What Data are needed for Semantic Segmentation in Earth Observation? - Archive ouverte HAL Access content directly
Conference Papers Year : 2019

What Data are needed for Semantic Segmentation in Earth Observation?

Abstract

This paper explores different aspects of semantic segmentation of remote sensing data using deep neural networks. Learning with deep neural networks was revolutionized by the creation of ImageNet. Remote sensing benefited of these new techniques, however Earth Observation (EO) datasets remain small in comparison. In this work, we investigate how we can progress towards the ImageNet of remote sensing. In particular, two questions are addressed in this paper. First, how robust are existing supervised learning strategies with respect to data volume? Second, which properties are expected from a large-scale EO dataset? The main contributions of this work are: (i) a strong robustness analysis of existing supervised learning strategies with respect to remote sensing data, (ii) the introduction of a new, large-scale dataset named MiniFrance.
Fichier principal
Vignette du fichier
castillo_what-data_jurse19_preprint_hal.pdf (4.12 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-02343915 , version 1 (14-11-2019)
hal-02343915 , version 2 (10-12-2019)

Identifiers

Cite

Javiera Castillo-Navarro, Nicolas Audebert, Alexandre Boulch, Bertrand Le Saux, Sébastien Lefèvre. What Data are needed for Semantic Segmentation in Earth Observation?. 2019 Joint Urban Remote Sensing Event (JURSE), May 2019, Vannes, France. pp.1-4, ⟨10.1109/JURSE.2019.8809071⟩. ⟨hal-02343915v2⟩
201 View
221 Download

Altmetric

Share

Gmail Facebook X LinkedIn More