Contextual Multi-Scale Feature Learning for Person Re-Identification

Baoyu Fan, Li Wang, Runze Zhang, Zhenhua Guo, Yaqian Zhao, Rengang Li, Weifeng Gong

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

18 Citations (Scopus)


Representing features at multiple scales is significant for person re-identification (Re-ID). Most existing methods learn the multi-scale features by stacking streams and convolutions without considering the cooperation of multiple scales at a granular level. However, most scales are more discriminative only when they integrate other scales as contextual information. We termed that contextual multi-scale. In this paper, we proposed a novel architecture, namely contextual multi-scale network (CMSNet), for learning common and contextual multi-scale representations simultaneously. The building block of CMSNet obtains contextual multi-scale representations by bidirectionally hierarchical connection groups: the forward hierarchical connection group for stepwise inter-scale information fusion and the backward hierarchical connection group for leap-frogging inter-scale information fusion. Too rich scale features without a selection will confuse the discrimination. Additionally, we introduced a new channel-wise scale selection module to dynamically select scale features for corresponding input image. To the best of our knowledge, CMSNet is the most lightweight model for person Re-ID and it achieves state-of-the-art performance on four commonly used Re-ID datasets, surpassing most large-scale models.

Original languageEnglish
Title of host publicationMM 2020 - Proceedings of the 28th ACM International Conference on Multimedia
PublisherAssociation for Computing Machinery, Inc
Number of pages9
ISBN (Electronic)9781450379885
Publication statusPublished - 12 Oct 2020
Externally publishedYes
Event28th ACM International Conference on Multimedia, MM 2020 - Virtual, Online, United States
Duration: 12 Oct 202016 Oct 2020

Publication series

NameMM 2020 - Proceedings of the 28th ACM International Conference on Multimedia


Conference28th ACM International Conference on Multimedia, MM 2020
Country/TerritoryUnited States
CityVirtual, Online


  • attention mechanism
  • contextual multi-scale
  • hierarchical connection
  • person re-identification


Dive into the research topics of 'Contextual Multi-Scale Feature Learning for Person Re-Identification'. Together they form a unique fingerprint.

Cite this