Dynamic Image Difficulty-Aware DNN Pruning
Deep Neural Networks (DNNs) have achieved impressive performance in various image recognition tasks, but their large model sizes make them challenging to deploy on resource-constrained devices. In this paper, we propose a dynamic DNN pruning approach that takes into account the difficulty of the inc...
Saved in:
| Published in | Micromachines (Basel) Vol. 14; no. 5; p. 908 |
|---|---|
| Main Authors | , , |
| Format | Journal Article |
| Language | English |
| Published |
Switzerland
MDPI AG
23.04.2023
MDPI |
| Subjects | |
| Online Access | Get full text |
| ISSN | 2072-666X 2072-666X |
| DOI | 10.3390/mi14050908 |
Cover
| Abstract | Deep Neural Networks (DNNs) have achieved impressive performance in various image recognition tasks, but their large model sizes make them challenging to deploy on resource-constrained devices. In this paper, we propose a dynamic DNN pruning approach that takes into account the difficulty of the incoming images during inference. To evaluate the effectiveness of our method, we conducted experiments on the ImageNet dataset on several state-of-art DNNs. Our results show that the proposed approach reduces the model size and amount of DNN operations without the need to retrain or fine-tune the pruned model. Overall, our method provides a promising direction for designing efficient frameworks for lightweight DNN models that can adapt to the varying complexity of input images. |
|---|---|
| AbstractList | Deep Neural Networks (DNNs) have achieved impressive performance in various image recognition tasks, but their large model sizes make them challenging to deploy on resource-constrained devices. In this paper, we propose a dynamic DNN pruning approach that takes into account the difficulty of the incoming images during inference. To evaluate the effectiveness of our method, we conducted experiments on the ImageNet dataset on several state-of-art DNNs. Our results show that the proposed approach reduces the model size and amount of DNN operations without the need to retrain or fine-tune the pruned model. Overall, our method provides a promising direction for designing efficient frameworks for lightweight DNN models that can adapt to the varying complexity of input images. Deep Neural Networks (DNNs) have achieved impressive performance in various image recognition tasks, but their large model sizes make them challenging to deploy on resource-constrained devices. In this paper, we propose a dynamic DNN pruning approach that takes into account the difficulty of the incoming images during inference. To evaluate the effectiveness of our method, we conducted experiments on the ImageNet dataset on several state-of-art DNNs. Our results show that the proposed approach reduces the model size and amount of DNN operations without the need to retrain or fine-tune the pruned model. Overall, our method provides a promising direction for designing efficient frameworks for lightweight DNN models that can adapt to the varying complexity of input images.Deep Neural Networks (DNNs) have achieved impressive performance in various image recognition tasks, but their large model sizes make them challenging to deploy on resource-constrained devices. In this paper, we propose a dynamic DNN pruning approach that takes into account the difficulty of the incoming images during inference. To evaluate the effectiveness of our method, we conducted experiments on the ImageNet dataset on several state-of-art DNNs. Our results show that the proposed approach reduces the model size and amount of DNN operations without the need to retrain or fine-tune the pruned model. Overall, our method provides a promising direction for designing efficient frameworks for lightweight DNN models that can adapt to the varying complexity of input images. |
| Audience | Academic |
| Author | Anagnostopoulos, Iraklis Spantidi, Ourania Pentsos, Vasileios |
| AuthorAffiliation | School of Electrical, Computer and Biomedical Engineering, Southern Illinois University, Carbondale, IL 62901, USA |
| AuthorAffiliation_xml | – name: School of Electrical, Computer and Biomedical Engineering, Southern Illinois University, Carbondale, IL 62901, USA |
| Author_xml | – sequence: 1 givenname: Vasileios surname: Pentsos fullname: Pentsos, Vasileios – sequence: 2 givenname: Ourania surname: Spantidi fullname: Spantidi, Ourania – sequence: 3 givenname: Iraklis orcidid: 0000-0003-0985-3045 surname: Anagnostopoulos fullname: Anagnostopoulos, Iraklis |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/37241531$$D View this record in MEDLINE/PubMed |
| BookMark | eNp9kl1rFDEUhgep2Fp74w-QBW-kMjVfk9lcydL6sVCqFwrehTP5GLPMJGtmxrL_3rNOrW0RE0jCyXue5LzJ0-IgpuiK4jklZ5wr8qYPVJCKKLJ8VBwxUrNSSvnt4M76sDgZhg3BVtcKhyfFIa-ZoBWnR8XpxS5CH8xi3UPrFhfB-2CmbtyVq2vIGLi6WnzOUwyxfVY89tAN7uRmPi6-vn_35fxjefnpw_p8dVmairKxrJW0ilDFfG0oI6TxTDXccCuIbEwNQtGGCNtYBWCoYLISRvIlc2AsMK_4cbGeuTbBRm9z6CHvdIKgfwdSbjXkMZjOaWUtmEZ56gQipVGVlNZR0jDGiF0ukfV6Zk1xC7tr6LpbICV6b6D-ayCq387q7dT0zhoXxwzdvSvc34nhu27TT2QxJjjfE17dEHL6MblhRPxgXNdBdGkaNFuiI1QIVqP05QPpJk05orOookpgq_ZmnM2qFrDeEH3Cgw126_DV8Cv4gPFVjQUoJqTAhBd3a7i9_J8nRwGZBSanYcjOaxNGGEPalxS6f_ty-iDlPyb-ApT3yOc |
