ADVERSARIAL LABEL-EFFICIENT SATELLITE IMAGE CHANGE DETECTION - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

ADVERSARIAL LABEL-EFFICIENT SATELLITE IMAGE CHANGE DETECTION

Résumé

Satellite image change detection aims at finding occurrences of targeted changes in a given scene taken at different instants. This task is highly challenging due to the acquisition conditions and also to the subjectivity of changes. In this paper, we investigate satellite image change detection using active learning. Our method is interactive and relies on a question & answer model which asks the oracle (user) questions about the most informative display (dubbed as virtual exemplars), and according to the user's responses, updates change detections. The main contribution of our method consists in a novel adversarial model that allows frugally probing the oracle only with the most representative, diverse and uncertain virtual exemplars. The latter are learned to challenge (the most) the trained change decision criteria which ultimately leads to a better re-estimate of these criteria in the following iterations of active learning. Conducted experiments show the out-performance of our proposed adversarial display model against related display strategies as well as the related work.
Fichier principal
Vignette du fichier
Template.pdf (291.95 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04274276 , version 1 (07-11-2023)

Identifiants

Citer

Hichem Sahbi, Sebastien Deschamps. ADVERSARIAL LABEL-EFFICIENT SATELLITE IMAGE CHANGE DETECTION. EEE International Geoscience and Remote Sensing Symposium (IGARSS), Jul 2023, Pasadena, United States. pp.5794 - 5797, ⟨10.1109/IGARSS52108.2023.10283388⟩. ⟨hal-04274276⟩
10 Consultations
20 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More