ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning

In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficac...

Celý popis

Uloženo v:

Podrobná bibliografie
Vydáno v:	IEEE transactions on pattern analysis and machine intelligence Ročník 44; číslo 12; s. 9733 - 9740
Hlavní autoři:	Yan, Caixia, Chang, Xiaojun, Li, Zhihui, Guan, Weili, Ge, Zongyuan, Zhu, Lei, Zheng, Qinghua
Médium:	Journal Article
Jazyk:	angličtina
Vydáno:	New York IEEE 01.12.2022 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Témata:	Computer architecture Datasets Differentiable architecture search Generative adversarial networks Generators Optimization Search methods Source code Task analysis Testing Training Zero-shot learning
ISSN:	0162-8828, 1939-3539, 2160-9292, 1939-3539
On-line přístup:	Získat plný text
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!

Abstract	In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficacy, however, there is still no guarantee that these hand-crafted models can consistently achieve good performance across diversified datasets or scenarios. Accordingly, in this paper, we turn to neural architecture search (NAS) and make the first attempt to bring NAS techniques into the ZSL realm. Specifically, we propose a differentiable GAN architecture search method over a specifically designed search space for zero-shot learning, referred to as ZeroNAS. Considering the relevance and balance of the generator and discriminator, ZeroNAS jointly searches their architectures in a min-max player game via adversarial training. Extensive experiments conducted on four widely used benchmark datasets demonstrate that ZeroNAS is capable of discovering desirable architectures that perform favorably against state-of-the-art ZSL and generalized zero-shot learning (GZSL) approaches. Source code is at https://github.com/caixiay/ZeroNAS .
AbstractList	In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficacy, however, there is still no guarantee that these hand-crafted models can consistently achieve good performance across diversified datasets or scenarios. Accordingly, in this paper, we turn to neural architecture search (NAS) and make the first attempt to bring NAS techniques into the ZSL realm. Specifically, we propose a differentiable GAN architecture search method over a specifically designed search space for zero-shot learning, referred to as ZeroNAS. Considering the relevance and balance of the generator and discriminator, ZeroNAS jointly searches their architectures in a min-max player game via adversarial training. Extensive experiments conducted on four widely used benchmark datasets demonstrate that ZeroNAS is capable of discovering desirable architectures that perform favorably against state-of-the-art ZSL and generalized zero-shot learning (GZSL) approaches. Source code is at https://github.com/caixiay/ZeroNAS.In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficacy, however, there is still no guarantee that these hand-crafted models can consistently achieve good performance across diversified datasets or scenarios. Accordingly, in this paper, we turn to neural architecture search (NAS) and make the first attempt to bring NAS techniques into the ZSL realm. Specifically, we propose a differentiable GAN architecture search method over a specifically designed search space for zero-shot learning, referred to as ZeroNAS. Considering the relevance and balance of the generator and discriminator, ZeroNAS jointly searches their architectures in a min-max player game via adversarial training. Extensive experiments conducted on four widely used benchmark datasets demonstrate that ZeroNAS is capable of discovering desirable architectures that perform favorably against state-of-the-art ZSL and generalized zero-shot learning (GZSL) approaches. Source code is at https://github.com/caixiay/ZeroNAS. In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of training samples in ZSL, a surge of GAN architectures have been developed by human experts through trial-and-error testing. Despite their efficacy, however, there is still no guarantee that these hand-crafted models can consistently achieve good performance across diversified datasets or scenarios. Accordingly, in this paper, we turn to neural architecture search (NAS) and make the first attempt to bring NAS techniques into the ZSL realm. Specifically, we propose a differentiable GAN architecture search method over a specifically designed search space for zero-shot learning, referred to as ZeroNAS. Considering the relevance and balance of the generator and discriminator, ZeroNAS jointly searches their architectures in a min-max player game via adversarial training. Extensive experiments conducted on four widely used benchmark datasets demonstrate that ZeroNAS is capable of discovering desirable architectures that perform favorably against state-of-the-art ZSL and generalized zero-shot learning (GZSL) approaches. Source code is at https://github.com/caixiay/ZeroNAS .
