Training Lightweight Deep Convolutional Neural Networks Using Bag-of-Features Pooling
Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs are complex models that require the use of powerful hardware, both for training and deploying them. To this end, a quantization-based poolin...
Uloženo v:
| Vydáno v: | IEEE transaction on neural networks and learning systems Ročník 30; číslo 6; s. 1705 - 1715 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
United States
IEEE
01.06.2019
The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Témata: | |
| ISSN: | 2162-237X, 2162-2388, 2162-2388 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs are complex models that require the use of powerful hardware, both for training and deploying them. To this end, a quantization-based pooling method is proposed in this paper. The proposed method is inspired from the bag-of-features model and can be used for learning more lightweight deep neural networks. Trainable radial basis function neurons are used to quantize the activations of the final convolutional layer, reducing the number of parameters in the network and allowing for natively classifying images of various sizes. The proposed method employs differentiable quantization and aggregation layers leading to an end-to-end trainable CNN architecture. Furthermore, a fast linear variant of the proposed method is introduced and discussed, providing new insight for understanding convolutional neural architectures. The ability of the proposed method to reduce the size of CNNs and increase the performance over other competitive methods is demonstrated using seven data sets and three different learning tasks (classification, regression, and retrieval). |
|---|---|
| AbstractList | Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs are complex models that require the use of powerful hardware, both for training and deploying them. To this end, a quantization-based pooling method is proposed in this paper. The proposed method is inspired from the bag-of-features model and can be used for learning more lightweight deep neural networks. Trainable radial basis function neurons are used to quantize the activations of the final convolutional layer, reducing the number of parameters in the network and allowing for natively classifying images of various sizes. The proposed method employs differentiable quantization and aggregation layers leading to an end-to-end trainable CNN architecture. Furthermore, a fast linear variant of the proposed method is introduced and discussed, providing new insight for understanding convolutional neural architectures. The ability of the proposed method to reduce the size of CNNs and increase the performance over other competitive methods is demonstrated using seven data sets and three different learning tasks (classification, regression, and retrieval). Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs are complex models that require the use of powerful hardware, both for training and deploying them. To this end, a quantization-based pooling method is proposed in this paper. The proposed method is inspired from the bag-of-features model and can be used for learning more lightweight deep neural networks. Trainable radial basis function neurons are used to quantize the activations of the final convolutional layer, reducing the number of parameters in the network and allowing for natively classifying images of various sizes. The proposed method employs differentiable quantization and aggregation layers leading to an end-to-end trainable CNN architecture. Furthermore, a fast linear variant of the proposed method is introduced and discussed, providing new insight for understanding convolutional neural architectures. The ability of the proposed method to reduce the size of CNNs and increase the performance over other competitive methods is demonstrated using seven data sets and three different learning tasks (classification, regression, and retrieval).Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs are complex models that require the use of powerful hardware, both for training and deploying them. To this end, a quantization-based pooling method is proposed in this paper. The proposed method is inspired from the bag-of-features model and can be used for learning more lightweight deep neural networks. Trainable radial basis function neurons are used to quantize the activations of the final convolutional layer, reducing the number of parameters in the network and allowing for natively classifying images of various sizes. The proposed method employs differentiable quantization and aggregation layers leading to an end-to-end trainable CNN architecture. Furthermore, a fast linear variant of the proposed method is introduced and discussed, providing new insight for understanding convolutional neural architectures. The ability of the proposed method to reduce the size of CNNs and increase the performance over other competitive methods is demonstrated using seven data sets and three different learning tasks (classification, regression, and retrieval). |
| Author | Tefas, Anastasios Passalis, Nikolaos |
| Author_xml | – sequence: 1 givenname: Nikolaos orcidid: 0000-0003-1177-9139 surname: Passalis fullname: Passalis, Nikolaos email: passalis@csd.auth.gr organization: Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece – sequence: 2 givenname: Anastasios surname: Tefas fullname: Tefas, Anastasios email: tefas@aiia.csd.auth.gr organization: Department of Informatics, Aristotle University of Thessaloniki, Thessaloniki, Greece |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30369453$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kctOwzAQRS0E4v0DIKFIbNik-BE79hLKU6oKEkViFznJuATSuNgJFX-PQ0sXLPDCY43OHWvu3UObjW0AoSOCB4RgdT4Zj0dPA4qJHFCZUqX4BtqlRNCYMik31-_0ZQcdev-GwxGYi0Rtox2GmVAJZ7voeeJ01VTNNBpV09d2Af0dXQHMo6FtPm3dtZVtdB2NoXM_pV1Y9-6jZ9-LLvU0tia-Ad12Dnz0aG0d-gdoy-jaw-Gq7qPJzfVkeBePHm7vhxejuEhI2saq5CVWhgtTcqmB4MQkCrOcGJbQguaCp5QRkxQ6T41ICy3KVJYm5ySHnGK2j86WY-fOfnTg22xW-QLqWjdgO59RQoUiVHER0NM_6JvtXFgsUJThlEjGVKBOVlSXz6DM5q6aafeV_foVALoECme9d2DWCMFZn0v2k0vW55Ktcgki-UdUVK3ufW2D-fX_0uOltAKA9V-SYyFowr4BKHKaMw |
| CODEN | ITNNAL |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2020_3042439 crossref_primary_10_1109_TITS_2020_3015530 crossref_primary_10_1109_TNNLS_2022_3190139 crossref_primary_10_1016_j_ijleo_2021_166726 crossref_primary_10_1016_j_optmat_2021_111292 crossref_primary_10_1016_j_asoc_2024_111791 crossref_primary_10_1109_JESTPE_2022_3184754 crossref_primary_10_1109_TIM_2021_3054673 crossref_primary_10_1080_23248378_2020_1795942 crossref_primary_10_1016_j_asoc_2022_109197 crossref_primary_10_1109_TBCAS_2021_3090995 crossref_primary_10_1109_TGRS_2019_2961681 crossref_primary_10_1109_TNNLS_2020_3029613 crossref_primary_10_1109_ACCESS_2024_3475380 crossref_primary_10_20965_jaciii_2023_p0165 crossref_primary_10_1109_JSTARS_2022_3233125 crossref_primary_10_3390_electronics10030255 crossref_primary_10_1109_TVT_2019_2937076 crossref_primary_10_20965_jaciii_2024_p0231 crossref_primary_10_1007_s11063_025_11741_1 crossref_primary_10_1016_j_engappai_2024_108935 crossref_primary_10_1109_TII_2021_3067321 crossref_primary_10_1109_TVT_2023_3244560 crossref_primary_10_1109_TCYB_2022_3206064 crossref_primary_10_1088_1742_6596_1550_3_032103 crossref_primary_10_1007_s00521_019_04330_6 crossref_primary_10_1016_j_sysarc_2022_102584 crossref_primary_10_1016_j_micpro_2021_104080 crossref_primary_10_1016_j_neucom_2024_128357 crossref_primary_10_1002_itl2_246 crossref_primary_10_1109_TCYB_2021_3060176 crossref_primary_10_1109_TNNLS_2020_2984665 crossref_primary_10_1007_s10489_022_03774_z |
