Adversarial erasing attention for person re-identification in camera networks under complex environments

Liu, Shuang and Hao, Xiaolong and Zhang, Ronghua and Zhang, Zhong and Durrani, Tariq S. (2020) Adversarial erasing attention for person re-identification in camera networks under complex environments. IEEE Access, 8. pp. 56469-56479. ISSN 2169-3536 (https://doi.org/10.1109/ACCESS.2020.2982032)

[thumbnail of Liu-etal-IEEE-Access-2020-Adversarial-erasing-attention-for-person-re-identification-in-camera]
Preview
 Text. Filename: Liu_etal_IEEE_Access_2020_Adversarial_erasing_attention_for_person_re_identification_in_camera.pdf
Final Published Version
License: Creative Commons Attribution 4.0 logo
Download (1MB)| Preview

Abstract

Person re-identification (Re-ID) in camera networks under complex environments has achieved promising performance using deep feature representations. However, most approaches usually ignore to learn features from non-salient parts of pedestrian, which results in an incomplete pedestrian representation. In this paper, we propose a novel person Re-ID method named Adversarial Erasing Attention (AEA) to mine discriminative completed features using an adversarial way. Specifically, the proposed AEA consists of the basic network and the complementary network. On the one hand, original pedestrian images are used to train the basic network in order to extract global and local deep features. On the other hand, to learn features complementary to the basic network, we propose the adversarial erasing operation, that locates non-salient areas with the help of attention map, to generate erased pedestrian images. Then, we utilize them to train the complementary network and adopt the dynamic strategy to match the dynamic status of AEA in the learning process. Hence, the diversity of training samples is enriched and the complementary network could discover new clues when learning deep features. Finally, we combine the features learned from the basic and complementary networks to represent the pedestrian image. Experiments on three databases (Market1501, CUHK03 and DukeMTMC-reID) demonstrate the proposed AEA achieves great performances.

  • Item type:Article
    ID code:72320
    Dates:
    Date
    Event
    20 March 2020
    Published
    18 March 2020
    Accepted
    Notes:© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
    Subjects:Technology > Electrical engineering. Electronics Nuclear engineering
    Department:Faculty of Engineering > Electronic and Electrical Engineering
    Depositing user: Pure Administrator
    Date deposited:07 May 2020 13:59
    Last modified:09 Apr 2024 01:28
    Related URLs:
    URI:https://strathprints.strath.ac.uk/id/eprint/72320
CORE (COnnecting REpositories)