Representation learning via a semi-supervised stacked distance autoencoder for image classification
Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An autoencoder is a special type of neural network, often used for dimensionality reducti...
Uloženo v:
| Vydáno v: | Frontiers of information technology & electronic engineering Ročník 21; číslo 7; s. 1005 - 1018 |
|---|---|
| Hlavní autoři: | , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Hangzhou
Zhejiang University Press
01.07.2020
Springer Nature B.V College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China |
| Témata: | |
| ISSN: | 2095-9184, 2095-9230 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An autoencoder is a special type of neural network, often used for dimensionality reduction and feature extraction. The proposed method is based on the traditional autoencoder, incorporating the “distance” information between samples from different categories. The model is called a semi-supervised distance autoencoder. Each layer is first pre-trained in an unsupervised manner. In the subsequent supervised training, the optimized parameters are set as the initial values. To obtain more suitable features, we use a stacked model to replace the basic autoencoder structure with a single hidden layer. A series of experiments are carried out to test the performance of different models on several datasets, including the MNIST dataset, street view house numbers (SVHN) dataset, German traffic sign recognition benchmark (GTSRB), and CIFAR-10 dataset. The proposed semi-supervised distance autoencoder method is compared with the traditional autoencoder, sparse autoencoder, and supervised autoencoder. Experimental results verify the effectiveness of the proposed model. |
|---|---|
| AbstractList | TP391.9; Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An autoencoder is a special type of neural network, often used for dimensionality reduction and feature extraction. The proposed method is based on the traditional auto-encoder, incorporating the "distance" information between samples from different categories. The model is called a semi-supervised distance autoencoder. Each layer is first pre-trained in an unsupervised manner. In the subsequent supervised training, the optimized parameters are set as the initial values. To obtain more suitable features, we use a stacked model to replace the basic autoencoder structure with a single hidden layer. A series of experiments are carried out to test the performance of different models on several datasets, including the MNIST dataset, street view house numbers (SVHN) dataset, German traffic sign recognition benchmark (GTSRB), and CIFAR-10 dataset. The proposed semi-supervised distance autoencoder method is compared with the traditional autoencoder, sparse autoencoder, and supervised autoencoder. Experimental results verify the effectiveness of the proposed model. Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the features that are extracted via deep learning methods. An autoencoder is a special type of neural network, often used for dimensionality reduction and feature extraction. The proposed method is based on the traditional autoencoder, incorporating the “distance” information between samples from different categories. The model is called a semi-supervised distance autoencoder. Each layer is first pre-trained in an unsupervised manner. In the subsequent supervised training, the optimized parameters are set as the initial values. To obtain more suitable features, we use a stacked model to replace the basic autoencoder structure with a single hidden layer. A series of experiments are carried out to test the performance of different models on several datasets, including the MNIST dataset, street view house numbers (SVHN) dataset, German traffic sign recognition benchmark (GTSRB), and CIFAR-10 dataset. The proposed semi-supervised distance autoencoder method is compared with the traditional autoencoder, sparse autoencoder, and supervised autoencoder. Experimental results verify the effectiveness of the proposed model. |
| Author | Hou, Liang Wang, Zi-yang Luo, Xiao-yi Liang, Jun |
| AuthorAffiliation | College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China |
| AuthorAffiliation_xml | – name: College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China |
| Author_xml | – sequence: 1 givenname: Liang orcidid: 0000-0003-0887-627X surname: Hou fullname: Hou, Liang organization: College of Control Science and Engineering, Zhejiang University – sequence: 2 givenname: Xiao-yi surname: Luo fullname: Luo, Xiao-yi organization: College of Control Science and Engineering, Zhejiang University – sequence: 3 givenname: Zi-yang surname: Wang fullname: Wang, Zi-yang organization: College of Control Science and Engineering, Zhejiang University – sequence: 4 givenname: Jun orcidid: 0000-0003-1115-0824 surname: Liang fullname: Liang, Jun email: jliang@zju.edu.cn organization: College of Control Science and Engineering, Zhejiang University |
| BookMark | eNp1kE1LAzEQhoMoqLVH7wFvwtbJfmQ3RylVCwVB9LzMZmdLaputybZ-_HpjtyKInmYIz_smeU7ZoW0tMXYuYCRkIq5upo-TyUgoACHkATuJQWWRihM4_N5FkR6zofcLCIwUKlfFCdMPtHbkyXbYmdbyJaGzxs751iBH7mllIr9Zk9saTzX3HernMGsTNquJ46Zryeq2Jseb1nGzwjlxvUTvTWP0rvSMHTW49DTczwF7upk8ju-i2f3tdHw9i3SSqC5KBRaJzopUSYGZprwgpVWqQdakRA4a8wIQIJzGVVqlWSKFAMoxrWIpZZUM2GXf-4q2QTsvF-3G2XBj-bGo394qXVIMMUAOkAX4oofXrn3ZkO9-6DioyuNgqAhU1FPatd47asq1C19076WA8st7ufNe7r0HPvnFa9Ob7Rya5b-pUZ_yod3Oyf285e_AJ1ISlwM |
| CitedBy_id | crossref_primary_10_1049_ipr2_13213 crossref_primary_10_1109_JSEN_2024_3506937 crossref_primary_10_1016_j_jii_2022_100392 crossref_primary_10_1016_j_ecofro_2024_11_009 crossref_primary_10_1109_JSEN_2021_3092432 crossref_primary_10_1109_TIV_2022_3195635 crossref_primary_10_1088_1361_6501_ad5c8e crossref_primary_10_1631_FITEE_2000695 crossref_primary_10_1007_s10462_023_10662_6 crossref_primary_10_1177_01423312231197363 crossref_primary_10_1007_s00521_024_10539_x crossref_primary_10_1029_2024JH000566 crossref_primary_10_1016_j_engstruct_2025_120603 |
| Cites_doi | 10.1109/TNNLS.2018.2881143 10.1016/j.dsp.2018.06.004 10.1109/TPAMI.2013.50 10.1109/TIP.2015.2421443 10.1007/s11063-018-9828-2 10.1007/s11263-019-01176-2 10.1016/j.neucom.2018.05.117 10.1109/TCSVT.2018.2834480 10.1561/2200000006 10.1109/TPAMI.2012.193 10.1007/s00521-016-2790-x 10.1126/science.1127647 10.1117/1.JEI.27.5.051221 10.1016/j.tics.2007.09.004 10.1109/TIP.2017.2774041 10.1109/TSMC.1973.4309314 10.1016/j.neucom.2018.09.040 10.1109/ijcnn.2017.7965877 10.1109/acii.2013.90 10.1109/ijcnn.2016.7727620 10.1109/cvprw.2014.79 10.1109/acc.2016.7525420 10.1109/ijcnn.2013.6707028 |
