Unsupervised person re-identification (Re-ID) aims to learn discriminative representations for person retrieval from unlabeled data. Recent research accomplishes this task with pseudo-labels and a center-level memory, but the pseudo-labels are inherently noisy and the update status of central features in memory is inconsistent, thus reducing the accuracy of Re-ID. In this paper, we propose a novel Spatial and Temporal Dual-Attention (STDA) framework to solve the above two problems. Firstly, to overcome the noisy label problem, we design an Intra-class Neighbor-based Spatial Attention (INSA) module to refine pseudo-labels by mining the spatial-level connections of positive instances. Specifically, we design a neighbor agreement as the similarity between central features and positive instance features in feature space to exploit the reliable complementary relationship. Based on the neighbor agreement, we aggregate the predictions of positive instances, thus jointly mitigating the noise in single instance feature clustering. Secondly, the central features in memory cannot be updated simultaneously, which leads to an inter-class update inconsistency problem. We introduce an Inter-class Sequence-based Temporal Attention (ISTA) module to alleviate this problem by computing a memory update factor based on the temporal-level update sequence of centrals. The weights are larger for newer updated centrals than for older updated centrals and non-updated centrals to mitigate the inter-class inconsistent update status. Finally, we combine the INSA and ISTA modules with contrastive learning for training. Extensive experimental results on Market-1501, MSMT17, and VeRi-776 show the effectiveness of the proposed method over the state-of-the-art performance. The code is available at: https://github.com/heqlin5/STDA.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Spatial and Temporal Dual-Attention for Unsupervised Person Re-Identification


    Contributors:
    He, Qiaolin (author) / Wang, Zihan (author) / Zheng, Zhijie (author) / Hu, Haifeng (author)


    Publication date :

    2024-02-01


    Size :

    1935343 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Cluster Contrast for Unsupervised Person Re-identification

    Dai, Zuozhuo / Wang, Guangyuan / Yuan, Weihao et al. | British Library Conference Proceedings | 2023


    Part-Aware Attention Network for Person Re-identification

    Xiang, Wangmeng / Huang, Jianqiang / Hua, Xian-Sheng et al. | British Library Conference Proceedings | 2021


    Co-attention Aligned Mutual Cross-Attention for Cloth-Changing Person Re-identification

    Wang, Qizao / Qian, Xuelin / Fu, Yanwei et al. | British Library Conference Proceedings | 2023


    Unsupervised Vehicle Re-Identification by Spatio-Temporal Contrastive Learning

    Guo, Xingping / Yang, Jing / Fang, Jianwu | IEEE | 2023


    Unsupervised Learning of Human Action Categories Using Spatial-Temporal Words

    Niebles, J. C. / Wang, H. / Fei-Fei, L. | British Library Online Contents | 2008