Generative Enhancement-based Similarity Prediction Hashing for Image Retrieval

Hashing is frequently used in approximate nearest neighbor search due to its storage and search efficiency. On account of the bottleneck of traditional learning to hash methods, deep-based learning to hash has gained quite a popularity among researchers recently. While such methods show a promising...

Full description

Saved in:
Bibliographic Details
Published in:Proceedings - International Conference on Parallel and Distributed Systems pp. 1437 - 1444
Main Authors: Cao, Yuan, Meng, Fanlei, Wu, Xiangyu, Wang, Zijie
Format: Conference Proceeding
Language:English
Published: IEEE 17.12.2023
Subjects:
Benchmark testing
Binary codes
generative model
hashing
Image retrieval
Scalability
Semantics
Training
Training data
unsupervised learning
ISSN:2690-5965
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Abstract Hashing is frequently used in approximate nearest neighbor search due to its storage and search efficiency. On account of the bottleneck of traditional learning to hash methods, deep-based learning to hash has gained quite a popularity among researchers recently. While such methods show a promising performance gain by utilizing deep neural networks into its end-to-end training process to generate compact binary codes, the intrinsic connections between components make it unfeasible to optimize the architecture significantly. Subject to noise interference and absence of similarity labels of training data, normal unsupervised deep models even carry a noticeable deviation at representation learning stage. By integrating Generative Adversarial Network, this paper presents a novel architecture for generating compact hash codes from an extended set derived from original images while using the benefit of similarity prediction. Extensive experiments conducted on three benchmarks, NUS-WIDE, CIFAR-10, and MS-COCO illustrate that our method outperforms state-of-the-art image retrieval models and generates high-quality binary hash codes seamlessly.
AbstractList Hashing is frequently used in approximate nearest neighbor search due to its storage and search efficiency. On account of the bottleneck of traditional learning to hash methods, deep-based learning to hash has gained quite a popularity among researchers recently. While such methods show a promising performance gain by utilizing deep neural networks into its end-to-end training process to generate compact binary codes, the intrinsic connections between components make it unfeasible to optimize the architecture significantly. Subject to noise interference and absence of similarity labels of training data, normal unsupervised deep models even carry a noticeable deviation at representation learning stage. By integrating Generative Adversarial Network, this paper presents a novel architecture for generating compact hash codes from an extended set derived from original images while using the benefit of similarity prediction. Extensive experiments conducted on three benchmarks, NUS-WIDE, CIFAR-10, and MS-COCO illustrate that our method outperforms state-of-the-art image retrieval models and generates high-quality binary hash codes seamlessly.
Author Wang, Zijie
Meng, Fanlei
Wu, Xiangyu
Cao, Yuan
Author_xml – sequence: 1
  givenname: Yuan
  surname: Cao
  fullname: Cao, Yuan
  email: cy8661@ouc.edu.cn
  organization: Ocean University of China,School of Computer Science and Technology,Qingdao,China
– sequence: 2
  givenname: Fanlei
  surname: Meng
  fullname: Meng, Fanlei
  organization: Ocean University of China,School of Computer Science and Technology,Qingdao,China
– sequence: 3
  givenname: Xiangyu
  surname: Wu
  fullname: Wu, Xiangyu
  organization: Ocean University of China,School of Computer Science and Technology,Qingdao,China
– sequence: 4
  givenname: Zijie
  surname: Wang
  fullname: Wang, Zijie
  organization: Ocean University of China,School of Computer Science and Technology,Qingdao,China