Author	Zhu, Lei Chang, Xiaojun Zheng, Qinghua Yan, Caixia Ge, Zongyuan Li, Zhihui Guan, Weili
Author_xml	– sequence: 1 givenname: Caixia orcidid: 0000-0003-2595-0398 surname: Yan fullname: Yan, Caixia email: yancaixia@stu.xjtu.edu.cn organization: Department of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China – sequence: 2 givenname: Xiaojun orcidid: 0000-0002-7778-8807 surname: Chang fullname: Chang, Xiaojun email: cxj273@gmail.com organization: School of Computing Technologies, RMIT University, Melbourne, VIC, Australia – sequence: 3 givenname: Zhihui orcidid: 0000-0001-9642-8009 surname: Li fullname: Li, Zhihui email: zhihuilics@gmail.com organization: Shandong Artificial Intelligence Institute, Qilu University of Technology (Shandong Academy of Sciences), Jinan, China – sequence: 4 givenname: Weili orcidid: 0000-0002-5658-5509 surname: Guan fullname: Guan, Weili email: honeyguan@gmail.com organization: Faculty of Information Technology, Monash University, Melbourne, VIC, Australia – sequence: 5 givenname: Zongyuan orcidid: 0000-0002-5880-8673 surname: Ge fullname: Ge, Zongyuan email: Zongyuan.Ge@monash.edu organization: Faculty of Information Technology, Monash University, Melbourne, VIC, Australia – sequence: 6 givenname: Lei orcidid: 0000-0002-2993-7142 surname: Zhu fullname: Zhu, Lei email: leizhu0608@gmail.com organization: School of Information Science and Engineering, Shandong Normal University, Jinan, China – sequence: 7 givenname: Qinghua surname: Zheng fullname: Zheng, Qinghua email: qhzheng@mail.xjtu.edu.cn organization: Department of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, China
BookMark	eNp9kE1PGzEQhi1EBQH6B-hlpV64bLDHjtfuLaJ8SeFDClx6sZz1GEwXm9obEP-eDUEcOPQ00uh93hk9O2QzpoiE7DM6Zozqw5vr6cX5GCiwMWfQcCE3yAiYpLUGDZtkRJmEWilQ22SnlAdKmZhQvkW2uWgkTJQYkds_mNPldP6r-h28x4yxD3bRYXWKEbPtwzNWU_eMudgcbFddYv-S8t9SzdHm9r7yKVerinp-n_pqNixjiHd75Ju3XcHvH3OX3J4c3xyd1bOr0_Oj6axuOai-VtZTTR3ShYKJluAaZ5kUAq12Qjgn7MIDWtp420jXLJTC1rUSGArbIvd8lxyse59y-rfE0pvHUFrsOhsxLYsZWhuhFQM5RH9-iT6kZY7Dd2aljqtJo_mQgnWqzamUjN485fBo86th1Kykm3fpZiXdfEgfIPUFakM_qEuxzzZ0_0d_rNGAiJ-3tGRAheBv-4qP_w
CODEN	ITPIDJ
CitedBy_id	crossref_primary_10_1109_TCSVT_2023_3293514 crossref_primary_10_1016_j_patcog_2023_110133 crossref_primary_10_1007_s11263_024_02014_w crossref_primary_10_1007_s12652_023_04703_9 crossref_primary_10_1016_j_ins_2023_119883 crossref_primary_10_1007_s12652_022_03887_w crossref_primary_10_1109_TII_2024_3363078 crossref_primary_10_1109_TNNLS_2024_3382724 crossref_primary_10_1109_TIM_2024_3470961 crossref_primary_10_3390_s23135774 crossref_primary_10_1016_j_knosys_2023_110785 crossref_primary_10_1109_TNNLS_2023_3331506 crossref_primary_10_1109_TMM_2023_3289755 crossref_primary_10_32604_cmc_2024_059715 crossref_primary_10_1007_s12652_024_04779_x crossref_primary_10_1016_j_ins_2023_118960 crossref_primary_10_1109_TMM_2023_3318289 crossref_primary_10_1016_j_cviu_2023_103721 crossref_primary_10_1109_TIM_2023_3280503 crossref_primary_10_1109_TNNLS_2024_3442290 crossref_primary_10_1016_j_engappai_2023_105845 crossref_primary_10_1049_ell2_12916 crossref_primary_10_1109_TIP_2023_3305817 crossref_primary_10_1109_TNNLS_2023_3314451 crossref_primary_10_1109_TII_2025_3526478 crossref_primary_10_1109_TBDATA_2024_3414341 crossref_primary_10_3390_app13084836 