Fine-Grained Vehicle Classification With Channel Max Pooling Modified CNNs

doi:10.1109/TVT.2019.2899972

CORC > 兰州理工大学 > 兰州理工大学

	Fine-Grained Vehicle Classification With Channel Max Pooling Modified CNNs
	Ma, Zhanyu 1; Chang, Dongliang 2; Xie, Jiyang 1; Ding, Yifeng 1; Wen, Shaoguo 3; Li, Xiaoxu 2; Si, Zhongwei 3; Guo, Jun 1
刊名	IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
	2019-04
卷号	68 期号:4 页码:3224-3233
关键词	Fine-grained vehicle classification convolutional neural network channel pooling feature extraction
ISSN号	0018-9545
DOI	10.1109/TVT.2019.2899972
英文摘要	Convolutional neural networks (CNNs) have recently shown excellent performance on the task of fine-grained vehicle classification, where the motivation is to identify the fine-grained categories of the given vehicles. Generally speaking, the main motivation of the conventional back-propagation algorithm is to optimize the loss function. The algorithm itself does not guarantee if the extracted features are discriminative for the task of classification. Intuitively, if we can learn more discriminative features with a relatively small number of feature maps, the generalization ability of the CNNs will be significantly improved. Therefore, we propose a channel max pooling (CMP) scheme, where a new layer is inserted between the fully connected layers and the convolutional layers. The proposed CMP scheme divides the feature maps into to several sub-groups. Then, it compresses the feature maps within each sub-group into a new one. The compression is carried out by selecting the maximum value among the same locations from different feature maps. Moreover, the proposed CMP layer has the advantage that it can reduce the number of parameters via reducing the number of channels in the CNNs. Experimental results on two fine-grained vehicle datasets demonstrate that the CMP modified CNNs can improve the classification accuracies on the task of fine-grained vehicle classification while a massive amount of parameters are reduced. Moreover, it has competitive performance when comparing with the-state-of-the-art methods.
WOS研究方向	Engineering ; Telecommunications ; Transportation
语种	英语
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
WOS记录号	WOS:000465241600015
内容类型	期刊论文
源URL	[http://119.78.100.223/handle/2XXMBERH/32004]
专题	兰州理工大学
作者单位	1.Beijing Univ Posts & Telecommun, Pattern Recognit & Intelligent Syst Lab, Beijing 100876, Peoples R China; 2.Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou 730050, Gansu, Peoples R China; 3.Beijing Univ Posts & Telecommun, Minist Educ, Key Lab Universal Commun, Beijing 100876, Peoples R China
推荐引用方式 GB/T 7714	Ma, Zhanyu,Chang, Dongliang,Xie, Jiyang,et al. Fine-Grained Vehicle Classification With Channel Max Pooling Modified CNNs[J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY,2019,68(4):3224-3233.
APA	Ma, Zhanyu.,Chang, Dongliang.,Xie, Jiyang.,Ding, Yifeng.,Wen, Shaoguo.,...&Guo, Jun.(2019).Fine-Grained Vehicle Classification With Channel Max Pooling Modified CNNs.IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY,68(4),3224-3233.
MLA	Ma, Zhanyu,et al."Fine-Grained Vehicle Classification With Channel Max Pooling Modified CNNs".IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 68.4(2019):3224-3233.