| ClassificationCodes | TP391.9 |
| ContentType | Journal Article |
| Copyright | Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2020 Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2020. Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2020 – notice: Zhejiang University and Springer-Verlag GmbH Germany, part of Springer Nature 2020. – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | AAYXX CITATION 8FE 8FG ABJCF AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- L6V M7S P5Z P62 PHGZM PHGZT PKEHL PQEST PQGLB PQQKQ PQUKI PTHSS 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.1631/FITEE.1900116 |
| DatabaseName | CrossRef ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central Technology Collection ProQuest One ProQuest Central Korea ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection Computer Science Database (ProQuest) ProQuest Engineering Collection Engineering Database Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection Proquest Central Premium ProQuest One Academic (New) ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition Engineering Collection Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitle | CrossRef Computer Science Database ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection SciTech Premium Collection ProQuest One Community College ProQuest Central ProQuest One Applied & Life Sciences ProQuest Engineering Collection ProQuest Central Korea ProQuest Central (New) Engineering Collection Advanced Technologies & Aerospace Collection Engineering Database ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection Advanced Technologies & Aerospace Database ProQuest One Academic UKI Edition Materials Science & Engineering Collection ProQuest One Academic ProQuest One Academic (New) |
| DatabaseTitleList | Computer Science Database |
| Database_xml | – sequence: 1 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science |
| EISSN | 2095-9230 |
| EndPage | 1018 |
| ExternalDocumentID | zjdxxbc_e202007005 10_1631_FITEE_1900116 |
| GrantInformation_xml | – fundername: the National Natural Science Foundation of China funderid: (. U1664264 and U1509203) |
| GroupedDBID | -EM -SI -S~ 0R~ 2KG 4.4 406 5VR 96X AACDK AAHNG AAIAL AAJBT AAJKR AANZL AARHV AARTL AASML AATNV AATVU AAUYE AAXDM AAYIU AAYTO AAYZH AAZMS ABAKF ABDZT ABECU ABFTD ABFTV ABJCF ABJNI ABJOX ABKCH ABMQK ABQBU ABSXP ABTEG ABTHY ABTKH ABTMW ABXPI ACAOD ACBXY ACDTI ACGFS ACHSB ACIWK ACKNC ACMDZ ACMLO ACOKC ACPIV ACZOJ ADINQ ADKNI ADKPE ADRFC ADURQ ADYFF ADZKW AEBTG AEFQL AEGNC AEJHL AEJRE AEMSY AENEX AEOHA AESKC AETCA AEVLU AEXYK AFBBN AFKRA AFLOW AFQWF AFUIB AFZKB AGAYW AGDGC AGJBK AGMZJ AGQEE AGQMX AGRTI AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AILAN AITGF AJBLW AJRNO AJZVZ ALFXC ALMA_UNASSIGNED_HOLDINGS AMKLP AMXSW AMYLF ANMIH AOCGG ARAPS AXYYD BENPR BGLVJ BGNMA CAJEI CCEZO CCPQU CHBEP CUBFJ CW9 DDRTE DNIVK DPUIP EBLON EBS EIOEI EJD FA0 FERAY FIGPU FINBP FNLPD FRRFC FSGXE FYJPI GGCAI GGRSB HCIFZ IKXTQ IWAJR J-C JUIAU JZLTJ K7- KOV LLZTM M4Y M7S NPVJJ NQJWS NU0 O9J PT4 PTHSS Q-- R-I RLLFE ROL RSV S.. SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE TCJ TGT TSG U1G U5S UG4 UOJIU UTJUX UZXMN VFIZW Z7R Z7X Z7Z Z83 Z88 ZMTXR AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC AEZWR AFDZB AFFHD AFHIU AFOHR AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION PHGZM PHGZT PQGLB 8FE 8FG AZQEC DWQXO GNUQQ JQ2 L6V P62 PKEHL PQEST PQQKQ PQUKI 2B. 4A8 92I 93N PMFND PSX |
