期刊
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
卷 18, 期 1, 页码 157-161出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/LGRS.2020.2966239
关键词
Convolution; Feature extraction; Laplace equations; Task analysis; Data models; Distance measurement; Hyperspectral sensors; Graph attention networks (GATs); hyperspectral images (HSIs); semisupervised classification; spatial– spectral graph
类别
资金
- National Natural Science Foundation of China [61971141, 61731021]
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.
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.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据