A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.

Hyperspectral Image (HSI) classification tasks are usually impacted by Convolutional Neural Networks (CNN). Specifically, the majority of models using traditional convolutions for HSI classification tasks extract redundant information due to the convolution layer, which makes the subsequent network...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuping Yin, Haodong Zhu, Lin Wei
Format: Article
Language:English
Published: Public Library of Science (PLoS) 2025-01-01
Series:PLoS ONE
Online Access:https://doi.org/10.1371/journal.pone.0322345
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325292199346176
author Yuping Yin
Haodong Zhu
Lin Wei
author_facet Yuping Yin
Haodong Zhu
Lin Wei
author_sort Yuping Yin
collection DOAJ
description Hyperspectral Image (HSI) classification tasks are usually impacted by Convolutional Neural Networks (CNN). Specifically, the majority of models using traditional convolutions for HSI classification tasks extract redundant information due to the convolution layer, which makes the subsequent network structure produce a large number of parameters and complex computations, so as to limit their classification effectiveness, particularly in situations with constraints on computational power and storage capacity. To address these issues, this paper proposes a lightweight multi-layer feature fusion classification method for hyperspectral images based on spatial and channel reconstruction (SCNet). Firstly, this method reduces redundant computations of spatial and spectral features by introducing Spatial and Channel Reconstruction Convolutions (SCConv), a novel convolutional compression method. Secondly, the proposed network backbone is stacked with multiple SCConv modules, which allows the network to capture spatial and spectral features that are more beneficial for hyperspectral image classification. Finally, to effectively utilize the multi-layer feature information generated by SCConv modules, a multi-layer feature fusion (MLFF) unit was designed to connect multiple feature maps at different depths, thereby obtaining a more robust feature representation. The experimental results demonstrate that, compared to seven other hyperspectral image classification methods, this network has significant advantages in terms of the number of parameters, model complexity, and testing time. These findings have been validated through experiments on four benchmark datasets.
format Article
id doaj-art-d7a6dc7d0e0848999e08bd87c0febaa7
institution Kabale University
issn 1932-6203
language English
publishDate 2025-01-01
publisher Public Library of Science (PLoS)
record_format Article
series PLoS ONE
spelling doaj-art-d7a6dc7d0e0848999e08bd87c0febaa72025-08-20T03:48:27ZengPublic Library of Science (PLoS)PLoS ONE1932-62032025-01-01205e032234510.1371/journal.pone.0322345A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.Yuping YinHaodong ZhuLin WeiHyperspectral Image (HSI) classification tasks are usually impacted by Convolutional Neural Networks (CNN). Specifically, the majority of models using traditional convolutions for HSI classification tasks extract redundant information due to the convolution layer, which makes the subsequent network structure produce a large number of parameters and complex computations, so as to limit their classification effectiveness, particularly in situations with constraints on computational power and storage capacity. To address these issues, this paper proposes a lightweight multi-layer feature fusion classification method for hyperspectral images based on spatial and channel reconstruction (SCNet). Firstly, this method reduces redundant computations of spatial and spectral features by introducing Spatial and Channel Reconstruction Convolutions (SCConv), a novel convolutional compression method. Secondly, the proposed network backbone is stacked with multiple SCConv modules, which allows the network to capture spatial and spectral features that are more beneficial for hyperspectral image classification. Finally, to effectively utilize the multi-layer feature information generated by SCConv modules, a multi-layer feature fusion (MLFF) unit was designed to connect multiple feature maps at different depths, thereby obtaining a more robust feature representation. The experimental results demonstrate that, compared to seven other hyperspectral image classification methods, this network has significant advantages in terms of the number of parameters, model complexity, and testing time. These findings have been validated through experiments on four benchmark datasets.https://doi.org/10.1371/journal.pone.0322345
spellingShingle Yuping Yin
Haodong Zhu
Lin Wei
A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.
PLoS ONE
title A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.
title_full A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.
title_fullStr A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.
title_full_unstemmed A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.
title_short A lightweight hyperspectral image multi-layer feature fusion classification method based on spatial and channel reconstruction.
title_sort lightweight hyperspectral image multi layer feature fusion classification method based on spatial and channel reconstruction
url https://doi.org/10.1371/journal.pone.0322345
work_keys_str_mv AT yupingyin alightweighthyperspectralimagemultilayerfeaturefusionclassificationmethodbasedonspatialandchannelreconstruction
AT haodongzhu alightweighthyperspectralimagemultilayerfeaturefusionclassificationmethodbasedonspatialandchannelreconstruction
AT linwei alightweighthyperspectralimagemultilayerfeaturefusionclassificationmethodbasedonspatialandchannelreconstruction
AT yupingyin lightweighthyperspectralimagemultilayerfeaturefusionclassificationmethodbasedonspatialandchannelreconstruction
AT haodongzhu lightweighthyperspectralimagemultilayerfeaturefusionclassificationmethodbasedonspatialandchannelreconstruction
AT linwei lightweighthyperspectralimagemultilayerfeaturefusionclassificationmethodbasedonspatialandchannelreconstruction