crossref_primary_10_3389_fnins_2024_1519970 crossref_primary_10_1007_s11431_022_2197_y crossref_primary_10_1109_TNNLS_2023_3347792 crossref_primary_10_1109_TMM_2023_3284591 crossref_primary_10_1145_3571285 crossref_primary_10_3390_diagnostics13101700 crossref_primary_10_1109_TMM_2023_3289729 crossref_primary_10_1109_TMM_2024_3371220 crossref_primary_10_1109_TII_2024_3423487 crossref_primary_10_1109_TKDE_2025_3543503 crossref_primary_10_1016_j_engappai_2024_109020 crossref_primary_10_1016_j_imavis_2025_105456 crossref_primary_10_1007_s12652_022_03766_4 crossref_primary_10_1109_TIP_2023_3308393 crossref_primary_10_1109_TII_2024_3383459 crossref_primary_10_1109_TNNLS_2024_3359657 crossref_primary_10_1016_j_patrec_2023_06_016 crossref_primary_10_1109_TC_2024_3365949 crossref_primary_10_1109_TNNLS_2023_3327103 crossref_primary_10_1109_TKDE_2024_3384270 crossref_primary_10_1109_ACCESS_2024_3397664 crossref_primary_10_1109_TCYB_2024_3455760 crossref_primary_10_1016_j_dsp_2024_104612 crossref_primary_10_1109_TMM_2023_3324588 crossref_primary_10_1109_TMM_2023_3294800 crossref_primary_10_1016_j_engappai_2023_106477 crossref_primary_10_1109_TNNLS_2023_3330475 crossref_primary_10_1007_s11633_022_1357_9 crossref_primary_10_1109_TSMC_2024_3374393 crossref_primary_10_3390_computers12120258 crossref_primary_10_1016_j_patcog_2023_109591 crossref_primary_10_26599_BDMA_2023_9020019 crossref_primary_10_1109_ACCESS_2023_3317883 crossref_primary_10_1016_j_cviu_2025_104468 crossref_primary_10_1016_j_knosys_2023_110991 crossref_primary_10_1007_s12652_024_04761_7 crossref_primary_10_1109_TIM_2025_3545713 crossref_primary_10_1109_TPAMI_2021_3137605 crossref_primary_10_1007_s11227_023_05625_1 crossref_primary_10_3390_rs17040725 crossref_primary_10_1016_j_inffus_2025_103640 crossref_primary_10_1109_TII_2022_3190554 crossref_primary_10_3233_JIFS_224297 crossref_primary_10_1007_s12652_023_04641_6 crossref_primary_10_3390_s23084102 crossref_primary_10_1016_j_image_2024_117128 crossref_primary_10_1109_TNNLS_2023_3319315 crossref_primary_10_1109_TNNLS_2023_3309104 crossref_primary_10_1016_j_knosys_2023_110982 crossref_primary_10_1109_ACCESS_2023_3325705 crossref_primary_10_1016_j_neunet_2025_107423 crossref_primary_10_3390_electronics10243103 crossref_primary_10_1109_TNNLS_2023_3326477 crossref_primary_10_1007_s12652_024_04777_z crossref_primary_10_3390_s23104828 crossref_primary_10_1109_TIP_2023_3326691 crossref_primary_10_1109_TMM_2023_3340550 crossref_primary_10_3390_electronics10243183 crossref_primary_10_1007_s12652_023_04676_9 crossref_primary_10_1109_TMM_2024_3408048 crossref_primary_10_1109_TBDATA_2023_3313028 crossref_primary_10_1109_TPAMI_2023_3248041 crossref_primary_10_1016_j_knosys_2025_114017 crossref_primary_10_1109_TMM_2024_3521731 crossref_primary_10_1109_TMM_2023_3336576 crossref_primary_10_1109_TSMC_2024_3375456 crossref_primary_10_1109_TNNLS_2023_3339614 crossref_primary_10_1109_TNNLS_2023_3309632 crossref_primary_10_1109_TPAMI_2022_3229526 crossref_primary_10_3233_MGS_230132 crossref_primary_10_1016_j_knosys_2023_110452 crossref_primary_10_1016_j_neunet_2023_07_011 crossref_primary_10_1007_s12652_024_04764_4 crossref_primary_10_1109_TMM_2023_3303712 crossref_primary_10_1109_TNNLS_2023_3322390 crossref_primary_10_1016_j_jprocont_2024_103297 