Please use this identifier to cite or link to this item:
Scopus Web of Science® Altmetric
Type: Journal article
Title: Learning deep part-aware embedding for person retrieval
Author: Zhao, Y.
Shen, C.
Yu, X.
Chen, H.
Gao, Y.
Xiong, S.
Citation: Pattern Recognition, 2021; 116:1-10
Publisher: Elsevier
Issue Date: 2021
ISSN: 0031-3203
Statement of
Yang Zhao,Chunhua Shen, Xiaohan Yu, Hao Chen, Yongsheng Gao, Shengwu Xiong
Abstract: Person retrieval is an important vision task, aiming at matching the images of the same person under various camera views. The key challenge of person retrieval lies in the large intra-class variations among the person images. Therefore, how to learn discriminative feature representations becomes the core problem. In this paper, we propose a deep part-aware representation learning method for person retrieval. First, an improved triplet loss is introduced such that the global feature representations from the same identity are closely clustered. Meanwhile, a localization branch is proposed to automatically localize those discriminative person-wise parts or regions, only using identity labels in a weakly supervised manner. Via the learning simultaneously guided by the global branch and the localization branch, the proposed method can further improve the performance for person retrieval. Through an extensive set of ablation studies, we verify that the localization branch and the improved triplet loss each contributes to the performance boosts of the proposed method. Our model obtains superior (or comparable) performance compared to state-of-the-art methods for person retrieval on the four public person retrieval datasets. On the CUHK03-labeled dataset, for instance, the performance increases from 73.0% mAP and 77.9% rank-1 accuracy to 80.8% (+7.8%) mAP and 83.9% (+6.0%) rank-1 accuracy.
Keywords: Person retrieval; part-aware embedding; improved triplet loss
Rights: © 2021 Elsevier Ltd. All rights reserved.
DOI: 10.1016/j.patcog.2021.107938
Grant ID:
Published version:
Appears in Collections:Aurora harvest 4
Computer Science publications

Files in This Item:
There are no files associated with this item.

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.