Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification

Abstract In recent years, the hyperspectral classification algorithm based on deep learning has received widespread attention, but the existing network models have higher model complexity and require more time consumption. In order to further improve the accuracy of hyperspectral image classificatio...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Shuli Cheng, Liejun Wang, Anyu Du
Formato: article
Lenguaje:EN
Publicado: Nature Portfolio 2021
Materias:
R
Q
Acceso en línea:https://doaj.org/article/bfbf761333724195bd8a38c83405dff5
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
id oai:doaj.org-article:bfbf761333724195bd8a38c83405dff5
record_format dspace
spelling oai:doaj.org-article:bfbf761333724195bd8a38c83405dff52021-12-02T15:28:57ZAsymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification10.1038/s41598-021-97029-52045-2322https://doaj.org/article/bfbf761333724195bd8a38c83405dff52021-08-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-97029-5https://doaj.org/toc/2045-2322Abstract In recent years, the hyperspectral classification algorithm based on deep learning has received widespread attention, but the existing network models have higher model complexity and require more time consumption. In order to further improve the accuracy of hyperspectral image classification and reduce model complexity, this paper proposes an asymmetric coordinate attention spectral-spatial feature fusion network (ACAS2F2N) to capture distinguishing hyperspectral features. Specifically, adaptive asymmetric iterative attention was proposed to obtain the discriminative spectral-spatial features. Different from the common feature fusion method, this feature fusion method can adapt to most skip connection tasks. In addition, there is no manual parameter setting. Coordinate attention is used to obtain accurate coordinate information and channel relationship. The strip pooling module was introduced to increase the network’s receptive field and avoid irrelevant information brought by conventional convolution kernels. The proposed algorithm is tested on the mainstream hyperspectral datasets (IP, KSC, and Botswana), experimental results show that the proposed ACAS2F2N can achieve state-of-the-art performance with lower time complexity.Shuli ChengLiejun WangAnyu DuNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-17 (2021)
institution DOAJ
collection DOAJ
language EN
topic Medicine
R
Science
Q
spellingShingle Medicine
R
Science
Q
Shuli Cheng
Liejun Wang
Anyu Du
Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification
description Abstract In recent years, the hyperspectral classification algorithm based on deep learning has received widespread attention, but the existing network models have higher model complexity and require more time consumption. In order to further improve the accuracy of hyperspectral image classification and reduce model complexity, this paper proposes an asymmetric coordinate attention spectral-spatial feature fusion network (ACAS2F2N) to capture distinguishing hyperspectral features. Specifically, adaptive asymmetric iterative attention was proposed to obtain the discriminative spectral-spatial features. Different from the common feature fusion method, this feature fusion method can adapt to most skip connection tasks. In addition, there is no manual parameter setting. Coordinate attention is used to obtain accurate coordinate information and channel relationship. The strip pooling module was introduced to increase the network’s receptive field and avoid irrelevant information brought by conventional convolution kernels. The proposed algorithm is tested on the mainstream hyperspectral datasets (IP, KSC, and Botswana), experimental results show that the proposed ACAS2F2N can achieve state-of-the-art performance with lower time complexity.
format article
author Shuli Cheng
Liejun Wang
Anyu Du
author_facet Shuli Cheng
Liejun Wang
Anyu Du
author_sort Shuli Cheng
title Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification
title_short Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification
title_full Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification
title_fullStr Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification
title_full_unstemmed Asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification
title_sort asymmetric coordinate attention spectral-spatial feature fusion network for hyperspectral image classification
publisher Nature Portfolio
publishDate 2021
url https://doaj.org/article/bfbf761333724195bd8a38c83405dff5
work_keys_str_mv AT shulicheng asymmetriccoordinateattentionspectralspatialfeaturefusionnetworkforhyperspectralimageclassification
AT liejunwang asymmetriccoordinateattentionspectralspatialfeaturefusionnetworkforhyperspectralimageclassification
AT anyudu asymmetriccoordinateattentionspectralspatialfeaturefusionnetworkforhyperspectralimageclassification
_version_ 1718387167149948928