Deep Fuzzy Hashing Network for Efficient Image Retrieval

Hashing methods for efficient image retrieval aim at learning hash functions that map similar images to semantically correlated binary codes in the Hamming space with similarity well preserved. The traditional hashing methods usually represent image content by hand-crafted features. Deep hashing met...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on fuzzy systems Vol. 29; no. 1; pp. 166 - 176
Main Authors:	Lu, Huimin, Zhang, Ming, Xu, Xing, Li, Yujie, Shen, Heng Tao
Format:	Journal Article
Language:	English
Published:	New York IEEE 01.01.2021 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Artificial neural networks Binary codes Data models Data structures Deep neural network (DNN) Feature extraction Fuzzy logic fuzzy neural net-work (FNN) Fuzzy neural networks hashing learning Image management Image retrieval Machine learning Neural networks Similarity
ISSN:	1063-6706, 1941-0034
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Hashing methods for efficient image retrieval aim at learning hash functions that map similar images to semantically correlated binary codes in the Hamming space with similarity well preserved. The traditional hashing methods usually represent image content by hand-crafted features. Deep hashing methods based on deep neural network (DNN) architectures can generate more effective image features and obtain better retrieval performance. However, the underlying data structure is hardly captured by existing DNN models. Moreover, the similarity (either visually or semantically) between pairwise images is ambiguous, even uncertain, to be measured in the existing deep hashing methods. In this article, we propose a novel hashing method termed deep fuzzy hashing network (DFHN) to overcome the shortcomings of existing deep hashing approaches. Our DFHN method combines the fuzzy logic technique and the DNN to learn more effective binary codes, which can leverage fuzzy rules to model the uncertainties underlying the data. Derived from fuzzy logic theory, the generalized hamming distance is devised in the convolutional layers and fully connected layers in our DFHN to model their outputs, which come from an efficient xor operation on given inputs and weights. Extensive experiments show that our DFHN method obtains competitive retrieval accuracy with highly efficient training speed compared with several state-of-the-art deep hashing approaches on two large-scale image datasets: CIFAR-10 and NUS-WIDE.
AbstractList	Hashing methods for efficient image retrieval aim at learning hash functions that map similar images to semantically correlated binary codes in the Hamming space with similarity well preserved. The traditional hashing methods usually represent image content by hand-crafted features. Deep hashing methods based on deep neural network (DNN) architectures can generate more effective image features and obtain better retrieval performance. However, the underlying data structure is hardly captured by existing DNN models. Moreover, the similarity (either visually or semantically) between pairwise images is ambiguous, even uncertain, to be measured in the existing deep hashing methods. In this article, we propose a novel hashing method termed deep fuzzy hashing network (DFHN) to overcome the shortcomings of existing deep hashing approaches. Our DFHN method combines the fuzzy logic technique and the DNN to learn more effective binary codes, which can leverage fuzzy rules to model the uncertainties underlying the data. Derived from fuzzy logic theory, the generalized hamming distance is devised in the convolutional layers and fully connected layers in our DFHN to model their outputs, which come from an efficient xor operation on given inputs and weights. Extensive experiments show that our DFHN method obtains competitive retrieval accuracy with highly efficient training speed compared with several state-of-the-art deep hashing approaches on two large-scale image datasets: CIFAR-10 and NUS-WIDE.