crossref_primary_10_1109_TMM_2023_3290479 crossref_primary_10_1109_TMM_2023_3321421 crossref_primary_10_1080_17509653_2025_2455964 crossref_primary_10_1016_j_patcog_2023_110038 crossref_primary_10_1109_TII_2024_3395648 crossref_primary_10_1109_TMM_2023_3276523 crossref_primary_10_1109_TCSII_2023_3310192 crossref_primary_10_1007_s11263_025_02394_7 crossref_primary_10_1016_j_ins_2023_119661 crossref_primary_10_1109_TKDE_2023_3327777 crossref_primary_10_1007_s12652_023_04691_w crossref_primary_10_1109_TEVC_2022_3227562 crossref_primary_10_1109_TEVC_2023_3307245 crossref_primary_10_3390_electronics13040798 crossref_primary_10_1016_j_ins_2023_119157 crossref_primary_10_1109_TMM_2023_3256092 crossref_primary_10_1109_TII_2023_3306366 crossref_primary_10_1007_s12652_022_03788_y crossref_primary_10_1109_TIM_2025_3565070 crossref_primary_10_1109_TNNLS_2023_3289209 crossref_primary_10_1109_TIP_2024_3354420 crossref_primary_10_1109_TMM_2023_3330524 crossref_primary_10_3390_e25101467 crossref_primary_10_1109_TII_2024_3384597 crossref_primary_10_1016_j_eswa_2023_120812 crossref_primary_10_1109_TNNLS_2023_3336765 crossref_primary_10_1109_TIP_2023_3286710 crossref_primary_10_1016_j_ins_2024_121005 crossref_primary_10_1109_TNNLS_2023_3278715 crossref_primary_10_1109_TCSVT_2023_3285046 crossref_primary_10_1109_TMM_2023_3327645 crossref_primary_10_1109_TCSS_2023_3306909
Cites_doi	10.1109/CVPR.2019.00089 10.1007/s00521-021-06309-8 10.1109/CVPR.2019.00017 10.1109/CVPR.2016.13 10.1109/CVPR.2018.00581 10.1109/CVPR.2009.5206848 10.1109/ICCV.2019.00994 10.1109/TPAMI.2022.3194044 10.1109/CVPR.2018.00907 10.1109/ICCV.2017.154 10.1109/ICCV.2019.00332 10.1007/978-3-030-58542-6_29 10.1109/CVPR.2017.328 10.1007/978-3-030-01231-1_2 10.1109/CVPR.2019.01052 10.1109/TPAMI.2020.3035351 10.1109/CVPR.2019.00758 10.1109/CVPR.2016.90 10.1016/j.neucom.2018.10.043 10.1109/ICVGIP.2008.47 10.1609/aaai.v34i04.6069 10.1109/TPAMI.2013.140 10.1109/CVPR.2015.7298594 10.1609/aaai.v33i01.33014780 10.1609/aaai.v34i04.6143 10.1145/3343031.3350901 10.1109/CVPR.2019.01022 10.1109/CVPR.2012.6247998 10.1109/CVPR.2018.00111
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2022
DBID	97E RIA RIE AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TPAMI.2021.3127346
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Xplore CrossRef Computer and Information Systems Abstracts Electronics & Communications 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 MEDLINE - Academic
DatabaseTitle	CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic
DatabaseTitleList	MEDLINE - Academic Technology Research Database
Database_xml	– sequence: 1 dbid: RIE name: IEEE url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 2 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Engineering Computer Science
EISSN	2160-9292 1939-3539
EndPage	9740
ExternalDocumentID	10_1109_TPAMI_2021_3127346 9612044
Genre	orig-research
GrantInformation_xml	– fundername: National Natural Science Foundation of China; National Nature Science Foundation of China grantid: 62137002; 61872287; 62050194; 61906109 funderid: 10.13039/501100001809 – fundername: Consulting Research Project of Chinese Academy of Engineering – fundername: Australian Research Council grantid: DE190100626 funderid: 10.13039/501100000923 – fundername: China Knowledge Center for Engineering Science and Technology – fundername: National Key Research and Development Program of China grantid: 2018AAA0101400 – fundername: National Natural Science Foundation of China grantid: 61721002 funderid: 10.13039/501100001809 – fundername: Innovation Research Team of Ministry of Education grantid: IRT_17R86
