed change detection methods bring deep learning to this context, but change detection labelled...