Author	Xu, Xing Lu, Huimin Zhang, Ming Li, Yujie Shen, Heng Tao
Author_xml	– sequence: 1 givenname: Huimin orcidid: 0000-0001-9794-3221 surname: Lu fullname: Lu, Huimin email: dr.huimin.lu@ieee.org organization: Department of Mechanical and Control Engineering, Kyushu Institute of Technology, Kitakyushu, Japan – sequence: 2 givenname: Ming orcidid: 0000-0002-9732-4460 surname: Zhang fullname: Zhang, Ming email: zmingcs@gmail.com organization: Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 3 givenname: Xing orcidid: 0000-0001-5685-3123 surname: Xu fullname: Xu, Xing email: xing.xu@uestc.edu.cn organization: Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China – sequence: 4 givenname: Yujie orcidid: 0000-0002-0275-2797 surname: Li fullname: Li, Yujie email: yzyjli@gmail.com organization: School of Information Engineering, Yangzhou University, Yangzhou, China – sequence: 5 givenname: Heng Tao orcidid: 0000-0002-2999-2088 surname: Shen fullname: Shen, Heng Tao email: shenhengtao@hotmail.com organization: Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China
BookMark	eNp9kMFOAjEURRujiYD-gG4mcT34OtNpp0uDICREEwMbNk2nvGIRZrBTNPD1DkJcuHD17uKe-5LTJudlVSIhNxS6lIK8nwyms1k3gQS6icyZlPSMtKhkNAZI2XmTgacxF8AvSbuulwCUZTRvkfwRcRMNtvv9Lhrq-s2Vi-gZw1fl3yNb-ahvrTMOyxCN1nqB0SsG7_BTr67IhdWrGq9Pt0Omg_6kN4zHL0-j3sM4NimnIRbGADDG54WmIHgu0QAVjKPQlhaQplJbiZkxes6SXMwLEIWkFqTWFkySph1yd9zd-Opji3VQy2rry-alSphgOW_mD6382DK-qmuPVhkXdHBVGbx2K0VBHTypH0_q4EmdPDVo8gfdeLfWfvc_dHuEHCL-AhIynjWivwEpV3Ut
CODEN	IEFSEV
CitedBy_id	crossref_primary_10_1007_s11280_021_00976_2 crossref_primary_10_1007_s12652_021_02895_6 crossref_primary_10_3390_sym17020153 crossref_primary_10_1007_s42044_025_00277_1 crossref_primary_10_1016_j_cogr_2022_08_002 crossref_primary_10_1016_j_compeleceng_2022_108545 crossref_primary_10_1016_j_compeleceng_2022_107853 crossref_primary_10_1109_TFUZZ_2024_3402086 crossref_primary_10_1007_s11276_020_02382_4 crossref_primary_10_1016_j_compeleceng_2021_107173 crossref_primary_10_1007_s12652_020_02274_7 crossref_primary_10_1016_j_compeleceng_2024_109078 crossref_primary_10_1016_j_compeleceng_2022_107730 crossref_primary_10_1016_j_compeleceng_2024_109074 crossref_primary_10_1016_j_compeleceng_2024_109195 crossref_primary_10_1080_22797254_2023_2174706 crossref_primary_10_1016_j_compeleceng_2022_108261 crossref_primary_10_3233_IDA_215780 crossref_primary_10_1016_j_compeleceng_2024_109193 crossref_primary_10_1109_TITS_2022_3199805 crossref_primary_10_1016_j_compeleceng_2021_107508 crossref_primary_10_1155_2021_5595898 crossref_primary_10_1109_JIOT_2020_3024800 crossref_primary_10_32604_cmc_2024_052008 crossref_primary_10_1016_j_compeleceng_2022_107842 crossref_primary_10_1016_j_compeleceng_2023_108838 crossref_primary_10_1007_s11280_021_00968_2 crossref_primary_10_1016_j_compeleceng_2022_108538 crossref_primary_10_1109_TAI_2022_3153593 crossref_primary_10_1016_j_compeleceng_2022_107680 crossref_primary_10_1007_s11280_021_00938_8 crossref_primary_10_1016_j_compeleceng_2022_107684 crossref_primary_10_1016_j_compeleceng_2022_108258 crossref_primary_10_32604_cmc_2023_037134 crossref_primary_10_3390_electronics11142236 crossref_primary_10_1007_s11280_022_01037_y crossref_primary_10_1109_TSC_2022_3149847 