Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification

Shan Lin, Haoliang Li, Chang Tsun Li, Alex Chichung Kot

    Research output: Book chapter/Published conference paperConference paperpeer-review


    Most existing person re-identification (Re-ID) approaches follow a supervised learning framework, in which a large number of labelled matching pairs are required for training. Such a setting severely limits their scalability in real-world applications where no labelled samples are available during the training phase. To overcome this limitation, we develop a novel unsupervised Multi-task Mid-level Feature Alignment (MMFA) network for the unsupervised cross-dataset person re-identification task. Under the assumption that the source and target datasets share the same set of mid-level semantic attributes, our proposed model can be jointly optimised under the person's identity classification and the attribute learning task with a cross-dataset mid-level feature alignment regularisation term. In this way, the learned feature representation can be better generalised from one dataset to another which further improve the person re-identification accuracy. Experimental results on four benchmark datasets demonstrate that our proposed method outperforms the state-of-the-art baselines.

    Original languageEnglish
    Title of host publication29th British machine vision conference, BMVC 2018 proceedings
    Subtitle of host publication3rd-6th September 2018, Northumbria University
    Number of pages13
    Publication statusPublished - Jul 2018
    Event29th British Machine Vision Conference, BMVC 2018 - Northumbria University, Newcastle, United Kingdom
    Duration: 03 Sep 201806 Sep 2018 (booklet)
    file:///D:/Users/bmt175/AppData/Local/Temp/Temp1_BMVC2018%20(1).zip/index.html (program)


    Conference29th British Machine Vision Conference, BMVC 2018
    Country/TerritoryUnited Kingdom
    Internet address


    Dive into the research topics of 'Multi-task mid-level feature alignment network for unsupervised cross-dataset person re-identification'. Together they form a unique fingerprint.

    Cite this