Existing vehicle re-identification (Re-ID) methods usually suffer from intra-instance discrepancy and inter-instance similarity. The key to solving this problem lies in filtering out identity-irrelevant interference and collecting identity-relevant vehicle details. In this paper, we aim to design a robust vehicle Re-ID framework that trains a model guided by knowledge vectors yet is able to disentangle the identity-relevant features and identity-irrelevant features. Toward this end, we propose a novel Multi-scale Knowledge-Aware Transformer (MsKAT) to build a knowledge-guided multi-scale feature alignment framework. First, we construct a Knowledge-Aware Transformer (KAT) to interact with semantic knowledge and visual feature. KAT mainly includes State elimination Transformer (SeT) to eliminate state (camera, viewpoint) interference and Attribute aggregation Transformer (AaT) to gather attribute (color, type) information. Second, to learn the knowledge-guided sample differences, we propose to encourage the separation of identity-relevant features and identity-irrelevant features by a Knowledge-Guided Alignment loss ( $\mathcal {L}_{KGA}$ ). Specifically, $\mathcal {L}_{KGA}$ suppresses the difference between knowledge-guided positive pairs and the similarity between knowledge-guided negative pairs. Third, with the multi-scale settings of KAT and $\mathcal {L}_{KGA}$ , our model can capture knowledge-guided visual consistency features at different scales. Extensive evidence demonstrates our approach achieves new state-of-the-art on three widely-used vehicle re-identification benchmarks.


    Access

    Check access

    Check availability in my library

    Order at Subito €


    Export, share and cite



    Title :

    MsKAT: Multi-Scale Knowledge-Aware Transformer for Vehicle Re-Identification


    Contributors:
    Li, Hongchao (author) / Li, Chenglong (author) / Zheng, Aihua (author) / Tang, Jin (author) / Luo, Bin (author)

    Published in:

    Publication date :

    2022-10-01


    Size :

    3648183 byte




    Type of media :

    Article (Journal)


    Type of material :

    Electronic Resource


    Language :

    English



    MART: Mask-Aware Reasoning Transformer for Vehicle Re-Identification

    Lu, Zefeng / Lin, Ronghao / Hu, Haifeng | IEEE | 2023


    Knowledge-aware Graph Transformer for Pedestrian Trajectory Prediction

    Liu, Yu / Zhang, Yuexin / Li, Kunming et al. | IEEE | 2023


    Efficient Context-Aware Graph Transformer for Vehicle Motion Prediction

    Gomez-Huelamo, Carlos / Conde, Marcos V. / Gutierrez-Moreno, Rodrigo et al. | IEEE | 2023



    TVG-ReID: Transformer-Based Vehicle-Graph Re-Identification

    Li, Zhiwei / Zhang, Xinyu / Tian, Chi et al. | IEEE | 2023