Learning to Understand Earth Observation Images with Weak and Unreliable Ground Truth - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2019

Learning to Understand Earth Observation Images with Weak and Unreliable Ground Truth

Apprendre à comprendre les images d'observation de la Terre avec des annotations pauvres et non fiables

Résumé

In this paper we discuss the issues of using inexact and inaccurate ground truth in the context of supervised learning. To leverage large amounts of Earth observation data for training algorithms, one often has to use ground truth which was not been carefully assessed. We address both the problems of training and evaluation. We first propose a weakly supervised approach for training change classifiers which is able to detect pixel-level changes in aerial images. We then propose a data poisoning approach to get a reliable estimate of the accuracy that can be expected from a classifier, even when the only ground-truth available does not match the reality. Both are assessed on practical land use and land cover applications.
Fichier principal
Vignette du fichier
DTIS19090.1571822827_preprint.pdf (8.2 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-02355360 , version 1 (08-11-2019)

Identifiants

  • HAL Id : hal-02355360 , version 1

Citer

Rodrigo Caye Daudt, Adrien Chan-Hon-Tong, Bertrand Le Saux, Alexandre Boulch. Learning to Understand Earth Observation Images with Weak and Unreliable Ground Truth. IGARSS 2019, Jul 2019, YOKOHAMA, Japan. ⟨hal-02355360⟩
51 Consultations
72 Téléchargements

Partager

Gmail Facebook X LinkedIn More