| Cites_doi | 10.1016/j.cviu.2016.10.014 10.1109/TNNLS.2014.2361052 10.1109/TNNLS.2017.2740224 10.1109/TPAMI.2008.138 10.1109/CVPR.2017.243 10.1109/TNNLS.2016.2582924 10.1109/CVPR.2016.41 10.1109/TPAMI.2009.132 10.1109/ICME.2018.8486586 10.1109/ICCV.2017.469 10.1109/CVPR.2016.227 10.1109/5.726791 10.1109/CVPR.2015.7299085 10.1109/ICCV.2017.614 10.18653/v1/D16-1044 10.1109/ICCV.2015.170 10.1007/s11263-015-0816-y 10.1109/TPAMI.2017.2666812 10.1109/TNNLS.2015.2508025 10.1109/CVPR.2009.5206537 10.1109/TNNLS.2017.2705222 10.1109/TNNLS.2017.2774288 10.1109/TSMC.2017.2680404 10.1109/TPAMI.2015.2389824 10.23919/EUSIPCO.2017.8081171 10.1109/ICCV.1999.790410 10.1016/j.patcog.2016.11.014 10.1109/ICCVW.2011.6130513 10.1109/CVPRW.2015.7301269 10.1145/1646396.1646452 10.1007/978-3-642-53842-1_8 10.1109/ICCV.2003.1238663 10.1017/CBO9780511809071 10.1007/978-3-642-15561-1_12 10.1109/CVPR.2006.68 10.1109/CVPR.2014.222 10.1109/TPAMI.2016.2572683 10.1007/978-3-540-88682-2_24 10.1109/TNNLS.2017.2740318 10.1109/CVPR.2015.7298947 10.1145/2911996.2912061 |
| ContentType | Journal Article |
| Copyright | Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| Copyright_xml | – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019 |
| DBID | 97E RIA RIE AAYXX CITATION NPM 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| DOI | 10.1109/TNNLS.2018.2872995 |
| DatabaseName | IEEE Xplore (IEEE) IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef PubMed Aluminium Industry Abstracts Biotechnology Research Abstracts Calcium & Calcified Tissue Abstracts Ceramic Abstracts Chemoreception Abstracts Computer and Information Systems Abstracts Corrosion Abstracts Electronics & Communications Abstracts Engineered Materials Abstracts Materials Business File Mechanical & Transportation Engineering Abstracts Neurosciences Abstracts Solid State and Superconductivity Abstracts METADEX Technology Research Database ANTE: Abstracts in New Technology & Engineering Engineering Research Database Aerospace Database Materials Research Database ProQuest Computer Science Collection Civil Engineering Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional Biotechnology and BioEngineering Abstracts MEDLINE - Academic |
| DatabaseTitle | CrossRef PubMed Materials Research Database Technology Research Database Computer and Information Systems Abstracts – Academic Mechanical & Transportation Engineering Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Materials Business File Aerospace Database Engineered Materials Abstracts Biotechnology Research Abstracts Chemoreception Abstracts Advanced Technologies Database with Aerospace ANTE: Abstracts in New Technology & Engineering Civil Engineering Abstracts Aluminium Industry Abstracts Electronics & Communications Abstracts Ceramic Abstracts Neurosciences Abstracts METADEX Biotechnology and BioEngineering Abstracts Computer and Information Systems Abstracts Professional Solid State and Superconductivity Abstracts Engineering Research Database Calcium & Calcified Tissue Abstracts Corrosion Abstracts MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic PubMed Materials Research Database |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2162-2388 |
| EndPage | 1715 |
| ExternalDocumentID | 30369453 10_1109_TNNLS_2018_2872995 8506624 |
| Genre | orig-research Research Support, Non-U.S. Gov't Journal Article |
