Affordable Access

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

Authors
  • Daudt, Rodrigo
  • Chan-Hon-Tong, Adrien
  • Le Saux, Bertrand
  • Boulch, Alexandre
Publication Date
Jul 28, 2019
Source
Kaleidoscope Open Archive
Keywords
Language
English
License
Unknown
External links

Abstract

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.

Report this publication

Statistics

Seen <100 times