Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network

In order to solve the problems of large volume and high hardware requirements of deep convolutional neural network model in missile-borne terminal environment, a lightweight network structure based on improved dual-channel attention mechanism is constructed. Aiming at the problem that the network li...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autor principal:	Song Tainian, Qin Weiwei, Liang Zhuo, Wang Kui, Liu Gang
Formato:	article
Lenguaje:	ZH
Publicado:	Editorial Office of Aero Weaponry 2021
Materias:	\|mobilenetv2\|attention mechanism\|image classification\|convolutional neural network\|lightweight network\|artificial intelligence Motor vehicles. Aeronautics. Astronautics TL1-4050
Acceso en línea:	https://doaj.org/article/f0d4280fd3174199839c86dc03ae0a88
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:f0d4280fd3174199839c86dc03ae0a88
record_format	dspace
spelling	oai:doaj.org-article:f0d4280fd3174199839c86dc03ae0a882021-11-30T00:13:23ZImproved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network1673-504810.12132/ISSN.1673-5048.2020.0248https://doaj.org/article/f0d4280fd3174199839c86dc03ae0a882021-10-01T00:00:00Zhttps://www.aeroweaponry.avic.com/fileup/1673-5048/PDF/1636698938723-1453477565.pdfhttps://doaj.org/toc/1673-5048In order to solve the problems of large volume and high hardware requirements of deep convolutional neural network model in missile-borne terminal environment, a lightweight network structure based on improved dual-channel attention mechanism is constructed. Aiming at the problem that the network lightweight will sacrifice the classification accuracy, taking the MobileNetV2 lightweight network as the network basic structure, the self-designed attention module is introduced, and the MobileNetV2 network architecture based on SPP-DCAM module is designed to increase the weight of the significant feature map of convolutional layer learning, so as to improve the classification accuracy. The designed spatial information is input in parallel with channel information. By defining 1×1 and 3×3 small convolution, the computation amount and computational complexity are reduced on the basis of ensuring the lightweight of the structure. Finally, an experimental comparison is conducted on the cifar-100 image classification dataset. The results show that the classification accuracy of improved MobileNetV2 is better than that of the traditional VGG16, ResNet18 and DenseNet convoluted networks with the same number of parameters and computational complexity, and the comprehensive performance is stronger, which is more suitable for rapid classification under the condition of limited onboard computational resources.Song Tainian, Qin Weiwei, Liang Zhuo, Wang Kui, Liu GangEditorial Office of Aero Weaponryarticle\|mobilenetv2\|attention mechanism\|image classification\|convolutional neural network\|lightweight network\|artificial intelligenceMotor vehicles. Aeronautics. AstronauticsTL1-4050ZHHangkong bingqi, Vol 28, Iss 5, Pp 81-85 (2021)
institution	DOAJ
collection	DOAJ
language	ZH
topic	\|mobilenetv2\|attention mechanism\|image classification\|convolutional neural network\|lightweight network\|artificial intelligence Motor vehicles. Aeronautics. Astronautics TL1-4050
spellingShingle	\|mobilenetv2\|attention mechanism\|image classification\|convolutional neural network\|lightweight network\|artificial intelligence Motor vehicles. Aeronautics. Astronautics TL1-4050 Song Tainian, Qin Weiwei, Liang Zhuo, Wang Kui, Liu Gang Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network
description	In order to solve the problems of large volume and high hardware requirements of deep convolutional neural network model in missile-borne terminal environment, a lightweight network structure based on improved dual-channel attention mechanism is constructed. Aiming at the problem that the network lightweight will sacrifice the classification accuracy, taking the MobileNetV2 lightweight network as the network basic structure, the self-designed attention module is introduced, and the MobileNetV2 network architecture based on SPP-DCAM module is designed to increase the weight of the significant feature map of convolutional layer learning, so as to improve the classification accuracy. The designed spatial information is input in parallel with channel information. By defining 1×1 and 3×3 small convolution, the computation amount and computational complexity are reduced on the basis of ensuring the lightweight of the structure. Finally, an experimental comparison is conducted on the cifar-100 image classification dataset. The results show that the classification accuracy of improved MobileNetV2 is better than that of the traditional VGG16, ResNet18 and DenseNet convoluted networks with the same number of parameters and computational complexity, and the comprehensive performance is stronger, which is more suitable for rapid classification under the condition of limited onboard computational resources.
format	article
author	Song Tainian, Qin Weiwei, Liang Zhuo, Wang Kui, Liu Gang
author_facet	Song Tainian, Qin Weiwei, Liang Zhuo, Wang Kui, Liu Gang
author_sort	Song Tainian, Qin Weiwei, Liang Zhuo, Wang Kui, Liu Gang
title	Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network
title_short	Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network
title_full	Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network
title_fullStr	Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network
title_full_unstemmed	Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network
title_sort	improved dual-channel attention mechanism image classification method for lightweight network
publisher	Editorial Office of Aero Weaponry
publishDate	2021
url	https://doaj.org/article/f0d4280fd3174199839c86dc03ae0a88
work_keys_str_mv	AT songtainianqinweiweiliangzhuowangkuiliugang improveddualchannelattentionmechanismimageclassificationmethodforlightweightnetwork
_version_	1718406898461442048

Improved Dual-Channel Attention Mechanism Image Classification Method for Lightweight Network

Ejemplares similares