Vehicle Re-Identification With Viewpoint-Aware Metric Learning

Ruihang Chu, Yifan Sun, Yadong Li, Zheng Liu, Chi Zhang, Yichen Wei; The IEEE International Conference on Computer Vision (ICCV), 2019, pp. 8282-8291

Abstract


This paper considers vehicle re-identification (re-ID) problem. The extreme viewpoint variation (up to 180 degrees) poses great challenges for existing approaches. Inspired by the behavior in human's recognition process, we propose a novel viewpoint-aware metric learning approach. It learns two metrics for similar viewpoints and different viewpoints in two feature spaces, respectively, giving rise to viewpoint-aware network (VANet). During training, two types of constraints are applied jointly. During inference, viewpoint is firstly estimated and the corresponding metric is used. Experimental results confirm that VANet significantly improves re-ID accuracy, especially when the pair is observed from different viewpoints. Our method establishes the new state-of-the-art on two benchmarks.

Related Material


[pdf]
[bibtex]
@InProceedings{Chu_2019_ICCV,
author = {Chu, Ruihang and Sun, Yifan and Li, Yadong and Liu, Zheng and Zhang, Chi and Wei, Yichen},
title = {Vehicle Re-Identification With Viewpoint-Aware Metric Learning},
booktitle = {The IEEE International Conference on Computer Vision (ICCV)},
month = {October},
year = {2019}
}