crossref_primary_10_3390_sym14020334 crossref_primary_10_1016_j_asoc_2023_110209 crossref_primary_10_1109_LSP_2024_3509333 crossref_primary_10_1109_TCE_2024_3419447 crossref_primary_10_1016_j_compeleceng_2022_108250 crossref_primary_10_1016_j_compeleceng_2022_108093 crossref_primary_10_1155_2021_8013337 crossref_primary_10_1016_j_asoc_2022_109960 crossref_primary_10_1145_3403948 crossref_primary_10_1007_s12652_021_03444_x crossref_primary_10_1109_TFUZZ_2024_3425664 crossref_primary_10_1109_TITS_2022_3158253 crossref_primary_10_1007_s00530_024_01649_6 crossref_primary_10_1016_j_compeleceng_2023_108724 crossref_primary_10_1016_j_compeleceng_2023_108966 crossref_primary_10_1016_j_compeleceng_2021_107556 crossref_primary_10_1016_j_compeleceng_2021_107677 crossref_primary_10_1016_j_compeleceng_2021_107558 crossref_primary_10_1016_j_compeleceng_2021_107318 crossref_primary_10_1007_s11042_022_13991_w crossref_primary_10_1007_s12652_021_03420_5 crossref_primary_10_1016_j_compeleceng_2021_107319 crossref_primary_10_1016_j_compeleceng_2021_107152 crossref_primary_10_1109_TFUZZ_2024_3387429 crossref_primary_10_1016_j_compeleceng_2021_107670 crossref_primary_10_1016_j_compeleceng_2023_109011 crossref_primary_10_1016_j_procs_2022_09_174 crossref_primary_10_1016_j_compeleceng_2023_108841 crossref_primary_10_1016_j_compeleceng_2021_107673 crossref_primary_10_1016_j_compeleceng_2022_108168 crossref_primary_10_3390_math12142221 crossref_primary_10_3390_electronics10010014 crossref_primary_10_1007_s10586_023_04213_5 crossref_primary_10_1016_j_compeleceng_2022_108162 crossref_primary_10_1109_JIOT_2020_3011726 crossref_primary_10_1109_TFUZZ_2024_3436030 crossref_primary_10_3390_app151810034 crossref_primary_10_1007_s13042_022_01552_4 crossref_primary_10_1109_ACCESS_2021_3056330 crossref_primary_10_1109_TFUZZ_2024_3405541 crossref_primary_10_1016_j_jisa_2023_103673 crossref_primary_10_1016_j_compeleceng_2022_107866 crossref_primary_10_1016_j_compeleceng_2021_107206 crossref_primary_10_1016_j_compeleceng_2022_107747 crossref_primary_10_1016_j_compeleceng_2021_107041 crossref_primary_10_1007_s11042_022_13387_w crossref_primary_10_1109_TITS_2022_3182568 crossref_primary_10_1016_j_compeleceng_2022_108312 crossref_primary_10_1016_j_compeleceng_2021_107321 crossref_primary_10_1016_j_eswa_2023_120731 crossref_primary_10_1016_j_compeleceng_2023_108696 crossref_primary_10_1016_j_ypmed_2023_107618 crossref_primary_10_1016_j_compeleceng_2022_108270 crossref_primary_10_1007_s11063_021_10537_3 crossref_primary_10_2478_ijanmc_2022_0038 crossref_primary_10_1109_LSP_2023_3289761 crossref_primary_10_1016_j_compeleceng_2022_107777 crossref_primary_10_1016_j_compeleceng_2023_108986 crossref_primary_10_1016_j_compeleceng_2022_107779 crossref_primary_10_1016_j_compeleceng_2021_107370 crossref_primary_10_1016_j_compeleceng_2022_108342 crossref_primary_10_1016_j_compeleceng_2023_108583 crossref_primary_10_1109_ACCESS_2024_3510801 crossref_primary_10_1109_TCE_2024_3412168 crossref_primary_10_1016_j_compeleceng_2021_107252 crossref_primary_10_1016_j_compeleceng_2023_109033 crossref_primary_10_1016_j_compeleceng_2022_108345 crossref_primary_10_1016_j_compeleceng_2023_108622 crossref_primary_10_1016_j_compeleceng_2021_107255 