GroupedDBID	--- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT AENEX AGQYO AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ IEDLZ IFIPE IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNS RXW TAE TN5 UHB ~02 AAYXX CITATION 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c328t-8af090de0b825962d7da1644ea9d44dd4abf2ea07fa76d7b88ecdc621e4ace3f3
IEDL.DBID	RIE
ISICitedReferencesCount	154
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000880661400084&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0162-8828 1939-3539
IngestDate	Wed Oct 01 14:45:08 EDT 2025 Sun Nov 30 05:12:47 EST 2025 Sat Nov 29 02:58:18 EST 2025 Tue Nov 18 20:47:35 EST 2025 Wed Aug 27 02:18:56 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	12
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c328t-8af090de0b825962d7da1644ea9d44dd4abf2ea07fa76d7b88ecdc621e4ace3f3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0002-5658-5509 0000-0001-9642-8009 0000-0002-5880-8673 0000-0002-2993-7142 0000-0003-2595-0398 0000-0002-7778-8807
PMID	34762584
PQID	2734385793
PQPubID	85458
PageCount	8
ParticipantIDs	crossref_primary_10_1109_TPAMI_2021_3127346 proquest_miscellaneous_2597498126 crossref_citationtrail_10_1109_TPAMI_2021_3127346 ieee_primary_9612044 proquest_journals_2734385793
PublicationCentury	2000
PublicationDate	2022-12-01
PublicationDateYYYYMMDD	2022-12-01
PublicationDate_xml	– month: 12 year: 2022 text: 2022-12-01 day: 01
PublicationDecade	2020
PublicationPlace	New York
PublicationPlace_xml	– name: New York
PublicationTitle	IEEE transactions on pattern analysis and machine intelligence
PublicationTitleAbbrev	TPAMI
PublicationYear	2022
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	ref35 ref13 ref37 ref15 wei (ref17) 2018 ref36 ref30 zhang (ref25) 2002 ref10 liu (ref11) 2019 goodfellow (ref1) 2014 ref39 ref38 ref16 ref19 baker (ref27) 2017 ref18 ren (ref22) 2021; 54 zoph (ref21) 2017 ref45 ref26 ref20 ref42 wang (ref14) 0 ref41 ref44 ref43 yao (ref32) 2020 ref28 zhang (ref24) 2020 jin (ref31) 0 ref29 ref8 chen (ref12) 2019 ref7 ref9 ref4 ref6 wah (ref34) 2011 ref5 arjovsky (ref2) 2017 cheng (ref23) 2020 ref40 denton (ref3) 2015 hundt (ref33) 0 maaten (ref46) 2008; 9
References_xml	– year: 2017 ident: ref27 article-title: Designing neural network architectures using reinforcement learning publication-title: Proc ICLR – volume: 54 start-page: 76:1 year: 2021 ident: ref22 article-title: A comprehensive survey of neural architecture search: Challenges and solutions publication-title: ACM Comput Surv – year: 0 ident: ref14 article-title: AGAN: Towards automated design of generative adversarial networks publication-title: 2019 arXiv 1906 11080 – ident: ref6 doi: 10.1109/CVPR.2019.00089 – year: 2019 ident: ref11 article-title: Darts: Differentiable architecture search publication-title: Proc ICLR – volume: 9 start-page: 2579 year: 2008 ident: ref46 article-title: Visualizing data using