VOC-RelD: Vehicle Re-Identification Based on Vehicle-Orientation-Camera
Abstract
Vehicle re-identification is a challenging task due to high intra-class variances and small inter-class variances. In this work, we focus on the failure cases caused by similar background and shape. They pose serve bias on similarity, making it easier to neglect fine-grained information. To reduce the bias, we propose an approach named VOC- ReID, taking the triplet vehicle-orientation-camera as a whole and reforming background/shape similarity as camera/orientation re-identification. At first, we train models for vehicle, orientation and camera reidentification respectively. Then we use orientation and camera similarity as penalty to get final similarity. Besides, we propose a high performance baseline boosted by bag of tricks and weakly supervised data augmentation. Our algorithm achieves the second place in vehicle reidentification at the NVIDIA AI City Challenge 2020.
Cite
Text
Zhu et al. "VOC-RelD: Vehicle Re-Identification Based on Vehicle-Orientation-Camera." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00309Markdown
[Zhu et al. "VOC-RelD: Vehicle Re-Identification Based on Vehicle-Orientation-Camera." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/zhu2020cvprw-vocreld/) doi:10.1109/CVPRW50498.2020.00309BibTeX
@inproceedings{zhu2020cvprw-vocreld,
title = {{VOC-RelD: Vehicle Re-Identification Based on Vehicle-Orientation-Camera}},
author = {Zhu, Xiangyu and Luo, Zhenbo and Fu, Pei and Ji, Xiang},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {2566-2573},
doi = {10.1109/CVPRW50498.2020.00309},
url = {https://mlanthology.org/cvprw/2020/zhu2020cvprw-vocreld/}
}