crossref_primary_10_1016_j_compeleceng_2022_108189 crossref_primary_10_1016_j_compeleceng_2022_108465 crossref_primary_10_1016_j_compeleceng_2023_108982 crossref_primary_10_1016_j_cogr_2023_09_001 crossref_primary_10_1016_j_compeleceng_2023_108580 crossref_primary_10_1109_JIOT_2020_3036695 crossref_primary_10_1080_01431161_2022_2135413 crossref_primary_10_1109_JIOT_2020_3016145 crossref_primary_10_1109_LSP_2022_3157517 crossref_primary_10_1016_j_compeleceng_2022_108459 crossref_primary_10_1109_TITS_2022_3141107 crossref_primary_10_1016_j_compeleceng_2021_107027 crossref_primary_10_1016_j_jbo_2024_100645 crossref_primary_10_1016_j_compeleceng_2021_107667 crossref_primary_10_1016_j_compeleceng_2023_108914 crossref_primary_10_3233_JIFS_211426 crossref_primary_10_1016_j_asoc_2022_109481 crossref_primary_10_1016_j_compeleceng_2022_108177 crossref_primary_10_1016_j_compeleceng_2024_109269 crossref_primary_10_1016_j_cogr_2022_07_001 crossref_primary_10_1016_j_compeleceng_2022_108570 crossref_primary_10_1109_ACCESS_2024_3450920 crossref_primary_10_1109_TCSII_2022_3181057 crossref_primary_10_1016_j_compeleceng_2021_107385 crossref_primary_10_1109_TCE_2024_3470846 crossref_primary_10_1016_j_compeleceng_2021_107024 crossref_primary_10_1007_s00521_023_09118_3 crossref_primary_10_1016_j_compeleceng_2022_107882 crossref_primary_10_1016_j_compeleceng_2022_108179 crossref_primary_10_1016_j_compeleceng_2022_108575 crossref_primary_10_1016_j_compeleceng_2024_109267 crossref_primary_10_1109_JIOT_2024_3353250 crossref_primary_10_3390_s23010370 crossref_primary_10_1007_s13042_023_01774_0 crossref_primary_10_1109_TIFS_2025_3531104 crossref_primary_10_3233_JIFS_189707 crossref_primary_10_1007_s12652_021_03002_5 crossref_primary_10_1109_JSTARS_2025_3585184 crossref_primary_10_1016_j_compeleceng_2022_107679 crossref_primary_10_1016_j_compeleceng_2022_108127 crossref_primary_10_1109_TITS_2022_3145815 crossref_primary_10_3390_fractalfract8110637 crossref_primary_10_1007_s12652_021_03255_0 crossref_primary_10_1016_j_compeleceng_2023_108927 crossref_primary_10_3390_rs15163924 crossref_primary_10_1109_ACCESS_2025_3570790 crossref_primary_10_1016_j_compeleceng_2023_109056 crossref_primary_10_1016_j_engappai_2024_107960 crossref_primary_10_1016_j_compeleceng_2022_108003 crossref_primary_10_32604_cmc_2024_055592 crossref_primary_10_1109_JSEN_2023_3314441 crossref_primary_10_1016_j_compeleceng_2022_108084 crossref_primary_10_1016_j_compeleceng_2021_107192 crossref_primary_10_1016_j_asoc_2022_109795 crossref_primary_10_1109_TITS_2021_3076607 crossref_primary_10_1016_j_cogr_2021_06_004 crossref_primary_10_4018_JCIT_381312 crossref_primary_10_1145_3450520 crossref_primary_10_1016_j_cogr_2021_06_003 crossref_primary_10_1109_TITS_2021_3083656 crossref_primary_10_1016_j_compeleceng_2022_108237 crossref_primary_10_1109_TCE_2024_3445139 crossref_primary_10_1016_j_compeleceng_2022_107941 crossref_primary_10_1007_s13042_022_01559_x crossref_primary_10_1109_TCE_2024_3424456 crossref_primary_10_1016_j_compeleceng_2021_107648 crossref_primary_10_1016_j_compeleceng_2022_108077 crossref_primary_10_1016_j_compeleceng_2022_108473 crossref_primary_10_1016_j_compeleceng_2023_108893 crossref_primary_10_1016_j_compeleceng_2022_108075 