Hyperspectral Image Classification With Multiattention Fusion Network

Hyperspectral image (HSI) has hundreds of continuous bands that contain a lot of redundant information. Besides, a spatial patch of a hyperspectral cube often contains some pixels different from the center pixel category, which are usually called interference pixels. The existence of such interferen...

Full description

Saved in:
Bibliographic Details
Published in:IEEE geoscience and remote sensing letters 2022, Vol.19, p.1-5
Main Authors: Li, Zhaokui, Zhao, Xiaodan, Xu, Yimin, Li, Wei, Zhai, Lin, Fang, Zhuoqun, Shi, Xiangbin
Format: Article
Language:English
Subjects:
Band attention
Classification
Convolution
Data mining
Feature extraction
hyperspectral image (HIS) classification
Hyperspectral imaging
Image classification
Interference
Modules
multilayer feature fusion
Pixels
Redundancy
Source code
spatial attention
Spatial resolution
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Hyperspectral image (HSI) has hundreds of continuous bands that contain a lot of redundant information. Besides, a spatial patch of a hyperspectral cube often contains some pixels different from the center pixel category, which are usually called interference pixels. The existence of such interference pixels has a negative effect on extracting more discriminative information. Therefore, in this letter, a multiattention fusion network (MAFN) for HSI classification is proposed. Compared with the current state-of-the-art methods, MAFN uses band attention module (BAM) and spatial attention module (SAM), respectively, to alleviate the influence of redundant bands and interfering pixels. In this way, MAFN realizes feature reuse and obtains complementary information from different levels by combining multiattention and multilevel fusion mechanisms, which can extract more representative features. Experiments were conducted on two public HSI data sets to demonstrate the effectiveness of MAFN. Our source code is available at https://github.com/Li-ZK/MAFN-2021 .
ISSN:1545-598X
1558-0571
DOI:10.1109/LGRS.2021.3052346