Tasks Integrated Networks: Joint Detection and Retrieval for Image Search.

Zhang, L; He, Z; Yang, Y; Wang, L; Gao, X-B

Tasks Integrated Networks: Joint Detection and Retrieval for Image Search.

Zhang, L He, Z Yang, Y

Wang, L Gao, X-B

Permalink

Publisher:: IEEE COMPUTER SOC
Publication Type:: Journal Article
Citation:: IEEE transactions on pattern analysis and machine intelligence, 2022, PP, (1), pp. 456-473
Issue Date:: 2022-01-01

Closed Access

	Filename	Description	Size
	Tasks_Integrated_Networks_Joint_Detection_and_Retrieval_for_Image_Search.pdf	Published version	2.48 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	Zhang, L
dc.contributor.author	He, Z
dc.contributor.author	Yang, Y https://orcid.org/0000-0002-0512-880X
dc.contributor.author	Wang, L
dc.contributor.author	Gao, X-B
dc.date.accessioned	2023-03-17T04:40:43Z
dc.date.available	2023-03-17T04:40:43Z
dc.date.issued	2022-01-01
dc.identifier.citation	IEEE transactions on pattern analysis and machine intelligence, 2022, PP, (1), pp. 456-473
dc.identifier.issn	0162-8828
dc.identifier.issn	1939-3539
dc.identifier.uri	http://hdl.handle.net/10453/167469
dc.description.abstract	The traditional object (person) retrieval (re-identification) task aims to learn a discriminative feature representation or metric on the cropped objects. However, in many real-world scenarios, the objects are seldom accurately annotated. Therefore, object-level retrieval becomes intractable without annotation, which leads to a new but challenging topic, i.e. image search with joint detection and retrieval. To address the image search issue, we introduce an end-to-end Integrated Net, which has four merits: 1) A Siamese architecture and an on-line pairing strategy for similar and dissimilar objects in the given images are designed. 2) A novel on-line pairing (OLP) loss is introduced with a dynamic feature dictionary, which alleviates the multi-task training stagnation problem, by automatically generating a number of negative pairs to restrict the positives. 3) Two modules are tailored to handle different tasks separately in the integrated framework, such that the task specification is guaranteed. 4) A class-center guided HEP loss (C2HEP) by exploiting the stored class centers is proposed, such that the intra-similarity and inter-dissimilarity can be captured. Extensive experiments on the CUHK-SYSU and PRW datasets for person search and the large-scale WebTattoo dataset for tattoo search, demonstrate that the proposed model outperforms the state-of-the-art image search models.
dc.format	Print-Electronic
dc.language	eng
dc.publisher	IEEE COMPUTER SOC
dc.relation.ispartof	IEEE transactions on pattern analysis and machine intelligence
dc.relation.isbasedon	10.1109/tpami.2020.3009758
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject	0801 Artificial Intelligence and Image Processing, 0806 Information Systems, 0906 Electrical and Electronic Engineering
dc.subject.classification	Artificial Intelligence & Image Processing
dc.subject.mesh	Algorithms
dc.subject.mesh	Humans
dc.subject.mesh	Humans
dc.subject.mesh	Algorithms
dc.subject.mesh	Algorithms
dc.subject.mesh	Humans
dc.title	Tasks Integrated Networks: Joint Detection and Retrieval for Image Search.
dc.type	Journal Article
utslib.citation.volume	PP
utslib.location.activity	United States
utslib.for	0801 Artificial Intelligence and Image Processing
utslib.for	0806 Information Systems
utslib.for	0906 Electrical and Electronic Engineering
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
utslib.copyright.status	closed_access	*
pubs.consider-herdc	false
dc.date.updated	2023-03-17T04:40:18Z
pubs.issue	1
pubs.publication-status	Published
pubs.volume	PP
utslib.citation.issue	1

Abstract:

The traditional object (person) retrieval (re-identification) task aims to learn a discriminative feature representation or metric on the cropped objects. However, in many real-world scenarios, the objects are seldom accurately annotated. Therefore, object-level retrieval becomes intractable without annotation, which leads to a new but challenging topic, i.e. image search with joint detection and retrieval. To address the image search issue, we introduce an end-to-end Integrated Net, which has four merits: 1) A Siamese architecture and an on-line pairing strategy for similar and dissimilar objects in the given images are designed. 2) A novel on-line pairing (OLP) loss is introduced with a dynamic feature dictionary, which alleviates the multi-task training stagnation problem, by automatically generating a number of negative pairs to restrict the positives. 3) Two modules are tailored to handle different tasks separately in the integrated framework, such that the task specification is guaranteed. 4) A class-center guided HEP loss (C2HEP) by exploiting the stored class centers is proposed, such that the intra-similarity and inter-dissimilarity can be captured. Extensive experiments on the CUHK-SYSU and PRW datasets for person search and the large-scale WebTattoo dataset for tattoo search, demonstrate that the proposed model outperforms the state-of-the-art image search models.

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

http://hdl.handle.net/10453/167469