t-SNE publication-title: J Mach Learn Res – year: 0 ident: ref31 article-title: Auto-keras: Efficient neural architecture search with network morphism publication-title: 2018 arXiv 1806 10282 – ident: ref16 doi: 10.1007/s00521-021-06309-8 – ident: ref26 doi: 10.1109/CVPR.2019.00017 – ident: ref38 doi: 10.1109/CVPR.2016.13 – ident: ref4 doi: 10.1109/CVPR.2018.00581 – year: 0 ident: ref33 article-title: SharpDARTS: Faster and more accurate differentiable architecture search publication-title: 2019 arXiv 1903 09900 – ident: ref40 doi: 10.1109/CVPR.2009.5206848 – start-page: 2672 year: 2014 ident: ref1 article-title: Generative adversarial nets publication-title: Proc NIPS – year: 2017 ident: ref21 article-title: Neural architecture search with reinforcement learning publication-title: Proc ICLR – ident: ref20 doi: 10.1109/ICCV.2019.00994 – start-page: 1884 year: 2019 ident: ref12 article-title: DetNAS: Neural architecture search on object detection publication-title: Proc NIPS – ident: ref10 doi: 10.1109/TPAMI.2022.3194044 – ident: ref28 doi: 10.1109/CVPR.2018.00907 – start-page: 7806 year: 2002 ident: ref25 article-title: Overcoming multi-model forgetting in one-shot NAS with diversity maximization publication-title: Proc CVPR – ident: ref29 doi: 10.1109/ICCV.2017.154 – year: 2020 ident: ref23 article-title: Hierarchical neural architecture search for deep stereo matching publication-title: Proc NeurIPS – year: 2015 ident: ref3 article-title: Deep generative image models using a laplacian pyramid of adversarial networks publication-title: Proc NIPS – ident: ref13 doi: 10.1109/ICCV.2019.00332 – ident: ref44 doi: 10.1007/978-3-030-58542-6_29 – ident: ref45 doi: 10.1109/CVPR.2017.328 – start-page: 214 year: 2017 ident: ref2 article-title: Wasserstein generative adversarial networks publication-title: Proc ICML – ident: ref18 doi: 10.1007/978-3-030-01231-1_2 – ident: ref42 doi: 10.1109/CVPR.2019.01052 – ident: ref9 doi: 10.1109/TPAMI.2020.3035351 – year: 2018 ident: ref17 article-title: Improving the improved training of wasserstein GANs: A consistency term and its dual effect publication-title: Proc ICLR – ident: ref7 doi: 10.1109/CVPR.2019.00758 – ident: ref39 doi: 10.1109/CVPR.2016.90 – ident: ref5 doi: 10.1016/j.neucom.2018.10.043 – ident: ref35 doi: 10.1109/ICVGIP.2008.47 – ident: ref43 doi: 10.1609/aaai.v34i04.6069 – ident: ref37 doi: 10.1109/TPAMI.2013.140 – year: 2011 ident: ref34 article-title: The caltech-UCSD birds-200-2011 dataset – ident: ref15 doi: 10.1109/CVPR.2015.7298594 – ident: ref30 doi: 10.1609/aaai.v33i01.33014780 – year: 2020 ident: ref24 article-title: Differentiable neural architecture search in equivalent space with exploration enhancement publication-title: Proc NeurIPS – start-page: 6664 year: 2020 ident: ref32 article-title: Differentiable neural architecture search via proximal iterations publication-title: Proc AAAI doi: 10.1609/aaai.v34i04.6143 – ident: ref8 doi: 10.1145/3343031.3350901 – ident: ref41 doi: 10.1109/CVPR.2019.01022 – ident: ref36 doi: 10.1109/CVPR.2012.6247998 – ident: ref19 doi: 10.1109/CVPR.2018.00111
SSID	ssj0014503
Score	2.7013772
Snippet	In recent years, remarkable progress in zero-shot learning (ZSL) has been achieved by generative adversarial networks (GAN). To compensate for the lack of...
