Pixel-Superpixel Level Multiscale Graph and Spectral–Spatial Representation Fusion Network for Hyperspectral Image Classification

Abstract

Hyperspectral image (HSI) classification technology has continuously made breakthroughs. Especially with the emergence of convolutional neural networks (CNN), its performance has been rapidly enhanced. However, CNN uses kernels with fixed sizes, which cannot flexibly handle data with irregular patterns, affecting the HSI classification results. Therefore, the paper introduces a graph convolutional network (GCN) to assist CNN in further optimizing the HSI representation and proposes a pixel-superpixel level multiscale graph and spectral-spatial representations fusion network (Ps-MGSRF) that mainly includes a pixel-level feature representation module (PFRM) formed with multiple multiscale feature refiltering blocks and a superpixel-level feature representation module (SFRM) composed of different orders’ residual GCN (ResGCN) blocks. Finally, the loss of the PFRM branch ( loss ₁ ), the loss of the SFRM branch ( loss ₂ ), and the loss of the merging of the two branches ( loss ₃ ) are calculated separately, and the Ps-MGSRF network is updated by adaptive weighting three losses. The test results indicate that the proposed Ps-MGSRF model could achieve better experimental performance than the advanced comparison methods.