Going Beyond Real Data: A Robust Visual Representation for Vehicle Re-identification

Zheng, Z; Jiang, M; Wang, Z; Wang, J; Bai, Z; Zhang, X; Yu, X; Tan, X; Yang, Y; Wen, S; Ding, E

Going Beyond Real Data: A Robust Visual Representation for Vehicle Re-identification

Zheng, Z

Jiang, M Wang, Z Wang, J Bai, Z Zhang, X Yu, X Tan, X Yang, Y

Wen, S Ding, E

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020, 2020-June, pp. 2550-2558
Issue Date:: 2020-07-28

Closed Access

	Filename	Description	Size
	09150579.pdf	Published version	2.74 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Zheng, Z https://orcid.org/0000-0002-2434-9050
dc.contributor.author	Jiang, M
dc.contributor.author	Wang, Z
dc.contributor.author	Wang, J
dc.contributor.author	Bai, Z
dc.contributor.author	Zhang, X
dc.contributor.author	Yu, X
dc.contributor.author	Tan, X
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.contributor.author	Wen, S
dc.contributor.author	Ding, E
dc.date	2020-06-14
dc.date.accessioned	2021-04-15T09:51:30Z
dc.date.available	2021-04-15T09:51:30Z
dc.date.issued	2020-07-28
dc.identifier.citation	2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 2020, 2020-June, pp. 2550-2558
dc.identifier.isbn	978-1-7281-9361-8
dc.identifier.issn	2160-7508
dc.identifier.issn	2160-7516
dc.identifier.uri	http://hdl.handle.net/10453/148139
dc.description.abstract	In this report, we present the Baidu-UTS submission to the AICity Challenge in CVPR 2020. This is the winning solution to the vehicle re-identification (re-id) track. We focus on developing a robust vehicle re-id system for real-world scenarios. In particular, we aim to fully leverage the merits of the synthetic data while arming with real images to learn a robust representation for vehicles in different views and illumination conditions. By comprehensively investigating and evaluating various data augmentation approaches and popular strong baselines, we analyze the bottleneck restricting the vehicle re-id performance. Based on our analysis, we therefore design a vehicle re-id method with better data augmentation, training and post-processing strategies. Our proposed method has achieved the 1st place out of 41 teams, yielding 84.13% mAP on the private test set. We hope that our practice could shed light on using synthetic and real data effectively in training deep re-id networks and pave the way for real-world vehicle re-id systems.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
dc.relation.ispartof	2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops
dc.relation.isbasedon	10.1109/cvprw50498.2020.00307
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Going Beyond Real Data: A Robust Visual Representation for Vehicle Re-identification
dc.type	Conference Proceeding
utslib.citation.volume	2020-June
utslib.location.activity	Seattle, WA, USA
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Strength - AAII - Australian Artificial Intelligence Institute
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2021-04-15T09:51:28Z
pubs.finish-date	2020-06-19
pubs.publication-status	Published
pubs.start-date	2020-06-14
pubs.volume	2020-June

Abstract:

In this report, we present the Baidu-UTS submission to the AICity Challenge in CVPR 2020. This is the winning solution to the vehicle re-identification (re-id) track. We focus on developing a robust vehicle re-id system for real-world scenarios. In particular, we aim to fully leverage the merits of the synthetic data while arming with real images to learn a robust representation for vehicles in different views and illumination conditions. By comprehensively investigating and evaluating various data augmentation approaches and popular strong baselines, we analyze the bottleneck restricting the vehicle re-id performance. Based on our analysis, we therefore design a vehicle re-id method with better data augmentation, training and post-processing strategies. Our proposed method has achieved the 1st place out of 41 teams, yielding 84.13% mAP on the private test set. We hope that our practice could shed light on using synthetic and real data effectively in training deep re-id networks and pave the way for real-world vehicle re-id systems.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/148139