crossref_primary_10_1007_s11042_022_13119_0 crossref_primary_10_1016_j_compeleceng_2022_108230 crossref_primary_10_1016_j_compeleceng_2023_108890 crossref_primary_10_1016_j_compeleceng_2023_108896 crossref_primary_10_1016_j_compeleceng_2022_108112 crossref_primary_10_1016_j_neucom_2021_12_073 crossref_primary_10_1016_j_compeleceng_2021_107366 crossref_primary_10_1007_s11280_022_01014_5 crossref_primary_10_1016_j_neucom_2024_128251 crossref_primary_10_1007_s11042_021_11649_7 crossref_primary_10_1007_s13042_024_02298_x crossref_primary_10_1016_j_compeleceng_2021_107083 crossref_primary_10_3390_app13074140
Cites_doi	10.1109/TKDE.2020.2970050 10.1109/CVPRW.2015.7301269 10.1109/12.106218 10.1109/ICCV.2015.123 10.1109/ICCV.2009.5459469 10.1109/TIP.2017.2676345 10.1109/TIP.2015.2405340 10.1109/TPAMI.2012.48 10.1007/978-3-319-19683-1_31 10.1109/CVPR.2014.275 10.1109/CVPR.2015.7298947 10.1109/TPAMI.2018.2789887 10.1007/s10462-018-9630-6 10.1109/34.895972 10.1109/TPAMI.2012.193 10.1109/TCSVT.2017.2771332 10.1109/TCYB.2018.2883970 10.1109/TFUZZ.2016.2574915 10.1109/ICCCYB.2005.1511558 10.1109/TNNLS.2014.2346537 10.1109/CVPR.2017.243 10.1109/TIP.2015.2467315 10.1109/CVPR.2014.81 10.1109/91.298447 10.1109/CVPR.2016.90 10.1016/0165-0114(94)90279-8 10.1109/TIP.2016.2612883 10.1109/91.963761 10.1109/CVPR.2016.227 10.1016/S0031-3203(01)00162-5 10.1016/j.entcs.2009.07.045 10.1145/1646396.1646452 10.1023/B:VISI.0000029664.99615.94 10.1109/CVPRW.2014.131 10.1109/CVPR.2009.5206848 10.1109/TNNLS.2020.2967597 10.1109/TCYB.2019.2928180 10.1016/j.neucom.2015.11.133 10.1007/978-3-642-35221-8 10.1109/CVPR.2015.7298594 10.1109/TPAMI.2019.2914897 10.1016/j.patcog.2017.02.034
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2021
DBID	97E RIA RIE AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
DOI	10.1109/TFUZZ.2020.2984991
DatabaseName	IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Computer and Information Systems Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional
DatabaseTitle	CrossRef Computer and Information Systems Abstracts Technology Research Database Computer and Information Systems Abstracts – Academic Advanced Technologies Database with Aerospace ProQuest Computer Science Collection Computer and Information Systems Abstracts Professional
DatabaseTitleList	Computer and Information Systems Abstracts
Database_xml	– sequence: 1 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	1941-0034
EndPage	176
ExternalDocumentID	10_1109_TFUZZ_2020_2984991 9056506
Genre	orig-research
GrantInformation_xml	– fundername: National Key Research and Development Program of China grantid: 2018AAA0102200 – fundername: Leading Initiative for Excellent Young Researchers of Ministry of Education, Culture, Sports, Science and Technology, Japan grantid: 16809746 – fundername: Sichuan Science and Technology Program, China grantid: 2019ZDZX0008; 2018GZDZX0032 – fundername: National Natural Science Foundation of China grantid: 61976049; 61632007 funderid: 10.13039/501100001809
GroupedDBID	-~X .DC 0R~ 29I 4.4 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 EBS EJD HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 O9- OCL P2P PQQKQ RIA RIE RNS TAE TN5 VH1 AAYXX CITATION 7SC 8FD JQ2 L7M L~C L~D
