ACTIVE LEARNING WITH RE-SAMPLING FOR SUPPORT VECTOR MACHINE IN PERSON RE-IDENTIFICATION

被引:0
|
作者
Xiang, Jin-Peng [1 ]
Bai, Yang [1 ]
机构
[1] S China Univ Technol, Sch Comp Sci & Engn, Machine Learning & Cybernet Res Ctr, Guangzhou 510006, Guangdong, Peoples R China
关键词
Person re-identification; active learning; re-sampling; surveillance;
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Person re-identification is defined as to find the same person who re-occurred in a multi-camera surveillance system. A classifier for person re-identification may suffer from the imbalance dataset problem since the number of the targeted images is much less than irrelevant images. In this paper, we proposed over-sampling and under-sampling method for the active learning method for person re-identification. The sampling method is activated when the imbalance level of the training set is higher than a preset value during iteration of the active learning. The effect of the imbalance problem is reduced. Experimental results show the active learning method with the proposed re-sampling method scarifies the true negative rate to achieve higher true positive rate, which is more important in person re-identification.
引用
收藏
页码:597 / 602
页数:6
相关论文
共 50 条
  • [1] Person re-identification by integrating metric learning and support vector machine
    Zhao, Dandan
    Wang, Hongbin
    Yin, Hongpeng
    Yu, Zhengtao
    Li, Huafeng
    [J]. SIGNAL PROCESSING, 2020, 166
  • [2] Combining Re-sampling with Twin Support Vector Machine for Imbalanced Data Classification
    Cao, Lu
    Shen, Hong
    [J]. 2016 17TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED COMPUTING, APPLICATIONS AND TECHNOLOGIES (PDCAT), 2016, : 325 - 329
  • [3] RE-SAMPLING THE RE-SAMPLING IDEA
    BLESSER, B
    [J]. DB-SOUND ENGINEERING MAGAZINE, 1983, 17 (08): : 28 - &
  • [4] Early Active Learning with Pairwise Constraint for Person Re-identification
    Liu, Wenhe
    Chang, Xiaojun
    Chen, Ling
    Yang, Yi
    [J]. MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2017, PT I, 2017, 10534 : 103 - 118
  • [5] Person Re-Identification by Saliency Learning
    Zhao, Rui
    Oyang, Wanli
    Wang, Xiaogang
    [J]. IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2017, 39 (02) : 356 - 370
  • [6] Support Neighbor Loss for Person Re-Identification
    Li, Kai
    Ding, Zhengming
    Li, Kunpeng
    Zhang, Yulun
    Fu, Yun
    [J]. PROCEEDINGS OF THE 2018 ACM MULTIMEDIA CONFERENCE (MM'18), 2018, : 1492 - 1500
  • [7] Person Re-identification
    Bak, Slawomir
    Bremond, Francois
    [J]. ERCIM NEWS, 2013, (95): : 33 - 34
  • [8] Dense Invariant Feature Based Support Vector Ranking for Person Re-identification
    Tan, Shoubiao
    Zheng, Feng
    Shao, Ling
    [J]. 2015 IEEE GLOBAL CONFERENCE ON SIGNAL AND INFORMATION PROCESSING (GLOBALSIP), 2015, : 687 - 691
  • [9] Rethinking Sampling Strategies for Unsupervised Person Re-Identification
    Han, Xumeng
    Yu, Xuehui
    Li, Guorong
    Zhao, Jian
    Pan, Gang
    Ye, Qixiang
    Jiao, Jianbin
    Han, Zhenjun
    [J]. IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 29 - 42
  • [10] REGULARIZATION IN METRIC LEARNING FOR PERSON RE-IDENTIFICATION
    Si, Jianlou
    Zhang, Honggang
    Li, Chun-Guang
    [J]. 2015 IEEE INTERNATIONAL CONFERENCE ON IMAGE PROCESSING (ICIP), 2015, : 2309 - 2313