| ID | FETCH-LOGICAL-c339t-41a83c584961a5ce78e9c94c06de9170ca780a00e9c2b4b4536110e7a4b2666b3 |
| IEDL.DBID | M7S |
| ISICitedReferencesCount | 16 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000554736900004&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2095-9184 |
| IngestDate | Thu May 29 04:06:16 EDT 2025 Wed Nov 05 04:13:10 EST 2025 Tue Nov 18 20:41:50 EST 2025 Sat Nov 29 04:33:23 EST 2025 Fri Feb 21 02:35:19 EST 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 7 |
| Keywords | TP391.9 Neural network Autoencoder Semi-supervised learning Image classification |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c339t-41a83c584961a5ce78e9c94c06de9170ca780a00e9c2b4b4536110e7a4b2666b3 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0003-0887-627X 0000-0003-1115-0824 |
| PQID | 2918726198 |
| PQPubID | 2044401 |
| PageCount | 14 |
| ParticipantIDs | wanfang_journals_zjdxxbc_e202007005 proquest_journals_2918726198 crossref_primary_10_1631_FITEE_1900116 crossref_citationtrail_10_1631_FITEE_1900116 springer_journals_10_1631_FITEE_1900116 |
| PublicationCentury | 2000 |
| PublicationDate | 2020-07-01 |
| PublicationDateYYYYMMDD | 2020-07-01 |
| PublicationDate_xml | – month: 07 year: 2020 text: 2020-07-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Hangzhou |
| PublicationPlace_xml | – name: Hangzhou – name: Heidelberg |
| PublicationTitle | Frontiers of information technology & electronic engineering |
| PublicationTitleAbbrev | Front Inform Technol Electron Eng |
| PublicationTitle_FL | Frontiers of Information Technology & Electronic Engineering |
| PublicationYear | 2020 |
| Publisher | Zhejiang University Press Springer Nature B.V College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China |
| Publisher_xml | – name: Zhejiang University Press – name: Springer Nature B.V – name: College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China |
| References | Vincent, Larochelle, Lajoie (CR26) 2010; 11 Sun, Xue, Zhang (CR22) 2017; 30 Du, Zhang, Ji (CR5) 2018; 49 CR19 Gong, Lazebnik, Gordo (CR8) 2013; 35 CR16 CR14 Feng, Duarte (CR6) 2018; 312 Taherkhani, Cosma, Mcginnity (CR23) 2018; 322 CR30 Bianco, Buzzelli, Schettini (CR3) 2018; 27 Hinton (CR12) 2007; 11 Peng, He, Zhao (CR17) 2018; 27 He, Peng, Zhao (CR11) 2019; 127 Glorot, Bengio (CR7) 2010; 9 Rahmani, Almasganj, Ali (CR18) 2018; 82 Hinton, Salakhutdinov (CR13) 2006; 313 CR4 CR29 CR28 CR27 CR25 Tang, Li, Wang (CR24) 2015; 24 CR21 CR20 Bengio, Courville, Vincent (CR2) 2013; 35 Meng, Ding, Zhang (CR15) 2018; 30 Bengio (CR1) 2009; 2 Haralick, Shanmugam, Dinstein (CR9) 1973; SMC-3 He, Peng, Zhao (CR10) 2018; 29 S Bianco (1551_CR3) 2018; 27 YN Sun (1551_CR22) 2017; 30 Y Bengio (1551_CR2) 2013; 35 1551_CR25 1551_CR27 XT He (1551_CR11) 2019; 127 1551_CR29 YX Peng (1551_CR17) 2018; 27 1551_CR28 F Du (1551_CR5) 2018; 49 RM Haralick (1551_CR9) 1973; SMC-3 JH Tang (1551_CR24) 2015; 24 1551_CR21 YC Gong (1551_CR8) 2013; 35 1551_CR20 SW Feng (1551_CR6) 2018; 312 XT He (1551_CR10) 2018; 29 GE Hinton (1551_CR13) 2006; 313 Y Bengio (1551_CR1) 2009; 2 MH Rahmani (1551_CR18) 2018; 82 1551_CR14 1551_CR16 A Taherkhani (1551_CR23) 2018; 322 1551_CR19 1551_CR30 P Vincent (1551_CR26) 2010; 11 1551_CR4 LH Meng (1551_CR15) 2018; 30 GE Hinton (1551_CR12) 2007; 11 X Glorot (1551_CR7) 2010; 9 |
