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
  • [31] Cooperative Refinement Learning for domain adaptive person Re-identification
    Peng, Jinjia
    Jiang, Guangqi
    Wang, Huibing
    KNOWLEDGE-BASED SYSTEMS, 2022, 242
  • [32] Unsupervised Region Attention Network for Person Re-Identification
    Zhang, Chenrui
    Wu, Yangxu
    Lei, Tao
    IEEE ACCESS, 2019, 7 : 165520 - 165530
  • [33] Learning to Purification for Unsupervised Person Re-Identification
    Lan, Long
    Teng, Xiao
    Zhang, Jing
    Zhang, Xiang
    Tao, Dacheng
    IEEE TRANSACTIONS ON IMAGE PROCESSING, 2023, 32 : 3338 - 3353
  • [34] DCN-Based unsupervised domain adaptive person re-identification method
    Yang Hai-lun
    Wang Jin-cong
    Ren Hong-e
    Tao Rui
    CHINESE JOURNAL OF LIQUID CRYSTALS AND DISPLAYS, 2021, 36 (11) : 1573 - 1582
  • [35] AdaDC: Adaptive Deep Clustering for Unsupervised Domain Adaptation in Person Re-Identification
    Li, Shihua
    Yuan, Mingkuan
    Chen, Jie
    Hu, Zhilan
    IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY, 2022, 32 (06) : 3825 - 3838
  • [36] Dual Pseudo Label Refinement for Unsupervised Domain Adaptive Person Re-Identification
    Dong, Wenhui
    Qu, Peishu
    Li, Bingwen
    IEEE ACCESS, 2023, 11 : 44402 - 44412
  • [37] Distance constraint between features for unsupervised domain adaptive person re-identification
    Li, Zhihao
    Han, Bing
    Gao, Xinbo
    Hou, Biao
    Liu, Zongyuan
    NEUROCOMPUTING, 2021, 462 : 113 - 122
  • [38] Unsupervised Multiple Granularities Attention-Attribute Learning for Person Re-identification
    Yang, Rui
    Wu, Song
    Xiao, Guoqiang
    2020 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS), 2020,
  • [39] Semantic driven attention network with attribute learning for unsupervised person re-identification
    Xu, Simin
    Luo, Lingkun
    Hu, Jilin
    Yang, Bin
    Hu, Shiqiang
    KNOWLEDGE-BASED SYSTEMS, 2022, 252
  • [40] Multi-level self attention for unsupervised learning person re-identification
    Zheng Y.
    Zhao J.
    Zhou Y.
    Liu F.
    Yao R.
    Zhu H.
    El Saddik A.
    Multimedia Tools and Applications, 83 (26) : 68855 - 68874