Multi-Task Learning of Height and Semantics from Aerial Images - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue IEEE Geoscience and Remote Sensing Letters Année : 2019

Multi-Task Learning of Height and Semantics from Aerial Images

Apprentissage multi-tâche de l'élévation et de la sémantique à partir d'images aériennes

Résumé

Aerial or satellite imagery is a great source for land surface analysis, which might yield land use maps or elevation models. In this investigation, we present a neural network framework for learning semantics and local height together. We show how this joint multi-task learning benefits to each task on the large dataset of the 2018 Data Fusion Contest. Moreover, our framework also yields an uncertainty map which allows assessing the prediction of the model. Code is available at https://github.com/marcelampc/mtl_aerial_images .
Fichier principal
Vignette du fichier
DTIS19229.1580910909_postprint.pdf (6.63 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02386074 , version 1 (29-11-2019)
hal-02386074 , version 2 (10-02-2020)

Identifiants

Citer

Marcela Carvalho, Bertrand Le Saux, Pauline Trouvé-Peloux, Frédéric Champagnat, Andrés Almansa. Multi-Task Learning of Height and Semantics from Aerial Images. IEEE Geoscience and Remote Sensing Letters, 2019, ⟨10.1109/LGRS.2019.2947783⟩. ⟨hal-02386074v2⟩
106 Consultations
77 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More