Learning Hybrid Relationships for Person Re-identification

Authors

  • Shuang Liu Tianjin Normal University
  • Wenmin Huang Tianjin Normal University
  • Zhong Zhang Tianjin Normal University

Keywords:

Image and Video Retrieval

Abstract

Recently, the relationship among individual pedestrian images and the relationship among pairwise pedestrian images have become attractive for person re-identification (re-ID) as they effectively improve the ability of feature representation. In this paper, we propose a novel method named Hybrid Relationship Network (HRNet) to learn the two types of relationships in a unified framework that makes use of their own advantages. Specifically, for the relationship among individual pedestrian images, we take the features of pedestrian images as the nodes to construct a locally-connected graph, so as to improve the discriminative ability of nodes. Meanwhile, we propose the consistent node constraint to inject the identity information into the graph learning process and guide the information to propagate accurately. As for the relationship among pairwise pedestrian images, we treat the feature differences of pedestrian images as the nodes to construct a fully-connected graph so as to estimate robust similarity of nodes. Furthermore, we propose the inter-graph propagation to alleviate the information loss for the fully-connected graph. Extensive experiments on Market-1501, DukeMTMCreID, CUHK03 and MSMT17 demonstrate that the proposed HRNet outperforms the state-of-the-art methods.

Downloads

Published

2021-05-18

How to Cite

Liu, S., Huang, W., & Zhang, Z. (2021). Learning Hybrid Relationships for Person Re-identification. Proceedings of the AAAI Conference on Artificial Intelligence, 35(3), 2172-2179. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16315

Issue

Section

AAAI Technical Track on Computer Vision II