[1]张 璐,刘阿建.基于改进 Center Loss 函数的行人再辨识[J].计算机技术与发展,2019,29(09):45-50.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 009]
　ZHANG Lu,LIU A-jian.Pedestrian Re-identification Based on Improved Center Loss[J].,2019,29(09):45-50.[doi:10. 3969 / j. issn. 1673-629X. 2019. 09. 009]
点击复制

基于改进 Center Loss 函数的行人再辨识()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
29
期数:
2019年09期
页码:
45-50
栏目:
智能、算法、系统工程
出版日期:
2019-09-10

文章信息/Info

Title:
Pedestrian Re-identification Based on Improved Center Loss
文章编号:
1673-629X(2019)09-0045-06
作者:
张 璐1 ; 刘阿建2
1. 武汉大学,湖北 武汉 430061; 2. 太原理工大学 信息与计算机学院,山西 晋中 030600
Author(s):
ZHANG Lu1 ; LIU A-jian2
1. Wuhan University,Wuhan 430061,China; 2. School of Information and Computer,Taiyuan University of Technology,Jinzhong 030600,China
关键词:
行人再辨识; 深度学习; Center Loss; 分类损失函数
Keywords:
pedestrian re-identification; deep learning; Center Loss; classification loss function
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2019. 09. 009
摘要:
通过改进距离度量函数,在开集测试协议的基础上,对行人再辨识相关问题进行研究,使测量的行人特征满足以下两点:类间最小距离较大和类内最大距离较小。 目前还没有存在的算法能够满足这个条件。 文中采用 Center Loss 函数和分类损失函数相结合,使网络在分类损失与 Center Loss 函数的联合监督下,可以学习出更具判别性的行人特征。 其中,行人特征分辨性问题分类损失函数能很好地解决,但常规的 Center Loss 函数只能使类内最大距离较小,但未能解决类间最小距离较大的问题。 因此对 Center Loss 函数进行改进,在 Center Loss 函数中加入类间距离变量,使类间中心最小距离较大。 最后通过几组再辨识数据集的实验证明了提出的网络与改进 Center Loss 函数的优越性。
Abstract:
By improving the distance measurement function and on the basis of the open-collection test protocol,pedestrian re-identification related problems are studied to make the measured pedestrian characteristics meet the following two requirements:the minimum distance between classes is large and the maximum distance within classes is small. At present,there is no algorithm can satisfy the two goals. In this paper,Center Loss function and classification loss function are combined to make the network learn more discriminative pedestrian characteristics under the joint supervision. Among them,the classification loss function can solve problem of pedestrian feature resolution very well. The conventional Center Loss function can only make the maximum distance within the class smaller,but it can’t solve the problem that the minimum distance between classes is large. Therefore,we improve the Center Loss function by adding the variable of distance between different classes,which can make the minimum distance between different classes larger. Finally,the experiment shows that the improved classification loss function have a better realization.

相似文献/References:

[1]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(09):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[2]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(09):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[3]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(09):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(09):19.
[5]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(09):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[6]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(09):1.
[7]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(09):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[8]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(09):1.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(09):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(09):7.

更新日期/Last Update: 2019-09-10