| References_xml | – volume: 30 start-page: 2295 issue: 8 year: 2017 end-page: 2309 ident: CR22 article-title: A particle swarm optimization-based flexible convolutional autoencoder for image classification publication-title: IEEE Trans Neur Netw Learn Syst doi: 10.1109/TNNLS.2018.2881143 – volume: 82 start-page: 54 issue: 5 year: 2018 end-page: 63 ident: CR18 article-title: Audiovisual feature fusion via deep neural networks for automatic speech recognition publication-title: Dig Signal Process doi: 10.1016/j.dsp.2018.06.004 – volume: 35 start-page: 1798 issue: 8 year: 2013 end-page: 1828 ident: CR2 article-title: Representation learning: a review and new perspectives publication-title: IEEE Trans Patt Anal Mach Intell doi: 10.1109/TPAMI.2013.50 – volume: 24 start-page: 2827 issue: 9 year: 2015 end-page: 2840 ident: CR24 article-title: Neighborhood discriminant hashing for large-scale image retrieval publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2015.2421443 – volume: 49 start-page: 507 issue: 2 year: 2018 end-page: 520 ident: CR5 article-title: Discriminative representation learning with supervised auto-encoder publication-title: Neur Process Lett doi: 10.1007/s11063-018-9828-2 – volume: 127 start-page: 1235 issue: 9 year: 2019 end-page: 1255 ident: CR11 article-title: Which and how many regions to gaze: focus discriminative regions for finegrained visual categorization publication-title: Int J Comput Vis doi: 10.1007/s11263-019-01176-2 – ident: CR4 – ident: CR14 – ident: CR16 – volume: 312 start-page: 310 year: 2018 end-page: 323 ident: CR6 article-title: Graph autoencoder-based unsupervised feature selection with broad and local data structure preservation publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.05.117 – ident: CR30 – volume: 29 start-page: 1394 issue: 5 year: 2018 end-page: 1407 ident: CR10 article-title: Fast fine-grained image classification via weakly supervised discriminative localization publication-title: IEEE Trans Circ Syst Video Technol doi: 10.1109/TCSVT.2018.2834480 – volume: 2 start-page: 1 issue: 1 year: 2009 end-page: 127 ident: CR1 article-title: Learning deep architectures for AI publication-title: Found Trends Mach Learn doi: 10.1561/2200000006 – ident: CR29 – volume: 35 start-page: 2916 issue: 12 year: 2013 end-page: 2929 ident: CR8 article-title: Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval publication-title: IEEE Trans Patt Anal Mach Intell doi: 10.1109/TPAMI.2012.193 – volume: 30 start-page: 2083 issue: 7 year: 2018 end-page: 2100 ident: CR15 article-title: Research of stacked denoising sparse autoencoder publication-title: Neur Comput Appl doi: 10.1007/s00521-016-2790-x – volume: 313 start-page: 504 issue: 5786 year: 2006 end-page: 507 ident: CR13 article-title: Reducing the dimensionality of data with neural networks publication-title: Science doi: 10.1126/science.1127647 – ident: CR25 – ident: CR27 – volume: 9 start-page: 249 year: 2010 end-page: 256 ident: CR7 article-title: Understanding the difficulty of training deep feedforward neural networks publication-title: J Mach Learn Res – volume: 27 start-page: 051221 issue: 5 year: 2018 ident: CR3 article-title: Multiscale fully