Multi-attribute adaptive aggregation transformer for vehicle re-identification
作者:
Highlights:
• A vehicle attribute transformer for vehicle re-identification is proposed, which can aggregate the attributes of vehicle model, color and viewpoint adaptively.
• A multi-sample dispersion triplet loss is designed to optimize the proposed transformer network, which can consider richer positive and negative sample information.
• Extensive experiments on popular vehicle re-identification datasets verify that the proposed method can achieve state-of-the-art performance.
摘要
•A vehicle attribute transformer for vehicle re-identification is proposed, which can aggregate the attributes of vehicle model, color and viewpoint adaptively.•A multi-sample dispersion triplet loss is designed to optimize the proposed transformer network, which can consider richer positive and negative sample information.•Extensive experiments on popular vehicle re-identification datasets verify that the proposed method can achieve state-of-the-art performance.
论文关键词:Vehicle re-identification,Transformer,Multi-attribute adaptive aggregation,Multi-sample dispersion
论文评审过程:Received 20 September 2021, Revised 31 December 2021, Accepted 3 January 2022, Available online 10 January 2022, Version of Record 10 January 2022.
论文官网地址:https://doi.org/10.1016/j.ipm.2022.102868