Semisupervised Classification for Hyperspectral Images Using Graph Attention Networks

For hyperspectral images (HSIs), the imbalance between the high dimensionality and the limited labeled samples has been a main obstacle to classification task. As a solution, semisupervised learning utilizing both labeled and unlabeled samples has shown its potential. In this letter, a novel semisupervised classification framework based on graph attention networks (GATs) for HSIs is proposed. Spatial-spectral joint measurement is designed for the graph model construction to make full use of spatial information. In the convolution process, different weights are assigned to different neighboring nodes according to their attention coefficients, avoiding designing connection weights artificially in previous graph convolution networks (GCNs). Experimental results on multiple hyperspectral data sets with various contexts and resolutions demonstrate that the proposed method outperforms several state-of-the-art graph-based methods.

Automated summary

A novel semisupervised classification framework for hyperspectral images based on graph attention networks is proposed, utilizing spatial-spectral joint measurement and assigning different weights to neighboring nodes in the convolution process. Experimental results show that the method outperforms several state-of-the-art graph-based methods.