Vehicle instance retrieval (IR) often requires one to recognize the fine-grained visual differences between vehicles. Besides the holistic appearance of vehicles which is easily affected by the viewpoint variation and distortion, vehicle parts also provide crucial cues to differentiate near-identical vehicles. Motivated by these observations, we introduce a Part-Guided Attention Network (PGAN) to pinpoint the prominent part regions and effectively combine the global and local information for discriminative feature learning. PGAN first detects the locations of different part components and salient regions regardless of the vehicle identity, which serves as the bottom-up attention to narrow down the possible searching regions. To estimate the importance of detected parts, we propose a Part Attention Module (PAM) to adaptively locate the most discriminative regions with high-attention weights and suppress the distraction of irrelevant parts with relatively low weights. The PAM is guided by the identification loss and therefore provides top-down attention that enables attention to be calculated at the level of car parts and other salient regions. Finally, we aggregate the global appearance and local features together to improve the feature performance further. The PGAN combines part-guided bottom-up and top-down attention, global and local visual features in an end-to-end framework. Extensive experiments demonstrate that the proposed method achieves new state-of-the-art vehicle IR performance on four large-scale benchmark datasets.1


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    Part-Guided Attention Learning for Vehicle Instance Retrieval


    Contributors:
    Zhang, Xinyu (author) / Zhang, Rufeng (author) / Cao, Jiewei (author) / Gong, Dong (author) / You, Mingyu (author) / Shen, Chunhua (author)


    Publication date :

    2022-04-01


    Size :

    2802703 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    Orientation-Aware Vehicle Re-Identification with Semantics-Guided Part Attention Network

    Chen, Tsai-Shien / Liu, Chih-Ting / Wu, Chih-Wei et al. | British Library Conference Proceedings | 2020


    Localized Content-Based Image Retrieval Using Semi-Supervised Multiple Instance Learning

    Zhang, Dan / Shi, Zhenwei / Song, Yangqiu et al. | Springer Verlag | 2007



    Nighttime Motion Vehicle Detection Based on Multiple Instance Learning

    Zhu, Shao Ping | Trans Tech Publications | 2014


    Attention Guided Unsupervised learning of Monocular Visual-inertial Odometry

    Wang, Zhenke / Zhu, Yuan / Lu, Ke et al. | IEEE | 2022