Deep-Learning Based Multiple Land-Cover Map Translation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Deep-Learning Based Multiple Land-Cover Map Translation

Résumé

This paper presents a framework for simultaneously translating multiple land-cover maps into a given one in a supervised way. Conversely to existing approaches working on 1-1 translation, we propose a multi-translation setup that increases the generalizability and translation performance, especially on land-cover maps covering restricted spatial extents. The proposed method mainly assumes that the map of interest spatially overlaps at least with one of the other maps. High performance translation is achieved with a Convolutional Neural Network (CNN) based encoder-decoder framework trained with three goals: (i) high-quality translation; (ii) self-reconstruction ability; (iii) mapping of all datasets into a common representation space. Country-scale experimental results show the method effectiveness in translating six highly heterogeneous land-cover maps, achieving significantly better results than the traditional semantic-based method and better results than CNN trained for a 1-1 translation task (+ 9.7% in Overall Accuracy (OA) and +12% in macro F1-score (mF1)).
Fichier principal
Vignette du fichier
Deep-Learning_Based_Multiple_Land-Cover_Map_Translation.pdf (4.34 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03983066 , version 1 (10-02-2023)

Identifiants

Citer

Luc Baudoux, Jordi Inglada, Clément Mallet. Deep-Learning Based Multiple Land-Cover Map Translation. IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Jul 2022, Kuala Lumpur, Malaysia. pp.1260-1263, ⟨10.1109/IGARSS46834.2022.9883056⟩. ⟨hal-03983066⟩
27 Consultations
28 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More