| GrantInformation_xml | – fundername: Horizon 2020 Framework Programme grantid: 731667 funderid: 10.13039/100010661 |
| GroupedDBID | 0R~ 4.4 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABQJQ ABVLG ACIWK ACPRK AENEX AFRAH AGQYO AGSQL AHBIQ AKJIK AKQYR ALMA_UNASSIGNED_HOLDINGS ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ EBS EJD IFIPE IPLJI JAVBF M43 MS~ O9- OCL PQQKQ RIA RIE RNS AAYXX CITATION NPM RIG 7QF 7QO 7QP 7QQ 7QR 7SC 7SE 7SP 7SR 7TA 7TB 7TK 7U5 8BQ 8FD F28 FR3 H8D JG9 JQ2 KR7 L7M L~C L~D P64 7X8 |
| ID | FETCH-LOGICAL-c417t-9d5d09f56fd58ae104f4903b1f342c2b657231f4cab7f67ca6d78dfb51beb203 |
| IEDL.DBID | RIE |
| ISICitedReferencesCount | 45 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000469335200009&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2162-237X 2162-2388 |
| IngestDate | Sun Sep 28 01:05:41 EDT 2025 Sun Jun 29 13:20:31 EDT 2025 Wed Feb 19 02:33:20 EST 2025 Sat Nov 29 01:40:01 EST 2025 Tue Nov 18 21:24:08 EST 2025 Wed Aug 27 02:46:56 EDT 2025 |
| IsPeerReviewed | false |
| IsScholarly | true |
| Issue | 6 |
| 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-c417t-9d5d09f56fd58ae104f4903b1f342c2b657231f4cab7f67ca6d78dfb51beb203 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 |
| ORCID | 0000-0003-1177-9139 |
| PMID | 30369453 |
| PQID | 2230718339 |
| PQPubID | 85436 |
| PageCount | 11 |
| ParticipantIDs | crossref_citationtrail_10_1109_TNNLS_2018_2872995 pubmed_primary_30369453 ieee_primary_8506624 crossref_primary_10_1109_TNNLS_2018_2872995 proquest_miscellaneous_2126912956 proquest_journals_2230718339 |
| PublicationCentury | 2000 |
| PublicationDate | 2019-06-01 |
| PublicationDateYYYYMMDD | 2019-06-01 |
| PublicationDate_xml | – month: 06 year: 2019 text: 2019-06-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States – name: Piscataway |
| PublicationTitle | IEEE transaction on neural networks and learning systems |
| PublicationTitleAbbrev | TNNLS |
| PublicationTitleAlternate | IEEE Trans Neural Netw Learn Syst |
| PublicationYear | 2019 |
| 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 | ref57 ref13 clevert (ref49) 2015 li (ref61) 2016 ref56 ref59 ref52 ref55 ref54 ref17 ref19 ref18 mairal (ref25) 2009 arandjelovi? (ref37) 2016 howard (ref30) 2017 ref46 ref45 simonyan (ref10) 2014 ref48 ref47 ref42 ref41 ref44 ref43 wang (ref64) 2016 ref8 shi (ref4) 2018; 29 ref9 ref3 zhou (ref53) 2014 zagoruyko (ref11) 2016 ref6 ref5 chen (ref32) 2015 chen (ref1) 2018; 29 ref40 krizhevsky (ref58) 2009 ref34 ref31 wu (ref16) 2015 ref33 ref2 ref39 han (ref15) 2015 ref38 kingma (ref50) 2014 denil (ref14) 2013 haykin (ref12) 2009; 3 ref24 ref23 ref26 saxe (ref51) 2014 ref20 ref63 ref22 ref21 gong (ref29) 2014 ref28 ref27 he (ref7) 2015 ref60 malinowski (ref35) 2013 ref62 lin (ref36) 2014 |
| References_xml | – ident: ref45 doi: 10.1016/j.cviu.2016.10.014 – year: 2017 ident: ref30 publication-title: Mobilenets Efficient convolutional neural networks for mobile vision applications – ident: ref28 doi: 10.1109/TNNLS.2014.2361052 – ident: ref27 doi: 10.1109/TNNLS.2017.2740224 – ident: ref41 doi: 10.1109/TPAMI.2008.138 – year: 2015 ident: ref32 publication-title: Convolutional neural network – start-page: 1 year: 2014 ident: ref51 article-title: Exact solutions to the nonlinear dynamics of learning in deep linear neural network publication-title: Proc Int Conf Learn Represent – start-page: 2148 year: 2013 ident: ref14 article-title: Predicting parameters in deep learning publication-title: Proc Adv Neural Inf Process Syst – ident: ref60 doi: 10.1109/CVPR.2017.243 – year: 2014 ident: ref29 publication-title: Compressing deep convolutional networks