BookMark eNotjMtOAjEUQKvRRED-wJj-wODt9DVdEkQkIUpE1-ROewdqmGI6ExL-Xo2uzuKcnCG7SsdEjN0LmAgB7mE5W08fNwaUlpMSSjkBKEFdsLGzrpIapAQr7CUblMZBoZ3RN2zYdZ-_2Y8esJcFJcrYxxPxedpj8tRS6osaOwp8E9t4wBz7M19nCtH38Zj4M3b7mHa8OWa-bHFH_I36HOmEh1t23eCho_E_R-zjaf4-ey5Wr4vlbLoqohCuL7yuaqrQAPqglJdNwAYaAKuc8AGg1jZUAkUFtfWm1gaNMI0UytdKBarkiN39fSMRbb9ybDGftwKU1U4o-Q2UDFJL
CODEN IEEPAD
ContentType Conference Proceeding
DBID 6IE
6IL
CBEJK
RIE
RIL
DOI 10.1109/ICPADS60453.2023.00204
DatabaseName IEEE Electronic Library (IEL) Conference Proceedings
IEEE Xplore POP ALL
IEEE Xplore All Conference Proceedings
IEEE Electronic Library (IEL)
IEEE Proceedings Order Plans (POP All) 1998-Present
DatabaseTitleList
Database_xml – sequence: 1
  dbid: RIE
  name: IEEE Electronic Library (IEL)
  url: https://ieeexplore.ieee.org/
  sourceTypes: Publisher
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISBN 9798350330717
EISSN 2690-5965
EndPage 1444
ExternalDocumentID 10475914
Genre orig-research
GrantInformation_xml – fundername: Natural Science Foundation of Shandong Province
  funderid: 10.13039/501100007129
GroupedDBID 29O
6IE
6IF
6IH
6IK
6IL
6IM
6IN
AAJGR
AAWTH
ABLEC
ADZIZ
ALMA_UNASSIGNED_HOLDINGS
BEFXN
BFFAM
BGNUA
BKEBE
BPEOZ
CBEJK
CHZPO
IEGSK
IPLJI
OCL
RIE
RIL
RNS
ID FETCH-LOGICAL-i119t-c58be8a60acd44c3fdaf0f007491cd00b57d81a180b7c6b56a616f314cb44de83
IEDL.DBID RIE
IngestDate Wed Aug 27 02:11:35 EDT 2025
IsPeerReviewed false
IsScholarly true
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-i119t-c58be8a60acd44c3fdaf0f007491cd00b57d81a180b7c6b56a616f314cb44de83
PageCount 8
ParticipantIDs ieee_primary_10475914
PublicationCentury 2000
PublicationDate 2023-Dec.-17
PublicationDateYYYYMMDD 2023-12-17
PublicationDate_xml – month: 12
  year: 2023
  text: 2023-Dec.-17
  day: 17
PublicationDecade 2020
PublicationTitle Proceedings - International Conference on Parallel and Distributed Systems
PublicationTitleAbbrev ICPADS
PublicationYear 2023
Publisher IEEE
Publisher_xml – name: IEEE
SSID ssj0020350
Score 2.2411025
Snippet Hashing is frequently used in approximate nearest neighbor search due to its storage and search efficiency. On account of the bottleneck of traditional...
SourceID ieee
SourceType Publisher
StartPage 1437
SubjectTerms Benchmark testing
Binary codes
generative model
hashing
Image retrieval
Scalability
Semantics
Training
Training data
unsupervised learning
Title Generative Enhancement-based Similarity Prediction Hashing for Image Retrieval
URI https://ieeexplore.ieee.org/document/10475914
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LTwIxEG6UePCED4zv9OC1sLWv7dEgBC6EiCbcSF8b98BiEPz9droLxoMHb5se2mRm2_mm028-hB5yZoIWihJlHxnhInhiOIWu-4xpZzh3wSaxCTWZ5PO5njZk9cSFCSGkx2ehC5-plu9XbgtXZT1oKyA0yFYfKiVrstY-u4ISWUMBppnujfvTp-eZjIiFdUEivJtooL80VFIIGbb_ufgJ6vyQ8fB0H2ZO0UGozlB7p8aAm815jiZ1B2k4vvCgegdvwowE4pTHs3JZxiQ2Yu44GRRnwCF4VEsp4Yhc8XgZjxb8khS24u_XQW_DwWt_RBq1BFJSqjfEidyG3MjMOB9NzApviqwAiKCp81lmhfI5NTTPrHLSCmkklQWj3FnOfcjZBWpVqypcIlwI60ErBZIP7oSPkEK5wkXwwWL0N8UV6oB9Fh91Q4zFzjTXf4zfoGNwAbwCoeoWtTbrbbhDR-5rU36u75MbvwHWYZ8O
linkProvider IEEE
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV07T8MwELZQQYKpPIp444E1bVzbSTyi0ioVJapokbpVfkVkaIpKy-_H56RFDAxskQdbuot93_n83YfQQ0KlFTwmQay6NGDcmkAyAl33KRVaMqat8mITcZYls5kY12R1z4Wx1vrHZ7YNn76Wb5Z6A1dlHWgrwAXIVu9zxrphRdfa5VdQJKtJwCQUnWFv_Pg0iRxmoW0QCW97IugvFRUfRAbNfy5_jFo_dDw83gWaE7Rny1PU3Oox4Hp7nqGs6iENBxjul-_gT5gxgEhl8KRYFC6NdajbTQblGXAJTisxJeywKx4u3OGCX73GlvsBW-ht0J_20qDWSwgKQsQ60DxRNpFRKLVxRqa5kXmYA0gQRJswVDw2CZEkCVWsI8UjGZEop4RpxZixCT1HjXJZ2guEc64MqKVA-sE0Nw5UxDrXDn5QF_9lfolaYJ_5R9USY741zdUf4_foMJ2-jOajYfZ8jY7AHfAmhMQ3qLFebewtOtBf6-Jzdedd-g1K2aJV
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=Proceedings+-+International+Conference+on+Parallel+and+Distributed+Systems&rft.atitle=Generative+Enhancement-based+Similarity+Prediction+Hashing+for+Image+Retrieval&rft.au=Cao%2C+Yuan&rft.au=Meng%2C+Fanlei&rft.au=Wu%2C+Xiangyu&rft.au=Wang%2C+Zijie&rft.date=2023-12-17&rft.pub=IEEE&rft.eissn=2690-5965&rft.spage=1437&rft.epage=1444&rft_id=info:doi/10.1109%2FICPADS60453.2023.00204&rft.externalDocID=10475914