Learning a versatile representation of SAR data for regression and segmentation by leveraging self-supervised despeckling with MERLIN - Equipe Image, Modélisation, Analyse, GEométrie, Synthèse Accéder directement au contenu
Communication Dans Un Congrès Année : 2024

Learning a versatile representation of SAR data for regression and segmentation by leveraging self-supervised despeckling with MERLIN

Résumé

Synthetic Aperture Radar (SAR) images are abundantly available, yet labels are often missing. Thus, training a neural network in a fully supervised manner is arduous. In this work, we leverage MERLIN, a self-supervised despeckling algorithm, to learn a mapping of SAR images into a representation space shared among despeckling, segmentation and regression. Our experiments demonstrate that the joint training of a neural network for these three tasks reduces considerably the need for labeled data to solve the supervised tasks.
Fichier principal
Vignette du fichier
MERLIN_Seg_height.pdf (2.67 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04245654 , version 1 (17-10-2023)

Identifiants

  • HAL Id : hal-04245654 , version 1

Citer

Emanuele Dalsasso, Clément Rambour, Loïc Denis, Florence Tupin. Learning a versatile representation of SAR data for regression and segmentation by leveraging self-supervised despeckling with MERLIN. European Conference on Synthetic Aperture Radar, Apr 2024, Munich (Allemagne), Germany. ⟨hal-04245654⟩
123 Consultations
63 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More