Graph feature fusion driven by deep autoencoder for advanced hyperspectral image unmixing

Download PDF
Open Webpage

Refka Hanachi, Akrem Sellami, Imed Riadh Farah, Mauro Dalla Mura

Published: 01 Jan 2024, Last Modified: 12 Nov 2025Knowl. Based Syst. 2024EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•A multi-view graph neural networks is proposed for hyperspectral image unmixing.•Spectral- and Morphological Profiles-based graphs are built with relevant features.•Unmixing accuracy is improved by the learned shared latent representation.•Superior unmixing performance demonstrated on real HSI datasets.