Search & Find
DiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporamaDiaporama
Accueil
ICube   >   Agenda : PhD:“Learning Domain Invariant Representations of Heterogeneous Image Data”

PhD:“Learning Domain Invariant Representations of Heterogeneous Image Data”

Le 29 septembre 2023
À 09h00
ICube, Illkirch - salle A301

PhD defence : Mihailo Obrenović

Team: EM3 (ex SDC)

Date & time : Friday, September 29th, at 09:00 AM at ICube, Illkirch in room A301

Title : “Learning Domain Invariant Representations of Heterogeneous Image Data

Abstract : 

Supervised deep learning relies heavily on the existence of a large amount of labelled data, which in many cases is difficult to obtain. Domain adaptation deals with this problem by learning on a labelled dataset and applying that knowledge to another, unlabelled or scarcely labelled dataset, with a related but different probability distribution. Heterogeneous domain adaptation is an especially challenging area where domains lie in different input spaces. These methods are very interesting for the field of remote sensing (and indeed computer vision in general), where a variety of sensors are used, capturing images of different modalities, different spatial and spectral resolutions, and where labelling is a very expensive process.

This thesis proposes novel approaches for Heterogeneous Image Domain Adaptation (HIDA) that are based on extracting domain invariant features using deep adversarial learning. The thesis considers different scenarios of integrating the supervision information in the target domain. The results show advantages of using domain invariant HIDA method over the competing methods based on image-to-image/feature translation.

The jury will be composed of:

  • Reviewer — Mr. Dino Ienco (Director of Research, INRAE, France)
  • Reviewer — Mr. Nicolas Courty (Professor, University of Bretagne Sud, France)
  • Examinator — Ms. Charlotte Pelletier (Assistant Professor, University of Bretagne Sud, France)
  • Examinator — Mr. Vincent Noblet (Research Engineer, University of Strasbourg, France)
  • Supervisor — Mr. Pierre Gançarski (Professor, University of Strasbourg, France)
  • Supervisor — Mr. Thomas Lampert (Assistant Professor, University of Strasbourg, France)
  • Supervisor — Mr. Miloš Ivanović (Associate Professor, University of Kragujevac, Serbia)

À la une

Le dépôt des candidatures pour les postes d’enseignants-chercheur est ouvert. Les offres sont...

Flux RSS

Flux RSS