convolutional network for image saliency publication-title: J Electron Imag doi: 10.1117/1.JEI.27.5.051221 – ident: CR21 – ident: CR19 – volume: 11 start-page: 428 issue: 10 year: 2007 end-page: 434 ident: CR12 article-title: Learning multiple layers of representation publication-title: Trends Cogn Sci doi: 10.1016/j.tics.2007.09.004 – volume: 27 start-page: 1487 issue: 3 year: 2018 end-page: 1500 ident: CR17 article-title: Object-part attention model for fine-grained image classification publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2017.2774041 – volume: 11 start-page: 3371 issue: 12 year: 2010 end-page: 3408 ident: CR26 article-title: Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion publication-title: J Mach Learn Res – volume: SMC-3 start-page: 610 issue: 6 year: 1973 end-page: 621 ident: CR9 article-title: Textural features for image classification publication-title: IEEE Trans Syst Man Cybern doi: 10.1109/TSMC.1973.4309314 – volume: 322 start-page: 22 year: 2018 end-page: 37 ident: CR23 article-title: Deep-FS: a feature selection algorithm for deep Boltzmann machines publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.09.040 – ident: CR28 – ident: CR20 – volume: 11 start-page: 428 issue: 10 year: 2007 ident: 1551_CR12 publication-title: Trends Cogn Sci doi: 10.1016/j.tics.2007.09.004 – ident: 1551_CR25 – volume: 322 start-page: 22 year: 2018 ident: 1551_CR23 publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.09.040 – ident: 1551_CR29 – ident: 1551_CR19 – volume: 29 start-page: 1394 issue: 5 year: 2018 ident: 1551_CR10 publication-title: IEEE Trans Circ Syst Video Technol doi: 10.1109/TCSVT.2018.2834480 – ident: 1551_CR16 doi: 10.1109/ijcnn.2017.7965877 – ident: 1551_CR21 – volume: 27 start-page: 051221 issue: 5 year: 2018 ident: 1551_CR3 publication-title: J Electron Imag doi: 10.1117/1.JEI.27.5.051221 – ident: 1551_CR4 doi: 10.1109/acii.2013.90 – volume: 127 start-page: 1235 issue: 9 year: 2019 ident: 1551_CR11 publication-title: Int J Comput Vis doi: 10.1007/s11263-019-01176-2 – volume: 82 start-page: 54 issue: 5 year: 2018 ident: 1551_CR18 publication-title: Dig Signal Process doi: 10.1016/j.dsp.2018.06.004 – ident: 1551_CR14 – volume: 30 start-page: 2295 issue: 8 year: 2017 ident: 1551_CR22 publication-title: IEEE Trans Neur Netw Learn Syst doi: 10.1109/TNNLS.2018.2881143 – ident: 1551_CR20 doi: 10.1109/ijcnn.2016.7727620 – volume: 11 start-page: 3371 issue: 12 year: 2010 ident: 1551_CR26 publication-title: J Mach Learn Res – volume: 9 start-page: 249 year: 2010 ident: 1551_CR7 publication-title: J Mach Learn Res – volume: 313 start-page: 504 issue: 5786 year: 2006 ident: 1551_CR13 publication-title: Science doi: 10.1126/science.1127647 – ident: 1551_CR27 doi: 10.1109/cvprw.2014.79 – volume: 35 start-page: 2916 issue: 12 year: 2013 ident: 1551_CR8 publication-title: IEEE Trans Patt Anal Mach Intell doi: 10.1109/TPAMI.2012.193 – ident: 1551_CR30 doi: 10.1109/acc.2016.7525420 – ident: 1551_CR28 doi: 10.1109/ijcnn.2013.6707028 – volume: 27 start-page: 1487 issue: 3 year: 2018 ident: 1551_CR17 publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2017.2774041 – volume: 30 start-page: 2083 issue: 7 year: 2018 ident: 1551_CR15 publication-title: Neur Comput Appl doi: 10.1007/s00521-016-2790-x – volume: 35 start-page: 1798 issue: 8 year: 2013 