3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples

Owing to the outstanding feature extraction capability, convolutional neural networks (CNNs) have been widely applied in hyperspectral image (HSI) classification problems and have achieved an impressive performance. However, it is well known that 2D convolution suffers from the absent consideration...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yuchao Feng, Jianwei Zheng, Mengjie Qin, Cong Bai, Jinglin Zhang
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	3D-2D mixed convolutional neural network (MCNN) hyperspectral image (HSI) classification principal component analysis (PCA) 3D octave and 2D vanilla mixed convolutions homology shifting Science Q
Acceso en línea:	https://doaj.org/article/000accfbcf8a49019efa500682411c25
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:000accfbcf8a49019efa500682411c25
record_format	dspace
spelling	oai:doaj.org-article:000accfbcf8a49019efa500682411c252021-11-11T18:55:44Z3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples10.3390/rs132144072072-4292https://doaj.org/article/000accfbcf8a49019efa500682411c252021-11-01T00:00:00Zhttps://www.mdpi.com/2072-4292/13/21/4407https://doaj.org/toc/2072-4292Owing to the outstanding feature extraction capability, convolutional neural networks (CNNs) have been widely applied in hyperspectral image (HSI) classification problems and have achieved an impressive performance. However, it is well known that 2D convolution suffers from the absent consideration of spectral information, while 3D convolution requires a huge amount of computational cost. In addition, the cost of labeling and the limitation of computing resources make it urgent to improve the generalization performance of the model with scarcely labeled samples. To relieve these issues, we design an end-to-end 3D octave and 2D vanilla mixed CNN, namely Oct-MCNN-HS, based on the typical 3D-2D mixed CNN (MCNN). It is worth mentioning that two feature fusion operations are deliberately constructed to climb the top of the discriminative features and practical performance. That is, 2D vanilla convolution merges the feature maps generated by 3D octave convolutions along the channel direction, and homology shifting aggregates the information of the pixels locating at the same spatial position. Extensive experiments are conducted on four publicly available HSI datasets to evaluate the effectiveness and robustness of our model, and the results verify the superiority of Oct-MCNN-HS both in efficacy and efficiency.Yuchao FengJianwei ZhengMengjie QinCong BaiJinglin ZhangMDPI AGarticle3D-2D mixed convolutional neural network (MCNN)hyperspectral image (HSI) classificationprincipal component analysis (PCA)3D octave and 2D vanilla mixed convolutionshomology shiftingScienceQENRemote Sensing, Vol 13, Iss 4407, p 4407 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	3D-2D mixed convolutional neural network (MCNN) hyperspectral image (HSI) classification principal component analysis (PCA) 3D octave and 2D vanilla mixed convolutions homology shifting Science Q
spellingShingle	3D-2D mixed convolutional neural network (MCNN) hyperspectral image (HSI) classification principal component analysis (PCA) 3D octave and 2D vanilla mixed convolutions homology shifting Science Q Yuchao Feng Jianwei Zheng Mengjie Qin Cong Bai Jinglin Zhang 3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples
description	Owing to the outstanding feature extraction capability, convolutional neural networks (CNNs) have been widely applied in hyperspectral image (HSI) classification problems and have achieved an impressive performance. However, it is well known that 2D convolution suffers from the absent consideration of spectral information, while 3D convolution requires a huge amount of computational cost. In addition, the cost of labeling and the limitation of computing resources make it urgent to improve the generalization performance of the model with scarcely labeled samples. To relieve these issues, we design an end-to-end 3D octave and 2D vanilla mixed CNN, namely Oct-MCNN-HS, based on the typical 3D-2D mixed CNN (MCNN). It is worth mentioning that two feature fusion operations are deliberately constructed to climb the top of the discriminative features and practical performance. That is, 2D vanilla convolution merges the feature maps generated by 3D octave convolutions along the channel direction, and homology shifting aggregates the information of the pixels locating at the same spatial position. Extensive experiments are conducted on four publicly available HSI datasets to evaluate the effectiveness and robustness of our model, and the results verify the superiority of Oct-MCNN-HS both in efficacy and efficiency.
format	article
author	Yuchao Feng Jianwei Zheng Mengjie Qin Cong Bai Jinglin Zhang
author_facet	Yuchao Feng Jianwei Zheng Mengjie Qin Cong Bai Jinglin Zhang
author_sort	Yuchao Feng
title	3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples
title_short	3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples
title_full	3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples
title_fullStr	3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples
title_full_unstemmed	3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples
title_sort	3d octave and 2d vanilla mixed convolutional neural network for hyperspectral image classification with limited samples
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/000accfbcf8a49019efa500682411c25
work_keys_str_mv	AT yuchaofeng 3doctaveand2dvanillamixedconvolutionalneuralnetworkforhyperspectralimageclassificationwithlimitedsamples AT jianweizheng 3doctaveand2dvanillamixedconvolutionalneuralnetworkforhyperspectralimageclassificationwithlimitedsamples AT mengjieqin 3doctaveand2dvanillamixedconvolutionalneuralnetworkforhyperspectralimageclassificationwithlimitedsamples AT congbai 3doctaveand2dvanillamixedconvolutionalneuralnetworkforhyperspectralimageclassificationwithlimitedsamples AT jinglinzhang 3doctaveand2dvanillamixedconvolutionalneuralnetworkforhyperspectralimageclassificationwithlimitedsamples
_version_	1718431624672051200

3D Octave and 2D Vanilla Mixed Convolutional Neural Network for Hyperspectral Image Classification with Limited Samples

Ejemplares similares