Lanzhou University of Technology Institutional Repository (LUT_IR)
Dual Cross-Entropy Loss for Small-Sample Fine-Grained Vehicle Classification | |
Li, Xiaoxu1; Yu, Liyun1; Chang, Dongliang1; Ma, Zhanyu2; Cao, Jie1 | |
2019-05 | |
发表期刊 | IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY |
ISSN | 0018-9545 |
卷号 | 68期号:5页码:4204-4212 |
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. |
关键词 | Cross-entropy loss fine-grained vehicle classification deep neural networks |
DOI | 10.1109/TVT.2019.2895651 |
收录类别 | SCI ; SCIE |
语种 | 英语 |
资助项目 | Natural Science Foundation of Gansu Province, China[17JR5RA125] |
WOS研究方向 | Engineering ; Telecommunications ; Transportation |
WOS类目 | Engineering, Electrical & Electronic ; Telecommunications ; Transportation Science & Technology |
WOS记录号 | WOS:000470017500011 |
出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
EI入藏号 | 20192307011087 |
EI主题词 | Neural networks |
EI分类号 | 641.1 Thermodynamics - 662.1 Automobiles - 716.1 Information Theory and Signal Processing |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | https://ir.lut.edu.cn/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 |
第一作者单位 | 兰州理工大学 |
第一作者的第一单位 | 兰州理工大学 |
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. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
Li-2019-Dual Cross-E(2367KB) | 期刊论文 | 出版稿 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论