Part-Regularized Near-Duplicate Vehicle Re-Identification

Bing He, Jia Li, Yifan Zhao, Yonghong Tian; The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2019, pp. 3997-4005

Abstract


Vehicle re-identification (Re-ID) has been attracting more interests in computer vision owing to its great contributions in urban surveillance and intelligent transportation. With the development of deep learning approaches, vehicle Re-ID still faces a near-duplicate challenge, which is to distinguish different instances with nearly identical appearances. Previous methods simply rely on the global visual features to handle this problem. In this paper, we proposed a simple but efficient part-regularized discriminative feature preserving method which enhances the perceptive ability of subtle discrepancies. We further develop a novel framework to integrate part constrains with the global Re-ID modules by introducing an detection branch. Our framework is trained end-to-end with combined local and global constrains. Specially, without the part-regularized local constrains in inference step, our Re-ID network outperforms the state-of-the-art method by a large margin on large benchmark datasets VehicleID and VeRi-776.

Related Material


[pdf]
[bibtex]
@InProceedings{He_2019_CVPR,
author = {He, Bing and Li, Jia and Zhao, Yifan and Tian, Yonghong},
title = {Part-Regularized Near-Duplicate Vehicle Re-Identification},
booktitle = {The IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2019}
}