Feature Refinement and Filter Network for Person Re-Identification
Author(s): Ning, X (Ning, Xin); Gong, K (Gong, Ke); Li, WJ (Li, Weijun); Zhang, LP (Zhang, Liping); Bai, X (Bai, Xiao); Tian, SW (Tian, Shengwei)
Source: IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY Volume: 31 Issue: 9 Pages: 3391-3402 DOI: 10.1109/TCSVT.2020.3043026 Published: SEP 2021
Abstract: In the task of person re-identification, the attention mechanism and fine-grained information have been proved to be effective. However, it has been observed that models often focus on the extraction of features with strong discrimination, and neglect other valuable features. The extracted fine-grained information may include redundancies. In addition, current methods lack an effective scheme to remove background interference. Therefore, this paper proposes the feature refinement and filter network to solve the above problems from three aspects: first, by weakening the high response features, we aim to identify highly valuable features and extract the complete features of persons, thereby enhancing the robustness of the model; second, by positioning and intercepting the high response areas of persons, we eliminate the interference arising from background information and strengthen the response of the model to the complete features of persons; finally, valuable fine-grained features are selected using a multi-branch attention network for person re-identification to enhance the performance of the model. Our extensive experiments on the benchmark Market-1501, DukeMTMC-reID, CUHK03 and MSMT17 person re-identification datasets demonstrate that the performance of our method is comparable to that of state-of-the-art approaches.
Accession Number: WOS:000693647500009
Author Identifiers:
Author Web of Science ResearcherID ORCID Number
Ning, Xin M-9479-2018 0000-0001-7897-1673
ISSN: 1051-8215
eISSN: 1558-2205
Full Text: https://ieeexplore.ieee.org/document/9285312