ident: 1551_CR2 publication-title: IEEE Trans Patt Anal Mach Intell doi: 10.1109/TPAMI.2013.50 – volume: 2 start-page: 1 issue: 1 year: 2009 ident: 1551_CR1 publication-title: Found Trends Mach Learn doi: 10.1561/2200000006 – volume: 24 start-page: 2827 issue: 9 year: 2015 ident: 1551_CR24 publication-title: IEEE Trans Image Process doi: 10.1109/TIP.2015.2421443 – volume: SMC-3 start-page: 610 issue: 6 year: 1973 ident: 1551_CR9 publication-title: IEEE Trans Syst Man Cybern doi: 10.1109/TSMC.1973.4309314 – volume: 312 start-page: 310 year: 2018 ident: 1551_CR6 publication-title: Neurocomputing doi: 10.1016/j.neucom.2018.05.117 – volume: 49 start-page: 507 issue: 2 year: 2018 ident: 1551_CR5 publication-title: Neur Process Lett doi: 10.1007/s11063-018-9828-2 |
| SSID | ssj0001619798 |
| Score | 2.2532625 |
| Snippet | Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related to the... TP391.9; Image classification is an important application of deep learning. In a typical classification task, the classification accuracy is strongly related... |
| SourceID | wanfang proquest crossref springer |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 1005 |
| SubjectTerms | Classification Communications Engineering Computer Hardware Computer Science Computer Systems Organization and Communication Networks Datasets Deep learning Electrical Engineering Electronics and Microelectronics Feature extraction Image classification Instrumentation Machine learning Networks Neural networks Object recognition Traffic signs |
| SummonAdditionalLinks | – databaseName: SpringerLINK Contemporary 1997-Present dbid: RSV link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8QwEB509aAH3-L6IqDoxWraZJvkKOLiQUR84a2kaXZZ0Sp2VxZ_vZNs6ioi6KWHNp2WzOubTDIDsIsWTsdWsYh3UukunQi9IncMoUoYZoTPmN6di4sLeX-vLifgqD4L43e71ylJb6mdWqcsPmqjKp8eov9yqYNJmEJPJ12vhqvru_GiCoYDwve_TajvQSh5qKv5g8J3PzQGl5_5UH-Kp-zosvvF4bTn__2rCzAXsCU5HgnDIkzYcgnm674NJKjxEsx-KUK4DObKb4YNZ5BKEvpIdMlbTxNNKvvUi6rBi7MplS0IoklU_IIUDngiOaIH_WdXDbPATyACJr0nNFHEOFTutiF5oitw2z69OTmLQuuFyDCm-hGPtWQGwYlKY90yVkirjOKGpoXFAI8aLSTVlOLdJOc5b7EUcYQVmufo8dOcrUKjfC7tGpAWLRDVUQSSec5ZIVQSd2KptWZMGJOoJhzUjMhMqEvu2mM8Zi4-wenM_HRmYTqbsPc5_GVUkOO3gZs1V7Ogl1WWoEgIFzTKJuzXvBs__oXQThCE8cD3h2I4zE1mE-oWe9GUrf-Z3gbMuLdGe343odF_HdgtmDZv_V71uu0F-gNgcvAc priority: 102 providerName: Springer Nature |
| Title | Representation learning via a semi-supervised stacked distance autoencoder for image classification |
| URI | https://link.springer.com/article/10.1631/FITEE.1900116 https://www.proquest.com/docview/2918726198 https://d.wanfangdata.com.cn/periodical/zjdxxbc-e202007005 |
| Volume | 21 |
| WOSCitedRecordID | wos000554736900004&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: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 2095-9230 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0001619798 issn: 2095-9184 databaseCode: K7- dateStart: 20100101 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: Engineering Database customDbUrl: eissn: 2095-9230 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0001619798 issn: 2095-9184 databaseCode: M7S dateStart: 20100101 isFulltext: true titleUrlDefault: http://search.proquest.com providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest advanced technologies & aerospace journals customDbUrl: eissn: 2095-9230 