using vector quantization – ident: ref24 doi: 10.1109/TNNLS.2016.2582924 – ident: ref40 doi: 10.1109/CVPR.2016.41 – start-page: 1033 year: 2009 ident: ref25 article-title: Supervised dictionary learning publication-title: Proc Adv Neural Inf Process Syst – ident: ref48 doi: 10.1109/TPAMI.2009.132 – start-page: 5297 year: 2016 ident: ref37 article-title: NetVLAD: CNN architecture for weakly supervised place recognition publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref23 doi: 10.1109/ICME.2018.8486586 – ident: ref33 doi: 10.1109/ICCV.2017.469 – ident: ref6 doi: 10.1109/CVPR.2016.227 – ident: ref9 doi: 10.1109/5.726791 – ident: ref34 doi: 10.1109/CVPR.2015.7299085 – ident: ref21 doi: 10.1109/ICCV.2017.614 – volume: 3 year: 2009 ident: ref12 publication-title: Neural Networks and Learning Machines – ident: ref39 doi: 10.18653/v1/D16-1044 – ident: ref38 doi: 10.1109/ICCV.2015.170 – year: 2015 ident: ref16 publication-title: Quantized convolutional neural networks for mobile devices – ident: ref2 doi: 10.1007/s11263-015-0816-y – year: 2016 ident: ref11 publication-title: Wide residual networks – ident: ref5 doi: 10.1109/TPAMI.2017.2666812 – start-page: 487 year: 2014 ident: ref53 article-title: Learning deep features for scene recognition using places database publication-title: Proc Adv Neural Inf Process Syst – ident: ref26 doi: 10.1109/TNNLS.2015.2508025 – start-page: 1 year: 2013 ident: ref35 article-title: Learnable pooling regions for image classification publication-title: Proc Int Conf Learn Represent – ident: ref54 doi: 10.1109/CVPR.2009.5206537 – ident: ref3 doi: 10.1109/TNNLS.2017.2705222 – year: 2016 ident: ref64 publication-title: A Survey on Learning to Hash – ident: ref31 doi: 10.1109/TNNLS.2017.2774288 – ident: ref46 doi: 10.1109/TSMC.2017.2680404 – year: 2014 ident: ref50 publication-title: Adam A method for stochastic optimization – ident: ref52 doi: 10.1109/5.726791 – ident: ref8 doi: 10.1109/TPAMI.2015.2389824 – ident: ref22 doi: 10.23919/EUSIPCO.2017.8081171 – year: 2014 ident: ref10 publication-title: Very Deep Convolutional Networks for Large-scale Image Recognition – ident: ref19 doi: 10.1109/ICCV.1999.790410 – volume: 29 start-page: 2872 year: 2018 ident: ref4 article-title: Improving CNN performance accuracies with min-max objective publication-title: IEEE Trans Neural Netw Learn Syst – ident: ref44 doi: 10.1016/j.patcog.2016.11.014 – year: 2015 ident: ref7 publication-title: Deep residual learning for image recognition – ident: ref55 doi: 10.1109/ICCVW.2011.6130513 – ident: ref62 doi: 10.1109/CVPRW.2015.7301269 – ident: ref59 doi: 10.1145/1646396.1646452 – year: 2009 ident: ref58 article-title: Learning multiple layers of features from tiny images – year: 2015 ident: ref49 publication-title: Fast and accurate deep network learning by exponential linear units (ELUs) – ident: ref43 doi: 10.1007/978-3-642-53842-1_8 – ident: ref18 doi: 10.1109/ICCV.2003.1238663 – ident: ref57 doi: 10.1017/CBO9780511809071 – ident: ref42 doi: 10.1007/978-3-642-15561-1_12 – year: 2015 ident: ref15 publication-title: Deep compression Compressing deep neural networks with pruning trained quantization and huffman coding – ident: ref17 doi: 10.1109/CVPR.2006.68 – start-page: 1 year: 2014 ident: ref36 article-title: Network in network publication-title: Proc Int Conf Learn Represent – ident: ref13 doi: 10.1109/CVPR.2014.222 – start-page: 1711 year: 2016 ident: ref61 article-title: Feature learning based deep supervised hashing with pairwise labels publication-title: Proc 25th Int Conf Artif Intell – ident: ref20 doi: 10.1109/TPAMI.2016.2572683 – ident: ref56 doi: 10.1007/978-3-540-88682-2_24 – volume: 29 start-page: 3938 year: 2018 ident: ref1 article-title: Deep manifold learning combined with convolutional neural networks for action recognition publication-title: IEEE Trans Neural Netw Learn Syst doi: 10.1109/TNNLS.2017.2740318 – ident: ref63 doi: 10.1109/CVPR.2015.7298947 – ident: ref47 doi: 10.1145/2911996.2912061 |
