Multi-level graph learning network for hyperspectral image classification

作者：

Highlights：

• Incorporate multi-level contextual information to represent different region features precisely.

• Aim to achieve the mutual benefit of the representation learning and graph reconstruction modules.

• The first GCN-based method to adaptively learn the graph structural information for HSI classification.

摘要

•Incorporate multi-level contextual information to represent different region features precisely.•Aim to achieve the mutual benefit of the representation learning and graph reconstruction modules.•The first GCN-based method to adaptively learn the graph structural information for HSI classification.

论文关键词：Graph convolutional network,Graph-based machine learning,Hyperspectral image classification,Remote sensing,Graph structural learning

论文评审过程：Received 30 August 2021, Revised 24 January 2022, Accepted 7 April 2022, Available online 14 April 2022, Version of Record 21 April 2022.

论文官网地址：https://doi.org/10.1016/j.patcog.2022.108705