Compact network training for person ReID

Hussam Lawen, Avi Ben-Cohen, Matan Protter, Itamar Friedman, Lihi Zelnik-Manor

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The task of person re-identification (ReID) has attracted growing attention in recent years leading to improved performance, albeit with little focus on real-world applications. Most SotA methods are based on heavy pre-trained models, e.g. ResNet50 (∼25M parameters), which makes them less practical and more tedious to explore architecture modifications. In this study, we focus on a small-sized randomly initialized model that enables us to easily introduce architecture and training modifications suitable for person ReID. The outcomes of our study are a compact network and a fitting training regime. We show the robustness of the network by outperforming the SotA on both Market1501 and DukeMTMC. Furthermore, we show the representation power of our ReID network via SotA results on a different task of multi-object tracking.

Original languageEnglish
Title of host publicationICMR 2020 - Proceedings of the 2020 International Conference on Multimedia Retrieval
Pages164-171
Number of pages8
ISBN (Electronic)9781450370875
DOIs
StatePublished - 8 Jun 2020
Externally publishedYes
Event10th ACM International Conference on Multimedia Retrieval, ICMR 2020 - Dublin, Ireland
Duration: 8 Jun 202011 Jun 2020

Publication series

NameICMR 2020 - Proceedings of the 2020 International Conference on Multimedia Retrieval

Conference

Conference10th ACM International Conference on Multimedia Retrieval, ICMR 2020
Country/TerritoryIreland
CityDublin
Period8/06/2011/06/20

Keywords

  • Compact network
  • Deep person reid
  • Multi-object tracking

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications
  • Computer Science Applications
  • Computer Graphics and Computer-Aided Design

Fingerprint

Dive into the research topics of 'Compact network training for person ReID'. Together they form a unique fingerprint.

Cite this