ID	FETCH-LOGICAL-c361t-7cc00446dba107689ec01746e7af1b0339af9e5ccad4287db07b91f09aaf0c233
IEDL.DBID	RIE
ISICitedReferencesCount	282
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000605370700013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1063-6706
IngestDate	Sun Nov 30 05:01:11 EST 2025 Tue Nov 18 22:24:33 EST 2025 Sat Nov 29 03:12:39 EST 2025 Wed Aug 27 02:32:36 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	1
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c361t-7cc00446dba107689ec01746e7af1b0339af9e5ccad4287db07b91f09aaf0c233
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14
ORCID	0000-0002-0275-2797 0000-0002-9732-4460 0000-0001-9794-3221 0000-0002-2999-2088 0000-0001-5685-3123
PQID	2474860043
PQPubID	85428
PageCount	11
ParticipantIDs	crossref_citationtrail_10_1109_TFUZZ_2020_2984991 ieee_primary_9056506 crossref_primary_10_1109_TFUZZ_2020_2984991 proquest_journals_2474860043
PublicationCentury	2000
PublicationDate	2021-01-01
PublicationDateYYYYMMDD	2021-01-01
PublicationDate_xml	– month: 01 year: 2021 text: 2021-01-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on fuzzy systems
PublicationTitleAbbrev	TFUZZ
PublicationYear	2021
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref56 ref12 ref59 ref14 ref53 ref52 babenk (ref39) 1994; 61 ref55 ref11 ref54 bay (ref2) 0 zhao (ref27) 0 ref17 kumar (ref46) 2019; 38 khan (ref32) 2019 szegedy (ref15) 0 ref51 ref50 zhu (ref57) 0 weiss (ref49) 0 ref48 ref47 ref42 ref41 gionis (ref18) 0 ref44 ref43 ronneberger (ref16) 0 ref8 ref7 ref9 fan (ref31) 0 ref4 ref3 ref6 ref5 ref40 krizhevsky (ref58) 2009 ref34 liu (ref19) 0 ref37 ref36 ref30 ref33 kulis (ref60) 0 ref1 lin (ref45) 2015; 26 ref24 ref23 norouzi (ref20) 0 ref26 ref22 ref21 xia (ref25) 0 babenko (ref38) 0 ref28 krizhevsky (ref10) 0 simonyan (ref35) 0 ref29
References_xml	– start-page: 1106 year: 0 ident: ref10 article-title: ImagNet classification with deep convolutional neural networks publication-title: Proc Annu Conf Neural Inf Process Syst – start-page: 404 year: 0 ident: ref2 article-title: SURF: Speeded up robust features publication-title: Proc Eur Conf Comput Vis – ident: ref21 doi: 10.1109/TKDE.2020.2970050 – ident: ref22 doi: 10.1109/CVPRW.2015.7301269 – ident: ref29 doi: 10.1109/12.106218 – ident: ref14 doi: 10.1109/ICCV.2015.123 – ident: ref33 doi: 10.1109/ICCV.2009.5459469 – ident: ref54 doi: 10.1109/TIP.2017.2676345 – ident: ref53 doi: 10.1109/TIP.2015.2405340 – start-page: 1753 year: 0 ident: ref49 article-title: Spectral hashing publication-title: Proc Int Conf Neural Inf Process – ident: ref55 doi: 10.1109/TPAMI.2012.48 – ident: ref40 doi: 10.1007/978-3-319-19683-1_31 – ident: ref50 doi: 10.1109/CVPR.2014.275 – start-page: 1556 year: 0 ident: ref27 article-title: Deep semantic ranking based hashing for multi-label image retrieval publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref26 doi: 10.1109/CVPR.2015.7298947 – ident: ref51 doi: 10.1109/TPAMI.2018.2789887 – start-page: 234 year: 0 ident: ref16 article-title: U-net: Convolutional networks for biomedical image segmentation publication-title: Proc Int Conf Med Image Comput Comput -Assisted Intervention – ident: ref30 doi: 10.1007/s10462-018-9630-6 – ident: ref6 doi: 10.1109/34.895972 – ident: ref7 doi: 10.1109/TPAMI.2012.193 – volume: 38 start-page: 2561 year: 2019 ident: ref46 article-title: Two-stage data encryption using chaotic neural networks publication-title: J Intell Fuzzy Syst – ident: ref56 doi: 10.1109/TCSVT.2017.2771332 – ident: ref23 doi: 10.1109/TCYB.2018.2883970 – ident: ref43 doi: 10.1109/TFUZZ.2016.2574915 – ident: ref47 doi: 10.1109/ICCCYB.2005.1511558 – volume: 26 start-page: 1442 year: 2015 ident: ref45 article-title: An interval type-2 neural fuzzy system for online system identification and feature elimination publication-title: IEEE Trans Neural Netw Learn Syst doi: 10.1109/TNNLS.2014.2346537 – ident: ref37 doi: 10.1109/CVPR.2017.243 – ident: ref28 doi: 10.1109/TIP.2015.2467315 – start-page: 2553 year: 0 ident: ref15 article-title: Deep neural networks for object detection publication-title: Proc Annu Conf Neural Inf Process Syst – ident: ref12 doi: 10.1109/CVPR.2014.81 – ident: ref42 doi: 10.1109/91.298447 – ident: ref36 doi: 10.1109/CVPR.2016.90 – volume: 61 start-page: 1 year: 1994 ident: ref39 article-title: Invited review on the principles of fuzzy neural networks publication-title: Fuzzy Sets Syst doi: 10.1016/0165-0114(94)90279-8 – ident: ref8 doi: 10.1109/TIP.2016.2612883 – start-page: 353 year: 0 ident: ref20 article-title: Minimal loss hashing for compact binary codes publication-title: Proc Int Conf Mach Learn – ident: ref44 doi: 10.1109/91.963761 – start-page: 2156 year: 0 ident: ref25 article-title: Supervised hashing for image retrieval via image representation learning publication-title: Proc AAAI Conf Artif Intell – start-page: 1042 year: 0 ident: ref60 article-title: Learning to hash with binary reconstructive embeddings publication-title: Proc Int Conf Neural Inf Process – ident: ref5 doi: 10.1109/CVPR.2016.227 – ident: ref3 doi: 10.1016/S0031-3203(01)00162-5 – ident: ref48 doi: 10.1016/j.entcs.2009.07.045 – ident: ref59 doi: 10.1145/1646396.1646452 – ident: ref1 doi: 10.1023/B:VISI.0000029664.99615.94 – year: 2009 ident: ref58 article-title: Learning multiple layers of features from tiny images – ident: ref11 doi: 10.1109/CVPRW.2014.131 – ident: ref34 doi: 10.1109/CVPR.2009.5206848 – start-page: 584 year: 0 ident: ref38 article-title: Neural codes for image retrieval publication-title: Proc Eur Conf Comput Vis – ident: ref17 doi: 10.1109/TNNLS.2020.2967597 – start-page: 518 year: 0 ident: ref18 article-title: Similarity search in high dimensions via hashing publication-title: Proc Int Conf Very Large Data Bases – ident: ref4 doi: 10.1109/TCYB.2019.2928180 – ident: ref9 doi: 10.1016/j.neucom.2015.11.133 – year: 2019 ident: ref32 article-title: A survey of the recent architectures of deep convolutional neural networks publication-title: arXiv 1901 06032 – ident: ref41 doi: 10.1007/978-3-642-35221-8 – start-page: 2415 year: 0 ident: ref57 article-title: Deep hashing network for efficient similarity retrieval publication-title: Proc AAAI Conf Artif Intell – start-page: 2074 year: 0 ident: ref19 article-title: Supervised hashing with kernels publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref13 doi: 10.1109/CVPR.2015.7298594 – ident: ref24 doi: 10.1109/TPAMI.2019.2914897 – ident: ref52 doi: 10.1016/j.patcog.2017.02.034 – start-page: 309 year: 0 ident: ref35 article-title: Very deep convolutional networks for large-scale image recognition publication-title: Proc Int Conf Learn Represent – start-page: 1923 year: 0 ident: ref31 article-title: Revisit fuzzy neural network: Demystifying batch normalization and ReLU with generalized hamming network publication-title: Proc Annu Conf Neural Inf Process Syst
