Spectral Graph Reasoning Network for Hyperspectral Image Classification

TL;DR

This paper introduces a spectral graph reasoning network that enhances hyperspectral image classification by effectively utilizing spectral information through graph-based reasoning and ensembling, leading to significant accuracy improvements.

Contribution

The paper proposes a novel spectral graph reasoning framework with spectral decoupling and ensembling modules, advancing spectral information utilization in hyperspectral image classification.

Findings

Significantly improved classification accuracy on two HSI datasets.

Effective aggregation and alignment of spectral features via graph reasoning.

Robust spectral feature learning through recurrent graph propagation.

Abstract

Convolutional neural networks (CNNs) have achieved remarkable performance in hyperspectral image (HSI) classification over the last few years. Despite the progress that has been made, rich and informative spectral information of HSI has been largely underutilized by existing methods which employ convolutional kernels with limited size of receptive field in the spectral domain. To address this issue, we propose a spectral graph reasoning network (SGR) learning framework comprising two crucial modules: 1) a spectral decoupling module which unpacks and casts multiple spectral embeddings into a unified graph whose node corresponds to an individual spectral feature channel in the embedding space; the graph performs interpretable reasoning to aggregate and align spectral information to guide learning spectral-specific graph embeddings at multiple contextual levels 2) a spectral ensembling module explores the interactions and interdependencies across graph embedding hierarchy via a novel recurrent graph propagation mechanism. Experiments on two HSI datasets demonstrate that the proposed architecture can significantly improve the classification accuracy compared with the existing methods with a sizable margin.