Investigating Model Robustness Against Sensor Variation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Investigating Model Robustness Against Sensor Variation

Résumé

Large datasets of geospatial satellite images are available online, exhibiting significant variations in both image quality and content. These variations in image quality stem from the image processing pipeline and image acquisition settings, resulting in subtle differences within datasets of images acquired with the same satellites. Recent progress in the field of image processing have considerably enhanced capabilities in noise and artifacts removal, as well as image super-resolution. Consequently, this opens up possibilities for homogenizing geospatial image datasets by reducing the intra-dataset variations in image quality. In this work, we show that conventional image detection and segmentation neural networks trained on geospatial data are robust neither to noise and artefact removal preprocessing, nor to mild resolution variations.
Fichier principal
Vignette du fichier
IGARSS2023_MultiResolution.pdf (13.77 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04112635 , version 1 (31-05-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-04112635 , version 1

Citer

Matthieu Terris, Sagar Verma. Investigating Model Robustness Against Sensor Variation. IGARSS 2023 - International Geoscience and Remote Sensing Symposium, IEEE, Jul 2023, Pasadena, United States. ⟨hal-04112635⟩
66 Consultations
17 Téléchargements

Partager

Gmail Facebook X LinkedIn More