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0001619798 issn: 2095-9184 databaseCode: P5Z dateStart: 20100101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2095-9230 dateEnd: 20241209 omitProxy: false ssIdentifier: ssj0001619798 issn: 2095-9184 databaseCode: BENPR dateStart: 20100101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVAVX databaseName: SpringerLink Journals customDbUrl: eissn: 2095-9230 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0001619798 issn: 2095-9184 databaseCode: RSV dateStart: 20150101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3fT9swED4N2MN4gLEfosAqS0zbyzKc2I3tJ8SmVpM2VVXZENpL5Ngu6gRpaVqE-Os5uy5hD-xlL35ITk6k73L35e58B_AeLZxOnWIJH-XSL6MEvSL3gFAlDDMiZEzPfoh-X56fq0EMuNWxrHJlE4OhthPjY-RHmUql8HRfHk-vEz81ymdX4wiNNdjwXRLSULp32sRYUFyEcbgZDSMJJY9tNnOWHvXQNnQ_o0P0uYi_3VLDNR_So-FQTzXS1cUj_9Pb_t83fwlbkXmSk6Wq7MAzV72CzUf9CF-DGYa62HgcqSJxpMQFuRlrokntrsZJvZh681I7S5BYog2wxHoOispD9GI-8Y0xrZsRJMNkfIXWihhP0H1FUtj0DfzqdX9-_ZbEKQyJYUzNE55qyQzyFJWnumOckE4ZxQ3NrcN_PWq0kFRTilezkpe8w3KkFE5oXqLzz0v2FtarSeV2gXSoRYJHkVOWJWdWqCwdpVJrzZgwJlMt-LQCoTCxRbmflHFZ-F8VxKwImBURsxZ8eBCfLntzPCV4sEKmiJ9oXTSwtODjCuXm9hMbHUYlaATv_tjb29IULqM-7otWbe_fj9uHF150WfN7AOvz2cK9g-fmZj6uZ23Y-NLtD4ZtWPsuknbQZ1wHnd-4Dk_P7gGdo_tH |
| linkProvider | ProQuest |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VggQ98EZsKWCJ16WhTuyN7QNCCLpqtcsKoYJ6C47trRbR7Haz2xZ-FL-RsddpyqHceuCSQ-I4D3_zzYw9ngF4jgynU6dYwke59IdRglqR-wGhShhmRFgx_ToQw6Hc31efVuB3sxfGh1U2nBiI2k6MnyPfylQqhTf35dvpUeKrRvnV1aaExhIWfffzBF22-s3uBxzfF1nW2957v5PEqgKJYUzNE55qyQzqXZWnumuckE4ZxQ3NrUPfhRotJNWU4tms5CXvshxVpBOal6jM8pJhv1fgKmdSeLnqi6Sd08HXE6H8bkZDCUTJY1rPnKVbPeSi7deogP3ax99qsLVtz5ZjwyaiaqSrg3P6rnfrf_tTt-FmtKzJu6Uo3IEVV92FtXP5Fu-B-RzifuN2q4rEkhkH5HisiSa1Oxwn9WLq6bN2lqDhjBxnifU2NgoH0Yv5xCf-tG5G0Ngn40NkY2K8A-IjrkKn9-HLpXzlA1itJpV7CKRLLRqwFG3msuTMCpWlo1RqrRkTxmSqA5vNoBcmpmD3lUB-FN4VQ4wUASNFxEgHXp41ny5zj1zUcKNBQhEpqC5aGHTgVYOq9vIFHT2LoGsb_vpuT09LU7iM-nltZO31fz_uKVzf2fs4KAa7w_4juOFvW8Y3b8DqfLZwj-GaOZ6P69mTID0Evl02CP8A6ZVRbw |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV3dS9xAEB_8KNI-VOsHvVbrQou-GG-T3ctm6VOpHhXlkFbFt7DZ3ciVGg-TE_Gvd3Zv41lEEHzJQ7JMws7XbzKzMwDf0MKp2EoW8TLN3KWM0CtyxxAqhWZa-Izp2ZEYDLLzc3k8A9_bszC-2r1NSU7ONLguTVXTHZnSq3jK4m4f1Xp_F32ZSyPMwjx3NfQuVP9zNv3BgqGB8LNwE-rnEWY89Nh8QuF_nzQFmg-5UX-ipypVdfHI-fQXX_XZS_A-YE7yYyIkH2DGVsuw2M5zIEG9l-Hdo-aEK6B_-yLZcDapImG-xAW5GSqiSG0vh1E9HjlbU1tDEGWiQTDEOECK5IgaN1euS6bBVyAyJsNLNF1EO7TuypM80VU47e-f_PwVhZEMkWZMNhGPVcY0ghaZxqqnrcis1JJrmhqLgR_VSmRUUYp3k4IXvMdSxBdWKF4gEkgLtgZz1VVlPwLpUYNojyLALArOjJBJXMaZUooxoXUiO7DTMiXXoV-5G5vxL3dxC25n7rczD9vZga2H5aNJo47nFq63HM6DvtZ5guIhXDCZdWC75eP08TOEvgahmC68-2tubwud24S6n8Bo4j69mN4mLBzv9fOjg8HhZ3jrCEzKgtdhrrke2w14o2-aYX39xcv5Pbx4--Q |
| 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=Representation+learning+via+a+semi-supervised+stacked+distance+autoencoder+for+image+classification&rft.jtitle=Frontiers+of+information+technology+%26+electronic+engineering&rft.au=Hou%2C+Liang&rft.au=Luo%2C+Xiao-yi&rft.au=Wang%2C+Zi-yang&rft.au=Liang%2C+Jun&rft.date=2020-07-01&rft.pub=Springer+Nature+B.V&rft.issn=2095-9184&rft.eissn=2095-9230&rft.volume=21&rft.issue=7&rft.spage=1005&rft.epage=1018&rft_id=info:doi/10.1631%2FFITEE.1900116 |
| thumbnail_s | http://cvtisr.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fzjdxxbc-e%2Fzjdxxbc-e.jpg |