| SSID | ssj0000605649 |
| Score | 2.4788704 |
| Snippet | Convolutional neural networks (CNNs) are predominantly used for several challenging computer vision tasks achieving state-of-the-art performance. However, CNNs... |
| SourceID | proquest pubmed crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 1705 |
| SubjectTerms | Artificial neural networks Backpropagation algorithms Bag-of-features (BoF) Basis functions Computational modeling Computer architecture Computer vision convolutional neural networks (CNNs) Feature extraction Image classification Learning Lightweight lightweight neural networks Measurement Neural networks pooling operators Quantization (signal) Radial basis function Task analysis Task complexity Training |
| Title | Training Lightweight Deep Convolutional Neural Networks Using Bag-of-Features Pooling |
| URI | https://ieeexplore.ieee.org/document/8506624 https://www.ncbi.nlm.nih.gov/pubmed/30369453 https://www.proquest.com/docview/2230718339 https://www.proquest.com/docview/2126912956 |
| Volume | 30 |
| WOSCitedRecordID | wos000469335200009&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: 2162-2388 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000605649 issn: 2162-237X databaseCode: RIE dateStart: 20120101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1La9wwEB6S0EMvTZP04TQJKvTWKrFlPY9t2pDDsgS6hb0ZW49QCHbI7qZ_PyNZayi0hZ5s8EgWmpHmG2keAB80au0uOEdV7RTlmjPaORtrvWjvOi2NDylQeKbmc71cmpsd-DTFwnjvk_OZP4-v6S7fDXYTj8ouYnY1yfgu7Colx1it6TylRFwuE9pllWSU1Wq5jZEpzcViPp99j45c-hxNBNyCxW96KBVW-TvGTLrmav__RvkSXmRMST6PQnAAO74_hP1tvQaSl-8R_FjkehBkFk3yX-lUlHz1_p5cDv1jFkLsKWbsSI_kIr4iya-AfGlv6RBoBI0bNNLJzRAL_ty-gsXVt8XlNc1lFajllVpT44QrTRAyOKFbj_ZY4KasuyrUnFnWSaEQ9AVu204FqWwrndIudMhUNMPL-jXs9UPv3wJxthOaeYsY0HOjXOuMbINgjikk57aAajvHjc0px2Pli7smmR6laRJfmsiXJvOlgI9Tm_sx4cY_qY8iAybKPPcFnGxZ2eQ1uWpY9HnHHaw2BbyfPuNqilckbe-HDdJUTBqEQEIW8GYUganvqOwNF_Xxn__5Dp7jyMzoRnYCe-uHjT-FZ_Zx_XP1cIYiu9RnSWSfAKz66Es |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9UwFD_MKbgXp0636tQIvmm2Ns3no5uOibUMrHDfSpuPIYx27N47_32TNLcg6MCnFnqShpyTnN9JzgfAO-m1du-MwaI0AlNJCe6NDrVepDW95Mq6GChcibqWi4W62IIPcyyMtTY6n9mj8Brv8s2o1-Go7DhkV-OE3oP7jFKST9Fa84lK7pE5j3iXFJxgUorFJkomV8dNXVffgyuXPPJGgt-E2R-aKJZW-TfKjNrmbPf_xvkYHiVUiT5OYvAEtuzwFHY3FRtQWsB78KNJFSFQFYzyX_FcFH2y9hqdjsNtEkPfU8jZER_RSXyJomcBOuku8ehwgI1rb6ajizGU_Ll8Bs3Z5-b0HKfCCljTQqywMszkyjHuDJOd9RaZoyov-8KVlGjScyY87HNUd71wXOiOGyGN6z1bvSGel89hexgHewDI6J5JYrVHgZYqYTqjeOcYMUR4cqozKDZz3OqUdDzUvrhqo_GRqzbypQ18aRNfMng_t7meUm7cSb0XGDBTprnP4HDDyjatymVLgte738NKlcHb-bNfT-GSpBvsuPY0BeHKgyDGM9ifRGDuO6h7RVn54u__fAMPz5tvVVt9qb--hB0_SjU5lR3C9upmbV_BA327-rm8eR0F9zdsFeqq |
| 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=Training+Lightweight+Deep+Convolutional+Neural+Networks+Using+Bag-of-Features+Pooling&rft.jtitle=IEEE+transaction+on+neural+networks+and+learning+systems&rft.au=Passalis%2C+Nikolaos&rft.au=Tefas%2C+Anastasios&rft.date=2019-06-01&rft.pub=The+Institute+of+Electrical+and+Electronics+Engineers%2C+Inc.+%28IEEE%29&rft.issn=2162-237X&rft.eissn=2162-2388&rft.volume=30&rft.issue=6&rft.spage=1705&rft_id=info:doi/10.1109%2FTNNLS.2018.2872995&rft.externalDBID=NO_FULL_TEXT |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2162-237X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2162-237X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2162-237X&client=summon |