Standard
Person30K: A Dual-Meta Generalization Network for Person Re-Identification. / Bai, Yan; Jiao, Jile; Ce, Wang et al.
Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021. IEEE Computer Society Press, 2021. p. 2123-2132 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSN › Conference contribution/Paper › peer-review
Harvard
Bai, Y, Jiao, J, Ce, W
, Liu, J, Lou, Y, Feng, X & Duan, LY 2021,
Person30K: A Dual-Meta Generalization Network for Person Re-Identification. in
Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, IEEE Computer Society Press, pp. 2123-2132, 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, Online, United States,
19/06/21.
https://doi.org/10.1109/CVPR46437.2021.00216APA
Bai, Y., Jiao, J., Ce, W.
, Liu, J., Lou, Y., Feng, X., & Duan, L. Y. (2021).
Person30K: A Dual-Meta Generalization Network for Person Re-Identification. In
Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 (pp. 2123-2132). (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). IEEE Computer Society Press.
https://doi.org/10.1109/CVPR46437.2021.00216Vancouver
Bai Y, Jiao J, Ce W
, Liu J, Lou Y, Feng X et al.
Person30K: A Dual-Meta Generalization Network for Person Re-Identification. In Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021. IEEE Computer Society Press. 2021. p. 2123-2132. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). Epub 2021 Jun 20. doi: 10.1109/CVPR46437.2021.00216
Author
Bibtex
@inproceedings{7eca56f3dad14644952b1bf3c557bb9a,
title = "Person30K: A Dual-Meta Generalization Network for Person Re-Identification",
abstract = "Recently, person re-identification (ReID) has vastly benefited from the surging waves of data-driven methods. However, these methods are still not reliable enough for real-world deployments, due to the insufficient generalization capability of the models learned on existing benchmarks that have limitations in multiple aspects, including limited data scale, capture condition variations, and appearance diversities. To this end, we collect a new dataset named Person30K with the following distinct features: 1) a very large scale containing 1.38 million images of 30K identities, 2) a large capture system containing 6,497 cameras deployed at 89 different sites, 3) abundant sample diversities including varied backgrounds and diverse person poses. Furthermore, we propose a domain generalization ReID method, dual-meta generalization network (DMG-Net), to exploit the merits of meta-learning in both the training procedure and the metric space learning. Concretely, we design a “learning then generalization evaluation” meta-training procedure and a meta-discrimination loss to enhance model generalization and discrimination capabilities. Comprehensive experiments validate the effectiveness of our DMG-Net.",
author = "Yan Bai and Jile Jiao and Wang Ce and Jun Liu and Yihang Lou and Xuetao Feng and Duan, {Ling Yu}",
note = "Publisher Copyright: {\textcopyright} 2021 IEEE; 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021 ; Conference date: 19-06-2021 Through 25-06-2021",
year = "2021",
month = nov,
day = "2",
doi = "10.1109/CVPR46437.2021.00216",
language = "English",
isbn = "9781665445108",
series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE Computer Society Press",
pages = "2123--2132",
booktitle = "Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021",
}
RIS
TY - GEN
T1 - Person30K
T2 - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
AU - Bai, Yan
AU - Jiao, Jile
AU - Ce, Wang
AU - Liu, Jun
AU - Lou, Yihang
AU - Feng, Xuetao
AU - Duan, Ling Yu
N1 - Publisher Copyright:
© 2021 IEEE
PY - 2021/11/2
Y1 - 2021/11/2
N2 - Recently, person re-identification (ReID) has vastly benefited from the surging waves of data-driven methods. However, these methods are still not reliable enough for real-world deployments, due to the insufficient generalization capability of the models learned on existing benchmarks that have limitations in multiple aspects, including limited data scale, capture condition variations, and appearance diversities. To this end, we collect a new dataset named Person30K with the following distinct features: 1) a very large scale containing 1.38 million images of 30K identities, 2) a large capture system containing 6,497 cameras deployed at 89 different sites, 3) abundant sample diversities including varied backgrounds and diverse person poses. Furthermore, we propose a domain generalization ReID method, dual-meta generalization network (DMG-Net), to exploit the merits of meta-learning in both the training procedure and the metric space learning. Concretely, we design a “learning then generalization evaluation” meta-training procedure and a meta-discrimination loss to enhance model generalization and discrimination capabilities. Comprehensive experiments validate the effectiveness of our DMG-Net.
AB - Recently, person re-identification (ReID) has vastly benefited from the surging waves of data-driven methods. However, these methods are still not reliable enough for real-world deployments, due to the insufficient generalization capability of the models learned on existing benchmarks that have limitations in multiple aspects, including limited data scale, capture condition variations, and appearance diversities. To this end, we collect a new dataset named Person30K with the following distinct features: 1) a very large scale containing 1.38 million images of 30K identities, 2) a large capture system containing 6,497 cameras deployed at 89 different sites, 3) abundant sample diversities including varied backgrounds and diverse person poses. Furthermore, we propose a domain generalization ReID method, dual-meta generalization network (DMG-Net), to exploit the merits of meta-learning in both the training procedure and the metric space learning. Concretely, we design a “learning then generalization evaluation” meta-training procedure and a meta-discrimination loss to enhance model generalization and discrimination capabilities. Comprehensive experiments validate the effectiveness of our DMG-Net.
U2 - 10.1109/CVPR46437.2021.00216
DO - 10.1109/CVPR46437.2021.00216
M3 - Conference contribution/Paper
AN - SCOPUS:85116310489
SN - 9781665445108
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 2123
EP - 2132
BT - Proceedings - 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2021
PB - IEEE Computer Society Press
Y2 - 19 June 2021 through 25 June 2021
ER -
