Graph Kolmogorov–Arnold Convolutional Network for Hyperspectral Image Classification

The graph neural network (GNN) exhibits noteworthy performance in hyperspectral image classification (HSIC) due to its efficient message-passing structure, which employs the multilayer perceptron (MLP) for feature extraction and utilizes nonlinear activation function between two layers of the networ...

Full description

Bibliographic Details

Published in:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Main Authors:	Hengyi Zheng, Hongjun Su, Zhaoyue Wu, Yiping Chen, Qian Du
Format:	Article
Language:	English
Published:	IEEE 2025-01-01
Subjects:	Extended morphological attribute profile (EMAP) graph neural network (GNN) hyperspectral image classification (HSIC) Kolmogorov–Arnold network (KAN)
Online Access:	https://ieeexplore.ieee.org/document/11021283/