Domain Adaptive Attention Learning for Unsupervised Person Re-Identification

被引:0
|
作者
Huang, Yangru [1 ]
Peng, Peixi [2 ]
Jin, Yi [1 ]
Li, Yidong [1 ]
Xing, Junliang [2 ]
Ge, Shiming [3 ]
机构
[1] Beijing Jiaotong Univ, Sch Comp & Informat Technol, Beijing, Peoples R China
[2] Chinese Acad Sci, Inst Automat, Beijing, Peoples R China
[3] Chinese Acad Sci, Inst Informat Engn, Beijing, Peoples R China
关键词
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 (Re-ID) across multiple datasets is a challenging task due to two main reasons: the presence of large cross-dataset distinctions and the absence of annotated target instances. To address these two issues, this paper proposes a domain adaptive attention learning approach to reliably transfer discriminative representation from the labeled source domain to the unlabeled target domain. In this approach, a domain adaptive attention model is learned to separate the feature map into domain-shared part and domain-specific part. In this manner, the domain-shared part is used to capture transferable cues that can compensate cross-dataset distinctions and give positive contributions to the target task, while the domain-specific part aims to model the noisy information to avoid the negative transfer caused by domain diversity. A soft label loss is further employed to take full use of unlabeled target data by estimating pseudo labels. Extensive experiments on the Market-1501, DukeMTMC-reID and MSMT17 benchmarks demonstrate the proposed approach outperforms the state-of-the-arts.
引用
收藏
页码:11069 / 11076
页数:8
相关论文
共 50 条
  • [1] Dual Attention Network for Unsupervised Domain Adaptive Person Re-Identification
    Chen, Haiqin
    Wang, Hongyuan
    Ding, Zongyuan
    Li, Penghui
    IEEE ACCESS, 2023, 11 : 88184 - 88192
  • [2] Learning Feature Fusion for Unsupervised Domain Adaptive Person Re-identification
    Ding, Jin
    Zhou, Xue
    2022 26TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR), 2022, : 2613 - 2619
  • [3] Unsupervised domain adaptive person re-identification via camera penalty learning
    Zhu, Xiaodi
    Li, Yanfeng
    Sun, Jia
    Chen, Houjin
    Zhu, Jinlei
    MULTIMEDIA TOOLS AND APPLICATIONS, 2021, 80 (10) : 15215 - 15232
  • [4] Learning with noisy labels method for unsupervised domain adaptive person re-identification
    Zhu, Xiaodi
    Li, Yanfeng
    Sun, Jia
    Chen, Houjin
    Zhu, Jinlei
    NEUROCOMPUTING, 2021, 452 : 78 - 88
  • [5] Unsupervised domain adaptive person re-identification via camera penalty learning
    Xiaodi Zhu
    Yanfeng Li
    Jia Sun
    Houjin Chen
    Jinlei Zhu
    Multimedia Tools and Applications, 2021, 80 : 15215 - 15232
  • [6] JAC-Net: Joint learning with adaptive exploration and concise attention for unsupervised domain adaptive person re-identification
    Guo, Yingchun
    Feng, Fang
    Hao, Xiaoke
    Chen, Xi
    Neurocomputing, 2022, 483 : 262 - 274
  • [7] JAC-Net: Joint learning with adaptive exploration and concise attention for unsupervised domain adaptive person re-identification
    Guo, Yingchun
    Feng, Fang
    Hao, Xiaoke
    Chen, Xi
    NEUROCOMPUTING, 2022, 483 : 262 - 274
  • [8] Attention-disentangled re-ID network for unsupervised domain adaptive person re-identification
    Wang, Lun
    Huang, Jiapeng
    Huang, Luoqi
    Wang, Fei
    Gao, Changxin
    Li, Jinsheng
    Xiao, Fei
    Luo, Dapeng
    Knowledge-Based Systems, 2024, 304
  • [9] Domain Adaptive Learning with Multi-Granularity Features for Unsupervised Person Re-identification
    FU Lihua
    DU Yubin
    DING Yu
    WANG Dan
    JIANG Hanxu
    ZHANG Haitao
    Chinese Journal of Electronics, 2022, 31 (01) : 116 - 128
  • [10] Domain Adaptive Learning with Multi-Granularity Features for Unsupervised Person Re-identification
    Fu Lihua
    Du Yubin
    Ding Yu
    Wang Dan
    Jiang Hanxu
    Zhang Haitao
    CHINESE JOURNAL OF ELECTRONICS, 2022, 31 (01) : 116 - 128