Patch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples

Recently, data-driven methods represented by deep learning have been widely used in hyperspectral image (HSI) classification and achieved the promising success. However, using less labeled samples to obtain higher classification accuracy is still a challenging task. In this study, we propose a patch...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Bing Liu, Xuchu Yu
Formato:	article
Lenguaje:	EN
Publicado:	IEEE 2021
Materias:	Bilateral network deep learning (DL) hyperspectral image (HSI) classification Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
Acceso en línea:	https://doaj.org/article/d57a13efa2ed4762aad33712b09d495d
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:d57a13efa2ed4762aad33712b09d495d
record_format	dspace
spelling	oai:doaj.org-article:d57a13efa2ed4762aad33712b09d495d2021-11-04T23:00:09ZPatch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples2151-153510.1109/JSTARS.2021.3121334https://doaj.org/article/d57a13efa2ed4762aad33712b09d495d2021-01-01T00:00:00Zhttps://ieeexplore.ieee.org/document/9585561/https://doaj.org/toc/2151-1535Recently, data-driven methods represented by deep learning have been widely used in hyperspectral image (HSI) classification and achieved the promising success. However, using less labeled samples to obtain higher classification accuracy is still a challenging task. In this study, we propose a patch-free bilateral network (PBiNet) for HSI classification. In order to make better use of the features with different scales, PBiNet uses the spatial path and the semantic path to obtain different level features for classification. The spatial path with small stride is used to retain the spatial detail information. The semantic path with fast down sampling rate is used to retain high-level semantic information. Using fast downsampling rates is to expand the scope of receptive field, so that semantic branch can better focus on global information. Then we design a feature fusion module to fuse the features obtained by the two paths. Finally, we use the classification maps produced by different scale features to calculate the loss function to optimize the whole model. Due to the better use of different levels of features, the proposed method could achieve higher classification accuracy with limited labeled samples. More importantly, because the whole HSI is used as the input, the proposed method has higher computational efficiency. To verify the effectiveness of the proposed method, we carried out classification experiments on four popular HSI datasets. Quantitative and qualitative experimental results show that the accuracy of the proposed method exceeds the compared methods.Bing LiuXuchu YuIEEEarticleBilateral networkdeep learning (DL)hyperspectral image (HSI) classificationOcean engineeringTC1501-1800Geophysics. Cosmic physicsQC801-809ENIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 14, Pp 10794-10807 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Bilateral network deep learning (DL) hyperspectral image (HSI) classification Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809
spellingShingle	Bilateral network deep learning (DL) hyperspectral image (HSI) classification Ocean engineering TC1501-1800 Geophysics. Cosmic physics QC801-809 Bing Liu Xuchu Yu Patch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples
description	Recently, data-driven methods represented by deep learning have been widely used in hyperspectral image (HSI) classification and achieved the promising success. However, using less labeled samples to obtain higher classification accuracy is still a challenging task. In this study, we propose a patch-free bilateral network (PBiNet) for HSI classification. In order to make better use of the features with different scales, PBiNet uses the spatial path and the semantic path to obtain different level features for classification. The spatial path with small stride is used to retain the spatial detail information. The semantic path with fast down sampling rate is used to retain high-level semantic information. Using fast downsampling rates is to expand the scope of receptive field, so that semantic branch can better focus on global information. Then we design a feature fusion module to fuse the features obtained by the two paths. Finally, we use the classification maps produced by different scale features to calculate the loss function to optimize the whole model. Due to the better use of different levels of features, the proposed method could achieve higher classification accuracy with limited labeled samples. More importantly, because the whole HSI is used as the input, the proposed method has higher computational efficiency. To verify the effectiveness of the proposed method, we carried out classification experiments on four popular HSI datasets. Quantitative and qualitative experimental results show that the accuracy of the proposed method exceeds the compared methods.
format	article
author	Bing Liu Xuchu Yu
author_facet	Bing Liu Xuchu Yu
author_sort	Bing Liu
title	Patch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples
title_short	Patch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples
title_full	Patch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples
title_fullStr	Patch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples
title_full_unstemmed	Patch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples
title_sort	patch-free bilateral network for hyperspectral image classification using limited samples
publisher	IEEE
publishDate	2021
url	https://doaj.org/article/d57a13efa2ed4762aad33712b09d495d
work_keys_str_mv	AT bingliu patchfreebilateralnetworkforhyperspectralimageclassificationusinglimitedsamples AT xuchuyu patchfreebilateralnetworkforhyperspectralimageclassificationusinglimitedsamples
_version_	1718444621906837504

Patch-Free Bilateral Network for Hyperspectral Image Classification Using Limited Samples

Ejemplares similares