Omni-Scale Feature Learning for Person Re-Identification

Kaiyang Zhou, Yongxin Yang, Andrea Cavallaro, Tao Xiang

Research output: Chapter in book/report/conference proceedingConference proceedingpeer-review

697 Citations (Scopus)

Abstract

As an instance-level recognition problem, person re-identification (ReID) relies on discriminative features, which not only capture different spatial scales but also encapsulate an arbitrary combination of multiple scales. We callse features of both homogeneous and heterogeneous scales omni-scale features. In this paper, a novel deep ReID CNN is designed, termed Omni-Scale Network (OSNet), for omni-scale feature learning. This is achieved by designing a residual block composed of multiple convolutional feature streams, each detecting features at a certain scale. Importantly, a novel unified aggregation gate is introduced to dynamically fuse multi-scale features with input-dependent channel-wise weights. To efficiently learn spatial-channel correlations and avoid overfitting, the building block uses both pointwise and depthwise convolutions. By stacking such blocks layer-by-layer, our OSNet is extremely lightweight and can be trained from scratch on existing ReID benchmarks. Despite its small model size, our OSNet achieves state-of-the-art performance on six person-ReID datasets. Code and models are available at: Https://github.com/KaiyangZhou/deep-person-reid.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF International Conference on Computer Vision, ICCV 2019
PublisherIEEE
Pages3701-3711
Number of pages11
ISBN (Electronic)9781728148038
ISBN (Print)9781728148045
DOIs
Publication statusPublished - Oct 2019
Externally publishedYes
Event17th IEEE/CVF International Conference on Computer Vision, ICCV 2019 - Seoul, Korea, Republic of
Duration: 27 Oct 20192 Nov 2019
https://ieeexplore.ieee.org/xpl/conhome/8972782/proceeding

Publication series

NameProceedings of the IEEE International Conference on Computer Vision
Volume2019-October
ISSN (Print)1550-5499
ISSN (Electronic)2380-7504

Conference

Conference17th IEEE/CVF International Conference on Computer Vision, ICCV 2019
Country/TerritoryKorea, Republic of
CitySeoul
Period27/10/192/11/19
Internet address

Scopus Subject Areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

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

Cite this