Unsupervised Domain Adaptation for Person Re-identification via Heterogeneous Graph Alignment

Authors

  • Minying Zhang Alibaba Group
  • Kai Liu Alibaba Group Beijing Jiaotong University
  • Yidong Li Beijing Jiaotong Univeristy
  • Shihui Guo Xiamen University
  • Hongtao Duan Alibaba Group
  • Yimin Long Alibaba Group
  • Yi Jin Beijing JiaoTong University

Keywords:

Biometrics, Face, Gesture & Pose

Abstract

Unsupervised person re-identification (re-ID) is becoming increasingly popular due to its power in real-world systems such as public security and intelligent transportation systems. However, the person re-ID task is challenged by the problems of data distribution discrepancy across cameras and lack of label information. In this paper, we propose a coarse-to-fine heterogeneous graph alignment (HGA) method to find cross-camera person matches by characterizing the unlabeled data as a heterogeneous graph for each camera. In the coarse-alignment stage, we assign a projection for each camera and utilize an adversarial learning based method to align coarse-grained node groups from different cameras into a shared space, which consequently alleviates the distribution discrepancy between cameras. In the fine-alignment stage, we exploit potential fine-grained node groups in the shared space and introduce conservative alignment loss functions to constrain the graph aligning process, resulting in reliable pseudo labels as learning guidance. The proposed domain adaptation framework not only improves model generalization on target domain, but also facilitates mining and integrating the potential discriminative information across different cameras. Extensive experiments on benchmark datasets demonstrate that the proposed approach outperforms the state-of-the-arts.

Downloads

Published

2021-05-18

How to Cite

Zhang, M., Liu, K., Li, Y., Guo, S., Duan, H., Long, Y., & Jin, Y. (2021). Unsupervised Domain Adaptation for Person Re-identification via Heterogeneous Graph Alignment. Proceedings of the AAAI Conference on Artificial Intelligence, 35(4), 3360-3368. Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/16448

Issue

Section

AAAI Technical Track on Computer Vision III