Bayesian U-Net: Estimating Uncertainty in Semantic Segmentation of Earth Observation Images - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Remote Sensing Année : 2021

Bayesian U-Net: Estimating Uncertainty in Semantic Segmentation of Earth Observation Images

Résumé

In recent years, numerous deep learning techniques have been proposed to tackle the semantic segmentation of aerial and satellite images, increase trust in the leaderboards of main scientific contests and represent the current state-of-the-art. Nevertheless, despite their promising results, these state-of-the-art techniques are still unable to provide results with the level of accuracy sought in real applications, i.e., in operational settings. Thus, it is mandatory to qualify these segmentation results and estimate the uncertainty brought about by a deep network. In this work, we address uncertainty estimations in semantic segmentation. To do this, we relied on a Bayesian deep learning method, based on Monte Carlo Dropout, which allows us to derive uncertainty metrics along with the semantic segmentation. Built on the most widespread U-Net architecture, our model achieves semantic segmentation with high accuracy on several state-of-the-art datasets. More importantly, uncertainty maps are also derived from our model. While they allow for the performance of a sounder qualitative evaluation of the segmentation results, they also include valuable information to improve the reference databases.
Fichier principal
Vignette du fichier
remotesensing-13-03836-v2.pdf (58.81 Mo) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte

Dates et versions

hal-03379048 , version 1 (30-05-2022)

Licence

Paternité

Identifiants

Citer

Clément Dechesne, Pierre Lassalle, Sébastien Lefèvre. Bayesian U-Net: Estimating Uncertainty in Semantic Segmentation of Earth Observation Images. Remote Sensing, 2021, 13 (19), pp.3836. ⟨10.3390/rs13193836⟩. ⟨hal-03379048⟩
132 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More