AF2GNN: Graph convolution with adaptive filters and aggregator fusion for hyperspectral image classification

Yao Ding, Zhili Zhang*, Xiaofeng Zhao, Danfeng Hong, Wei Li, Wei Cai, Ying Zhan

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

79 Citations (Scopus)

Abstract

Hyperspectral image classification (HSIC) is essential in remote sensing image analysis. Applying a graph neural network (GNN) to hyperspectral image (HSI) classification has attracted increasing attention. However, the available GNNs for HSIC only adopt a kind of graph filter and an aggregator, which cannot well deal with the problems of land cover discrimination, noise impaction, and spatial feature learning. To overcome these problems, a graph convolution with adaptive filters and aggregator fusion (AF2GNN) is developed for HSIC. To reduce the number of graph nodes, a superpixel segment algorithm is employed to refine the local spatial features of the HSI. A two-layer 1D CNN is proposed to transform the spectral features of superpixels. In addition, a linear function is designed to combine the different graph filters, with which the graph filter can be adaptively determined by training different weight matrices. Moreover, degree-scalers are defined to combine the multiple filters and present the graph structure. Finally, the AF2GNN is proposed to realize the adaptive filters and aggregator fusion mechanism within a single network. In the proposed network, a softMax function is utilized for graph feature interpretation and pixel-label prediction. Compared with state-of-the-art methods, the proposed method achieves superior experimental results.

Original languageEnglish
Pages (from-to)201-219
Number of pages19
JournalInformation Sciences
Volume602
DOIs
Publication statusPublished - Jul 2022

Keywords

  • Adaptive filters
  • Aggregators fusion
  • Graph neural network
  • Hyperspectral image classification

Fingerprint

Dive into the research topics of 'AF2GNN: Graph convolution with adaptive filters and aggregator fusion for hyperspectral image classification'. Together they form a unique fingerprint.

Cite this