Learning a versatile representation of SAR data for regression and segmentation by leveraging self-supervised despeckling with MERLIN - Equipe Image, Modélisation, Analyse, GEométrie, Synthèse Access content directly
Preprints, Working Papers, ... Year : 2023

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

Abstract

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
Origin : Files produced by the author(s)

Dates and versions

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

Identifiers

  • HAL Id : hal-04245654 , version 1

Cite

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. 2023. ⟨hal-04245654⟩
99 View
48 Download

Share

Gmail Facebook X LinkedIn More