Back to Search Start Over

Deep Domain Adaptation in Earth Observation

Authors :
Nicolas Courty
Benjamin Kellenberger
Devis Tuia
Bharath Bhushan Damodaran
Onur Tasar
Camps-Valls, Gustau
Tuia, Devis
Zhu, XiaoXiang
Reichstein, Markus
Source :
Deep learning for the Earth Sciences, Deep Learning for the Earth Sciences, Deep Learning for the Earth Sciences. Wiley
Publisher :
Wiley

Abstract

When applied to new datasets, acquired at different time moments, with different sensors or under different acquisition conditions, deep learning models might fail spectacularly. This is because they have learned from the data distribution observed during training and, as such, do not generalize out of that domain naturally. This chapter introduces methodologies designed to tackle this problem and provide deep learning models able to adapt to new data distributions, i.e. domain adaptation. Domain adaptation works by either adapting the representation to the new data distribution, modifying the inputs or performing smart sampling. But independently of the strategy, they lead to updated models, able to process effectively the new data without needing observation from it (or a very limited amount).

Details

ISBN :
978-1-119-64614-3
ISBNs :
9781119646143
Database :
OpenAIRE
Journal :
Deep learning for the Earth Sciences, Deep Learning for the Earth Sciences, Deep Learning for the Earth Sciences. Wiley
Accession number :
edsair.doi.dedup.....74611805d7dd389968095ec0e12009d4