Collaborative Contrastive Refining for Weakly Supervised Person Search.

Jia, C; Luo, M; Yan, C; Zhu, L; Chang, X; Zheng, Q

Collaborative Contrastive Refining for Weakly Supervised Person Search.

Jia, C Luo, M Yan, C Zhu, L Chang, X

Zheng, Q

Permalink

Publisher:: IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
Publication Type:: Journal Article
Citation:: IEEE Trans Image Process, 2023, 32, pp. 4951-4963
Issue Date:: 2023

Closed Access

	Filename	Description	Size
	Collaborative Contrastive Refining for Weakly Supervised Person Search_published.pdf	Published version	2.25 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	Jia, C
dc.contributor.author	Luo, M
dc.contributor.author	Yan, C
dc.contributor.author	Zhu, L
dc.contributor.author	Chang, X https://orcid.org/0000-0002-7778-8807
dc.contributor.author	Zheng, Q
dc.date.accessioned	2024-03-27T05:51:40Z
dc.date.available	2024-03-27T05:51:40Z
dc.date.issued	2023
dc.identifier.citation	IEEE Trans Image Process, 2023, 32, pp. 4951-4963
dc.identifier.issn	1057-7149
dc.identifier.issn	1941-0042
dc.identifier.uri	http://hdl.handle.net/10453/177276
dc.description.abstract	Weakly supervised person search involves training a model with only bounding box annotations, without human-annotated identities. Clustering algorithms are commonly used to assign pseudo-labels to facilitate this task. However, inaccurate pseudo-labels and imbalanced identity distributions can result in severe label and sample noise. In this work, we propose a novel Collaborative Contrastive Refining (CCR) weakly-supervised framework for person search that jointly refines pseudo-labels and the sample-learning process with different contrastive strategies. Specifically, we adopt a hybrid contrastive strategy that leverages both visual and context clues to refine pseudo-labels, and leverage the sample-mining and noise-contrastive strategy to reduce the negative impact of imbalanced distributions by distinguishing positive samples and noise samples. Our method brings two main advantages: 1) it facilitates better clustering results for refining pseudo-labels by exploring the hybrid similarity; 2) it is better at distinguishing query samples and noise samples for refining the sample-learning process. Extensive experiments demonstrate the superiority of our approach over the state-of-the-art weakly supervised methods by a large margin (more than 3% mAP on CUHK-SYSU). Moreover, by leveraging more diverse unlabeled data, our method achieves comparable or even better performance than the state-of-the-art supervised methods.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
dc.relation.ispartof	IEEE Trans Image Process
dc.relation.isbasedon	10.1109/TIP.2023.3308393
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0906 Electrical and Electronic Engineering, 1702 Cognitive Sciences
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.classification	4603 Computer vision and multimedia computation
dc.subject.classification	4607 Graphics, augmented reality and games
dc.title	Collaborative Contrastive Refining for Weakly Supervised Person Search.
dc.type	Journal Article
utslib.citation.volume	32
utslib.location.activity	United States
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0906 Electrical and Electronic Engineering
utslib.for	1702 Cognitive Sciences
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
utslib.copyright.status	closed_access	*
dc.date.updated	2024-03-27T05:51:35Z
pubs.publication-status	Published
pubs.volume	32

Abstract:

Weakly supervised person search involves training a model with only bounding box annotations, without human-annotated identities. Clustering algorithms are commonly used to assign pseudo-labels to facilitate this task. However, inaccurate pseudo-labels and imbalanced identity distributions can result in severe label and sample noise. In this work, we propose a novel Collaborative Contrastive Refining (CCR) weakly-supervised framework for person search that jointly refines pseudo-labels and the sample-learning process with different contrastive strategies. Specifically, we adopt a hybrid contrastive strategy that leverages both visual and context clues to refine pseudo-labels, and leverage the sample-mining and noise-contrastive strategy to reduce the negative impact of imbalanced distributions by distinguishing positive samples and noise samples. Our method brings two main advantages: 1) it facilitates better clustering results for refining pseudo-labels by exploring the hybrid similarity; 2) it is better at distinguishing query samples and noise samples for refining the sample-learning process. Extensive experiments demonstrate the superiority of our approach over the state-of-the-art weakly supervised methods by a large margin (more than 3% mAP on CUHK-SYSU). Moreover, by leveraging more diverse unlabeled data, our method achieves comparable or even better performance than the state-of-the-art supervised methods.

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

http://hdl.handle.net/10453/177276