Person re-identification (re-ID) has many applications in intelligent transportation systems. Clustering-based methods, which alternate between the generation of pseudo labels via clustering and the optimization of the feature extractor, have obtained leading performance in unsupervised person re-ID. But there are still two issues not well addressed: 1) Most methods measure the feature similarity without considering the domain shift between cameras, degrading the clustering performance. 2) Outliers, which usually correspond to hard samples with large discrepancy from other images of the identical person, are in most cases directly excluded from the network training. To tackle the above issues, this paper proposes a plug-and-play pseudo label rectification framework, which jointly utilizes CAmera Shift adapTation module and Outlier progressive Recycling strategy ( $CASTOR$ ) to improve the quality of pseudo labels from both pre-clustering and post-clustering. Specifically, we first compute the camera similarity of two samples by utilizing a pretrained camera classification network and subtract the feature similarity by the camera similarity, the value of which is weighted in an exponential decay manner throughout the network training, in order to adaptively remedy the adverse impact of inter-camera distribution shift upon clustering. Besides, we carefully design an outlier progressive recycling strategy to reassign part of the outliers into the clustered groups to make full use of the useful information of outliers. Extensive experiments on three large scale unsupervised and unsupervised domain adaptive (UDA) person re-ID benchmarks validate the effectiveness of $CASTOR$ and its wide compatibility with the state-of-the-art clustering-based methods.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Pseudo Label Rectification With Joint Camera Shift Adaptation and Outlier Progressive Recycling for Unsupervised Person Re-Identification


    Contributors:
    Xu, Mingyuan (author) / Guo, Haiyun (author) / Jia, Yuheng (author) / Dai, Zhitao (author) / Wang, Jinqiao (author)


    Publication date :

    2023-03-01


    Size :

    2821149 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Mask-Aware Pseudo Label Denoising for Unsupervised Vehicle Re-Identification

    Lu, Zefeng / Lin, Ronghao / He, Qiaolin et al. | IEEE | 2023


    SELF-RECTIFICATION OF STEREO CAMERA

    BOUGNOUX SYLVAIN | European Patent Office | 2018

    Free access

    Viewpoint-Aware Progressive Clustering for Unsupervised Vehicle Re-Identification

    Zheng, Aihua / Sun, Xia / Li, Chenglong et al. | IEEE | 2022


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

    He, Qiaolin / Wang, Zihan / Zheng, Zhijie et al. | IEEE | 2024


    STEREO CAMERA DEVICE AND RECTIFICATION METHOD THEREFOR

    NAM DONG MIN | European Patent Office | 2016

    Free access