SourceID	proquest crossref ieee
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	9733
SubjectTerms	Computer architecture Datasets Differentiable architecture search Generative adversarial networks Generators Optimization Search methods Source code Task analysis Testing Training Zero-shot learning
Title	ZeroNAS: Differentiable Generative Adversarial Networks Search for Zero-Shot Learning
URI	https://ieeexplore.ieee.org/document/9612044 https://www.proquest.com/docview/2734385793 https://www.proquest.com/docview/2597498126
Volume	44
WOSCitedRecordID	wos000880661400084&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 customDbUrl: eissn: 2160-9292 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1baxQxFD60pQ_6YG2rdGstEXxrx2YymUni26KWFnQptJXFlyHXVig7ZS_-fk8y2UFRBN8GcmGYc8k5k3O-D-BtI50NtXVFYLUuML41hSkNL6SxIYbfwSQwna-fxWQip1N1tQGnQy-M9z4Vn_l38THd5bvOruKvsjOFxzHlfBM2hRB9r9ZwY8DrxIKMEQxaOKYR6wYZqs5ursZfLjEVZCVmqBHOJfIWVRzdQC35b-dRIlj5wyuno-Z85_9e8jk8yyElGfc6sAsbfrYHO2u6BpKtdw-e_oI9uA-33_y8m4yv35OPmSMFbd08eNIDUUcvSBJb80JHHSWTvl58QfoCZYLBLolbFNf33ZJkmNa7F3B7_unmw0WRORYKWzG5LKQOVFHnqcFUUTXMCacxg-JeK8e5c1ybwLymImjROGGk9NbZhpWea-urUL2ErVk38wdAFKsr25hGBupQGsyo2nKqI8QbL4XQIyjXX7q1GYA88mA8tCkRoapNgmqjoNosqBGcDGsee_iNf87ej_IYZmZRjOBoLdA2W-iijQsqWaN7GsGbYRhtK16Y6JnvVjgnZlsKQ6Dm8O87v4InLLZDpPKWI9hazlf-NWzbH8vvi_kxqulUHic1_Qnb4eIB
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fa9RAEB5qFawPVtuKp1VX8E3TbjabZLdvh1pavIZCr1J8CfuzFspF7od_v7ObvVBRBN8C2Q0h387sTHbm-wDeVcIaXxqbeVaqDONbnelc80xo40P47XUk0_k6qZtGXF3J8w34MPTCOOdi8Zk7CJfxLN92ZhV-lR1K3I4p5_fgfsk5y_tureHMgJdRBxljGLRxTCTWLTJUHk7Px2enmAyyHHPUQOgSlIsKjo6gFPy3HSlKrPzhl-Nmc7z9f6_5BB6noJKM-1XwFDbcbAe214INJNnvDjy6wz64C5ff3LxrxhdH5FNSSUFr17eO9FTUwQ-SqNe8UGGVkqavGF-QvkSZYLhLwiOyi-_dkiSi1us9uDz-PP14kiWVhcwUTCwzoTyV1DqqMVmUFbO1VZhDcaek5dxarrRnTtHaq7qytRbCGWsqljuujCt88Qw2Z93MPQciWVmYSlfCU4toMC1Lw6kKJG88r2s1gnz9pVuTKMiDEsZtG1MRKtsIVBuAahNQI3g_zPnRE3D8c_RuwGMYmaAYwf4a0DbZ6KINEwpRooMawdvhNlpXODJRM9etcEzItyQGQdWLvz_5DTw8mZ5N2slp8-UlbLHQHBGLXfZhczlfuVfwwPxc3izmr-Ni_QVxIORg
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=ZeroNAS%3A+Differentiable+Generative+Adversarial+Networks+Search+for+Zero-Shot+Learning&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=Yan%2C+Caixia&rft.au=Chang%2C+Xiaojun&rft.au=Li%2C+Zhihui&rft.au=Guan%2C+Weili&rft.date=2022-12-01&rft.issn=0162-8828&rft.eissn=2160-9292&rft.volume=44&rft.issue=12&rft.spage=9733&rft.epage=9740&rft_id=info:doi/10.1109%2FTPAMI.2021.3127346&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TPAMI_2021_3127346
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon