SHCNet: A semi-supervised hypergraph convolutional networks based on relevant feature selection for hyperspectral image classification

Akrem Sellami, Mohamed Farah, Mauro Dalla Mura

Abstract: Highlights•A novel feature selection method based on information theoretic criteria is proposed.•Propose a new deep learning framework for hyperspectral image classification.•The proposed model integrates a semi-supervised Hypergraph Convolutional Networks.•Preserve deep spectral and spatial features in the convolutional layers.•Enhance image classification compared to well established deep learning models.

External IDs:dblp:journals/prl/SellamiFM23