Les commentaires sont clos.

ICube, Strasbourg, France: Domain invariant interpretable representation learning for satellite image time-series

16 December 2021

Catégorie : Doctorant

The goal of the project is to develop models for learning domain invariant representations using deep learning for the analysis of satellite image time-series.

A fully funded PhD position is open at the University of Strasbourg (ICube). The position will be jointly funded by the French National Centre for Space Studies (CNES) and the Chair SDIA. The candidate will join the SDC research team under the supervision of Dr Thomas Lampert, the Chair of Data Science and Artificial Intelligence, and join his international team to develop novel deep learning approaches to domain invariant representation learning for satellite image time-series (SITS).

Domain invariant interpretable representation learning for satellite image time-series

It is difficult and expensive to annotate the huge amount of data generated by satellites, but this is needed for the success of deep learning algorithms. To overcome this, transfer learning and domain adaptation techniques will be developed to exploit unlabelled data. These techniques allow an algorithm’s performance to be improved with minimal (or potentially no) additional annotation, lowering the cost of deployment.

The successful candidate will have (or will soon obtain) an MSc in Computer Science or related subject. Experience with deep learning is required and experience with time series and/or remote sensing is a bonus.

Send a letter of motivation and your CV to Thomas Lampert and Gisèle Burgart ( and - !remove the numbers!) with the subject beginning with [CNES PhD].

The application deadline is 15/3/2022 and the starting date will be September 2022 (or soon after).

Detailed Description: