elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Deep Cosine Metric Learning for Person Re-Identification

Wojke, Nicolai and Bewley, Alex (2018) Deep Cosine Metric Learning for Person Re-Identification. In: Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017. IEEE. IEEE Winter Conference on Applications of Computer Vision (WACV), 12.-14. März 2018, Lake Tahoe, NV/CA.

[img] PDF
3MB

Abstract

Metric learning aims to construct an embedding where two extracted features corresponding to the same identity are likely to be closer than features from different identities. This paper presents a method for learning such a feature space where the cosine similarity is effectively optimized through a simple re-parametrization of the conventional softmax classification regime. At test time, the final classification layer can be stripped from the network to facilitate nearest neighbor queries on unseen individuals using the cosine similarity metric. This approach presents a simple alternative to direct metric learning objectives such as siamese networks that have required sophisticated pair or triplet sampling strategies in the past. The method is evaluated on two large-scale pedestrian re-identification datasets where competitive results are achieved overall. In particular, we achieve better generalization on the test set compared to a network trained with triplet loss.

Item URL in elib:https://elib.dlr.de/116408/
Document Type:Conference or Workshop Item (Speech)
Title:Deep Cosine Metric Learning for Person Re-Identification
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Wojke, NicolaiNicolai.Wojke (at) dlr.deUNSPECIFIED
Bewley, Alexbewley (at) robots.ox.ac.ukUNSPECIFIED
Date:2018
Journal or Publication Title:Proceedings - 2017 IEEE Winter Conference on Applications of Computer Vision, WACV 2017
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:Yes
In ISI Web of Science:No
Publisher:IEEE
Status:Accepted
Keywords:Person Re-Identification, Metric Learning, Convolutional Neural Networks
Event Title:IEEE Winter Conference on Applications of Computer Vision (WACV)
Event Location:Lake Tahoe, NV/CA
Event Type:international Conference
Event Dates:12.-14. März 2018
Organizer:IEEE
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Transport
HGF - Program Themes:Traffic Management (old)
DLR - Research area:Transport
DLR - Program:V VM - Verkehrsmanagement
DLR - Research theme (Project):V - I.MoVe (old)
Location: Berlin-Adlershof
Institutes and Institutions:Institute of Transportation Systems > Data Management and Knowledge Discovery
Deposited By: Wojke, Nicolai
Deposited On:19 Dec 2017 14:50
Last Modified:31 Jul 2019 20:13

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.