Dual Cross-Entropy Loss for Small-Sample Fine-Grained Vehicle Classification

doi:10.1109/TVT.2019.2895651

CORC > 兰州理工大学 > 兰州理工大学

	Dual Cross-Entropy Loss for Small-Sample Fine-Grained Vehicle Classification
	Li, Xiaoxu 1; Yu, Liyun 1; Chang, Dongliang 1; Ma, Zhanyu 2; Cao, Jie 1
刊名	IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
	2019-05
卷号	68 期号:5 页码:4204-4212
关键词	Cross-entropy loss fine-grained vehicle classification deep neural networks
ISSN号	0018-9545
DOI	10.1109/TVT.2019.2895651
英文摘要	Fine-grained vehicle classification is a challenging topic in computer vision due to the high intraclass variance and low interclass variance. Recently, considerable progress has been made in fine-grained vehicle classification due to the huge success of deep neural networks. Most studies of fine-grained vehicle classification based on neural networks, focus on the neural network structure to improve the classification performance. In contrast to existing works on fine-grained vehicle classification, we focus on the loss function of the neural network. We add a regularization term to the cross-entropy loss and propose a new loss function, Dual Cross-Entropy Loss. The regularization term places a constraint on the probability that a data point is assigned to a class other than its ground-truth class, which can alleviate the vanishing of the gradient when the value of the cross-entropy loss is close to zero. To demonstrate the effectiveness of our loss function, we perform two sets of experiments. The first set is conducted on a small-sample fine-grained vehicle classification dataset, the Stanford Cars-196 dataset. The second set is conducted on two small-sample datasets, the LabelMe dataset and the UIUC-Sports dataset, as well as on one large-sample dataset, the CIFAR-10 dataset. The experimental results show that the proposed loss function improves the fine-grained vehicle classification performance and has good performance on three other general image classification tasks.
资助项目	Natural Science Foundation of Gansu Province, China[17JR5RA125]
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:000470017500011
状态	已发表
内容类型	期刊论文
源URL	[http://119.78.100.223/handle/2XXMBERH/31896]
专题	兰州理工大学
通讯作者	Ma, Zhanyu
作者单位	1.Lanzhou Univ Technol, Sch Comp & Commun, Lanzhou 730050, Gansu, Peoples R China 2.Beijing Univ Posts & Telecommun, Pattern Recognit & Intelligent Syst Lab, Sch Informat & Commun Engn, Beijing 100876, Peoples R China
推荐引用方式 GB/T 7714	Li, Xiaoxu,Yu, Liyun,Chang, Dongliang,et al. Dual Cross-Entropy Loss for Small-Sample Fine-Grained Vehicle Classification[J]. IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY,2019,68(5):4204-4212.
APA	Li, Xiaoxu,Yu, Liyun,Chang, Dongliang,Ma, Zhanyu,&Cao, Jie.(2019).Dual Cross-Entropy Loss for Small-Sample Fine-Grained Vehicle Classification.IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY,68(5),4204-4212.
MLA	Li, Xiaoxu,et al."Dual Cross-Entropy Loss for Small-Sample Fine-Grained Vehicle Classification".IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY 68.5(2019):4204-4212.