Multi–Scale Graph Wavelet Convolutional Network for Hyperspectral and LiDAR Data Classification

In this paper, we present a novel Multi–Scale Graph Wavelet Convolutional Network for Hyperspectral and LiDAR Data Classification. The proposed MS-GWCN enables more effective learning of spatial–spectral relationships for pixel-wise classification. We conduct extensive experiments on the Houston 2013 dataset, which comprises 15 diverse land-cover classes. The results demonstrate that our method achieves significant improvements over baseline approaches, attaining an overall accuracy (OA) of 85.98%, an average accuracy (AA) of 88.39%, and a Kappa coefficient of 84.79%.