Prototype-Guided Saliency Feature Learning for Person Search

Title
Prototype-Guided Saliency Feature Learning for Person Search
Authors
김익재Hanjae KimSunghun JoungKwanghoon Sohn
Keywords
재식별; 사람 추적; Saliency
Issue Date
2021-06
Publisher
CVPR, IEEE conf. on Computer Vision and Pattern Recognition
Abstract
Existing person search methods integrate person detection and re-identification (re-ID) module into a unified system. Though promising results have been achieved, the misalignment problem, which commonly occurs in person search, limits the discriminative feature representation for re-ID. To overcome this limitation, we introduce a novel framework to learn the discriminative representation by utilizing prototype in OIM loss. Unlike conventional methods using prototype as a representation of person identity, we utilize it as guidance to allow the attention network to consistently highlight multiple instances across different poses. Moreover, we propose a new prototype update scheme with adaptive momentum to increase the discriminative ability across different instances. Extensive ablation experiments demonstrate that our method can significantly enhance the feature discriminative power, outperforming the state-ofthe-art results on two person search benchmarks including CUHK-SYSU and PRW.
URI
http://pubs.kist.re.kr/handle/201004/73527
ISSN
-
Appears in Collections:
KIST Publication > Conference Paper
Files in This Item:
There are no files associated with this item.
Export
RIS (EndNote)
XLS (Excel)
XML


qrcode

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

BROWSE