Fully Funded PhD – ICube, Strasbourg, France: Domain invariant interpretable representation learning

01/04/2022 – 02/04/2022 all-day

Offre en lien avec l’Action/le Réseau : – — –/– — –

Laboratoire/Entreprise : ICube, University of Strasbourg
Durée : 3 years
Contact : lampert@unistra.fr
Date limite de publication : 2022-04-01

Contexte :
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).

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

Detailed Description: https://drive.google.com/file/d/1W92enhzhKLJ0_IjD4pSSMYHw-y6SxQdj/view?usp=sharing

Profil du candidat :
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.

Formation et compétences requises :
MSc in Computer Science or related subject
deep learning

Adresse d’emploi :
ICube UMR 7357 – Laboratoire des sciences de l’ingénieur, de l’informatique et de l’imagerie
300 bd Sébastien Brant – CS 10413 – F-67412 Illkirch Cedex