Multiscale Wavelet and Graph Network With Spectral Self-Attention for Hyperspectral Image Classification

Hyperspectral image (HSI) classification has gained increasing attention in remote sensing due to its finegrained spectral information. However, existing methods still face significant challenges in preserving high-frequency details, modeling long-range dependencies, and integrating spectral, spatia...

Полное описание

Библиографические подробности

Главные авторы:	Anyembe C. Shibwabo, Zou Bin, Tahir Arshad, Jorge Abraham Rios Suarez
Формат:	Artigo
Язык:	Inglês
Опубликовано:	IEEE 2025-01-01
Серии:	IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Предметы:	Attention mechanism convolutional neural network (CNN) feature integration graph convolution network (GCN) hyperspectral image (HSI) classification
Online-ссылка:	https://ieeexplore.ieee.org/document/11018235/
Метки:	Добавить метку Нет меток, Требуется 1-ая метка записи!