期刊论文

Xiong, XR

英文

Applied Sciences-Basel

2076-3417

2024

14

6

2327-

10.3390/app14062327

This work was supported in part by Hubei’s Key Project of Research and Development Program under Grant 2023BBB046, and National Natural Science Foundation of China under Grant U23B2050, and Excellent young and middle-aged scientific and technological innovation teams in colleges and universities of Hubei Province under Grant T2021009, and NSFC-CAAC under Grant U1833119, and Science and Technology Program of Hubei Provincial Education Department under Grant D20221604, and the Natural Science Foundation of Hubei Province of China under Grant 2023AFB351, and the University-Industry Collaborative Education Program under Grant 230705841293521.

本校为第一且通讯机构

The immense representation power of deep learning frameworks has kept them in the spotlight in hyperspectral image (HSI) classification. Graph Convolutional Neural Networks (GCNs) can be used to compensate for the lack of spatial information in Convolutional Neural Networks (CNNs). However, most GCNs construct graph data structures based on pixel points, which requires the construction of neighborhood matrices on all data. Meanwhile, the setting of GCNs to construct similarity relations based on spatial structure is not fully applicable to HSIs. To make the network more compatible with HSIs, w...