Further Non-Local and Channel Attention Networks for Vehicle Re-Identification
Abstract
Vehicle re-identification remains challenging due to large intra-class difference and small inter-class variance. To address this problem, in AICity Vehicle Re-ID task 2020, we propose a two-branch adaptive attention network—Further Non-local and Channel attention (FNC) to improve feature representation and discrimination. Specifically, inspired by two-stream theory of visual cortex, based on Non-local and channel relation, a two-branch FNC network is constructed to capture multiple useful information. Second, an effective attention fusion method is proposed to sufficiently model the effects from spatial and channel attention. The experimental results show that our algorithm achieves 66.25%/Rank-1 and 53.54%/mAP in 2020 AIC-ity Challenge Vehicle Re-ID task without using extra data, annotation and other auxiliary information, which demonstrate the effectiveness of the proposed FNC network.
Cite
Text
Liu et al. "Further Non-Local and Channel Attention Networks for Vehicle Re-Identification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020. doi:10.1109/CVPRW50498.2020.00300Markdown
[Liu et al. "Further Non-Local and Channel Attention Networks for Vehicle Re-Identification." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2020.](https://mlanthology.org/cvprw/2020/liu2020cvprw-further/) doi:10.1109/CVPRW50498.2020.00300BibTeX
@inproceedings{liu2020cvprw-further,
title = {{Further Non-Local and Channel Attention Networks for Vehicle Re-Identification}},
author = {Liu, Kai and Xu, Zheng and Hou, Zhaohui and Zhao, Zhicheng and Su, Fei},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
year = {2020},
pages = {2494-2500},
doi = {10.1109/CVPRW50498.2020.00300},
url = {https://mlanthology.org/cvprw/2020/liu2020cvprw-further/}
}