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
  • [21] Refining Pseudo Labels for Unsupervised Domain Adaptive Person Re-Identification
    Xia, Limin
    Yu, Zhimin
    Ma, Wentao
    Zhu, Jiahui
    IEEE ACCESS, 2021, 9 : 121288 - 121301
  • [22] Style transfer for unsupervised domain-adaptive person re-identification
    Chong, Yanwen
    Peng, Chengwei
    Zhang, Jingjing
    Pan, Shaoming
    NEUROCOMPUTING, 2021, 422 : 314 - 321
  • [23] Unsupervised Attention Based Instance Discriminative Learning for Person Re-Identification
    Nikhal, Kshitij
    Riggan, Benjamin S.
    2021 IEEE WINTER CONFERENCE ON APPLICATIONS OF COMPUTER VISION WACV 2021, 2021, : 2421 - 2430
  • [24] Adaptive Exploration for Unsupervised Person Re-identification
    Ding, Yuhang
    Fan, Hehe
    Xu, Mingliang
    Yang, Yi
    ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS, 2020, 16 (01)
  • [25] Unsupervised Horizontal Pyramid Similarity Learning for Cross-Domain Adaptive Person Re-Identification
    Dong, Wenhui
    Qu, Peishu
    Liu, Chunsheng
    Tang, Yanke
    Gai, Ning
    IEEE ACCESS, 2021, 9 : 92901 - 92912
  • [26] Collaborative Feature Learning and Credible Soft Labeling for Unsupervised Domain Adaptive Person Re-Identification
    Wang, Haijian
    Yang, Meng
    2021 INTERNATIONAL JOINT CONFERENCE ON BIOMETRICS (IJCB 2021), 2021,
  • [27] Attention Mutual Teaching Network for Unsupervised Domain Adaptation Person Re-identification
    Zhang, Wenhao
    Liu, Chang
    Bo, Chunjuan
    Wang, Dong
    INTERNATIONAL SYMPOSIUM ON ARTIFICIAL INTELLIGENCE AND ROBOTICS 2021, 2021, 11884
  • [28] Sparse-attention augmented domain adaptation for unsupervised person re-identification
    Zhang, Wei
    Ye, Peijun
    Su, Tao
    Chen, Dihu
    Pattern Recognition Letters, 2025, 187 : 8 - 13
  • [29] Learning a Domain-Invariant Embedding for Unsupervised Person Re-identification
    Pu, Nan
    Georgiou, T. K.
    Bakker, Erwin M.
    Lew, Michael S.
    2019 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2019,
  • [30] Unsupervised Salience Learning for Person Re-identification
    Zhao, Rui
    Ouyang, Wanli
    Wang, Xiaogang
    2013 IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2013, : 3586 - 3593