Hyperspectral Image Classification via Spectral Pooling and Hybrid Transformer

Hyperspectral Image Classification via Spectral Pooling and Hybrid Transformer

Hyperspectral images (HSIs) contain spatially structured information and pixel-level sequential spectral attributes. The continuous spectral features contain hundreds of wavelength bands and the differences between spectra are essential for achieving fine-grained classification. Due to the limited r...

Full description

Bibliographic Details
Main Authors: Chen Ma, Junjun Jiang, Huayi Li, Xiaoguang Mei, Chengchao Bai
Format: Article
Language:English
Published: MDPI AG 2022-09-01
Series:Remote Sensing
Subjects:
hyperspectral image (HSI) classification
convolutional neural networks (CNNs)
self-attention mechanism
subtle discrepancy
feature fusion strategy
Online Access:https://www.mdpi.com/2072-4292/14/19/4732

Internet

https://www.mdpi.com/2072-4292/14/19/4732

Similar Items