Hyperspectral image classification with localized spectral filtering-based graph attention network

S. Pu, Y. Song, Y. Chen, Y. Li, J. Zhang, Q. Lin, X. Zhu, Y. Chen, H. Zeng, K. Liao, H. Yu, J. Yuan, S. Yu, W. Zuo

Research output: Contribution to journalConference articlepeer-review


Graph-based deep learning has been proved a promising approach that has an apparent superiority for learning graph data and modeling spatial topological relations between features. In particular, graph attention networks (GATs) are good at efficiently processing the graph-structured hyperspectral data by leveraging masked self-Attention layers to address the known shortcomings of previous frameworks based on graph convolutions or their approximations. In this study, we proposed a novel approach that combines localized spectral filtering and GAT for the hyperspectral image classification task. First, we conducted unsupervised t-SNE ( t-distributed stochastic neighbor embedding) manifold learning-based feature dimensionality reduction to create localized hyperspectral data cubes. Then, these feature cubes combined with localized adjacent matrices were fed into a shallow graph attention network in a supervised learning manner. Finally, we obtained credible classification results and promising classification performance in distinguishing diversified land covers through reducing the possible redundancy of spectral information and enhancing the expression of local spatial-spectral information. Experiments on two real hyperspectral data sets (that is, Indian Pines-A (IA) and Huanghekou (HH) data sets) demonstrated that the presented approach offers promising classification performance, that is, the GAT using t-SNE acquires superior performance than that of using PCA (principal component analysis), and also proves the great importance of combining spatial-and spectral information for hyperspectral image classification.

Original languageEnglish (US)
Pages (from-to)155-161
Number of pages7
JournalISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Issue number3
StatePublished - May 17 2022
Externally publishedYes
Event2022 24th ISPRS Congress on Imaging Today, Foreseeing Tomorrow, Commission III - Nice, France
Duration: Jun 6 2022Jun 11 2022


  • Graph attention network
  • Graphbased deep learning.
  • Hyperspectral image classification
  • Localized spectral filtering
  • Self-Attention

ASJC Scopus subject areas

  • Instrumentation
  • Environmental Science (miscellaneous)
  • Earth and Planetary Sciences (miscellaneous)


Dive into the research topics of 'Hyperspectral image classification with localized spectral filtering-based graph attention network'. Together they form a unique fingerprint.

Cite this