SSID	ssj0014518
Score	2.690849
Snippet	Hashing methods for efficient image retrieval aim at learning hash functions that map similar images to semantically correlated binary codes in the Hamming...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	166
SubjectTerms	Artificial neural networks Binary codes Data models Data structures Deep neural network (DNN) Feature extraction Fuzzy logic fuzzy neural net-work (FNN) Fuzzy neural networks hashing learning Image management Image retrieval Machine learning Neural networks Similarity
Title	Deep Fuzzy Hashing Network for Efficient Image Retrieval
URI	https://ieeexplore.ieee.org/document/9056506 https://www.proquest.com/docview/2474860043
Volume	29
WOSCitedRecordID	wos000605370700013&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0034 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014518 issn: 1063-6706 databaseCode: RIE dateStart: 19930101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEB5q8aAHq61itUoO3nTbZJPdNEfRlgpSRFoovSybbAKCtqUPwf56k-y2KIrgbQ8JWebLZCaZxwdwxSg2TEoS0DgSAZNMBGmU8cDa0rjNWUak8Ug_8n6_PRqJpxLcbGthtNY--Uw33aeP5WdTtXJPZS1hrXXk-mvvcM7zWq1txIBFJC97i2kQcxxvCmSwaA26w_HYXgVD3AxF27r45JsR8qwqP45ib1-6lf_92SEcFH4kus2BP4KSnlShsuFoQIXKVmH_S8PBGrTvtZ6h7mq9_kC9nEYJ9fNEcGS9V9TxDSXsUujhzR406NnzbdnNeAzDbmdw1wsK7oRA0ZgsA66Uj9VmMiUu2Ca0srrHYs1TQySmVKRG6Mjil7lLUyYxl4IYLNLUYBVSegLlyXSiTwEZGimsjMm4C9FxKZUVpZFpnEUWSMHrQDbCTFTRWNzxW7wm_oKBReIBSBwASQFAHa63c2Z5W40_R9ecyLcjC2nXobHBLCk0b5GEjDteLczo2e-zzmEvdHkp_hmlAeXlfKUvYFe9L18W80u_qT4BR5jIUA
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3NS8MwFH-ICurBj01xOjUHb9qZNGnTHEU3Js4hssHYpTRpAoJuQzdB_3qTtBuKInjrISHl_fLyXvI-fgCnjGLDpCQBjSMRMMlEkEU5D6wtjRPOciKNR7rDu91kMBD3S3C-qIXRWvvkM91wnz6Wn4_VzD2VXQhrrSPXX3slYiwkRbXWImbAIlIUvsU0iDmO5yUyWFz0Wv3h0F4GQ9wIRWKdfPLNDHlelR-Hsbcwra3__ds2bJaeJLosoN-BJT2qwNacpQGVSluBjS8tB6uQXGs9Qa3Zx8c7ahdESqhbpIIj67-ipm8pYZdCN8_2qEEPnnHLbsdd6Leavat2ULInBIrGZBpwpXy0NpcZceE2oZXVPhZrnhkiMaUiM0JHFsHcXZtyibkUxGCRZQarkNI9WB6NR3ofkKGRwsqYnLsgHZdSWVEamcV5ZKEUvAZkLsxUla3FHcPFU-qvGFikHoDUAZCWANTgbDFnUjTW-HN01Yl8MbKUdg3qc8zSUvde05Bxx6yFGT34fdYJrLV7d520c9O9PYT10GWp-EeVOixPX2b6CFbV2_Tx9eXYb7BP3j3Llw
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%3Ajournal&rft.genre=article&rft.atitle=Deep+Fuzzy+Hashing+Network+for+Efficient+Image+Retrieval&rft.jtitle=IEEE+transactions+on+fuzzy+systems&rft.au=Lu%2C+Huimin&rft.au=Zhang%2C+Ming&rft.au=Xu%2C+Xing&rft.au=Li%2C+Yujie&rft.date=2021-01-01&rft.issn=1063-6706&rft.eissn=1941-0034&rft.volume=29&rft.issue=1&rft.spage=166&rft.epage=176&rft_id=info:doi/10.1109%2FTFUZZ.2020.2984991&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TFUZZ_2020_2984991
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1063-6706&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1063-6706&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1063-6706&client=summon