| CitedBy_id | crossref_primary_10_1016_j_imavis_2024_105037 |
| Cites_doi | 10.1109/CVPR.2016.90 10.1109/JSSC.2016.2616357 10.1109/CVPR.2015.7298594 10.1109/CVPR.2009.5206848 10.1109/TCAD.2020.3012753 10.1109/CVPR.2016.237 10.1145/3065386 10.1109/TCAD.2022.3197522 10.1109/QoMEX.2013.6603194 10.1109/TIP.2012.2214050 10.1109/TETC.2022.3178730 10.1109/ISQED54688.2022.9806282 10.1109/CVPR52729.2023.01544 10.1007/978-3-030-01234-2_48 10.1109/CVPR42600.2020.00225 10.1109/ICCAD51958.2021.9643491 |
| ContentType | Journal Article |
| Copyright | COPYRIGHT 2023 MDPI AG 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. 2023 by the authors. 2023 |
| Copyright_xml | – notice: COPYRIGHT 2023 MDPI AG – notice: 2023 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. – notice: 2023 by the authors. 2023 |
| DBID | AAYXX CITATION NPM 7SP 7TB 8FD 8FE 8FG ABJCF ABUWG AFKRA AZQEC BENPR BGLVJ CCPQU DWQXO FR3 HCIFZ L6V L7M M7S PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS PTHSS 7X8 5PM ADTOC UNPAY DOA |
| DOI | 10.3390/mi14050908 |
| DatabaseName | CrossRef PubMed Electronics & Communications Abstracts Mechanical & Transportation Engineering Abstracts Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection Materials Science & Engineering Collection ProQuest Central (Alumni Edition) ProQuest Central UK/Ireland ProQuest Central Essentials ProQuest Central Technology collection ProQuest One Community College ProQuest Central Korea Engineering Research Database SciTech Premium Collection ProQuest Engineering Collection Advanced Technologies Database with Aerospace Engineering Database ProQuest Central Premium ProQuest One Academic (New) Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic ProQuest One Academic UKI Edition ProQuest Central China Engineering Collection MEDLINE - Academic PubMed Central (Full Participant titles) Unpaywall for CDI: Periodical Content Unpaywall DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef PubMed Publicly Available Content Database Technology Collection Technology Research Database ProQuest One Academic Middle East (New) Mechanical & Transportation Engineering Abstracts ProQuest Central Essentials ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Engineering Collection ProQuest Central Korea ProQuest Central (New) Advanced Technologies Database with Aerospace Engineering Collection Engineering Database ProQuest One Academic Eastern Edition Electronics & Communications Abstracts ProQuest Technology Collection ProQuest SciTech Collection ProQuest One Academic UKI Edition Materials Science & Engineering Collection Engineering Research Database ProQuest One Academic ProQuest One Academic (New) MEDLINE - Academic |
| DatabaseTitleList | PubMed Publicly Available Content Database CrossRef MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Open Access Full Text url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 3 dbid: UNPAY name: Unpaywall url: https://proxy.k.utb.cz/login?url=https://unpaywall.org/ sourceTypes: Open Access Repository – sequence: 4 dbid: 8FG name: ProQuest Technology Collection url: https://search.proquest.com/technologycollection1 sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISSN | 2072-666X |
| ExternalDocumentID | oai_doaj_org_article_9ddacb9f1e404d6c9566de10b2220d88 10.3390/mi14050908 PMC10224338 A750992464 37241531 10_3390_mi14050908 |
| Genre | Journal Article |
| GrantInformation_xml | – fundername: National Science Foundation grantid: 1361847 – fundername: Consortium for Embedded Systems at SIUC |
| GroupedDBID | 53G 5VS 8FE 8FG AADQD AAFWJ AAYXX ABJCF ADBBV ADMLS AENEX AFKRA AFPKN AFZYC ALMA_UNASSIGNED_HOLDINGS AOIJS BCNDV BENPR BGLVJ CCPQU CITATION GROUPED_DOAJ HCIFZ HYE IAO ITC KQ8 L6V M7S MM. MODMG M~E OK1 PGMZT PHGZM PHGZT PIMPY PQGLB PROAC PTHSS PUEGO RPM TR2 TUS NPM 7SP 7TB 8FD ABUWG AZQEC DWQXO FR3 L7M PKEHL PQEST PQQKQ PQUKI PRINS 7X8 5PM ADTOC C1A IPNFZ RIG UNPAY |
| ID | FETCH-LOGICAL-c512t-796d90192f7c1200bf29b3c3d406bc7a491b04dbd9aac142654c6382eacda2f93 |
| IEDL.DBID | DOA |
| ISSN | 2072-666X |
| IngestDate | Wed Aug 27 00:51:38 EDT 2025 Wed Aug 20 00:05:19 EDT 2025 Tue Sep 30 17:13:20 EDT 2025 Thu Sep 04 18:44:58 EDT 2025 Fri Jul 25 10:45:55 EDT 2025 Tue Jul 01 05:45:21 EDT 2025 Wed Feb 19 02:23:57 EST 2025 Wed Oct 01 04:20:24 EDT 2025 Thu Apr 24 23:05:28 EDT 2025 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 5 |
| Keywords | pruning image difficulty Deep Neural Networks embedded systems |
| Language | English |
| License | https://creativecommons.org/licenses/by/4.0 Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). cc-by |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c512t-796d90192f7c1200bf29b3c3d406bc7a491b04dbd9aac142654c6382eacda2f93 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23 These authors contributed equally to this work. |
| ORCID | 0000-0003-0985-3045 |
| OpenAccessLink | https://doaj.org/article/9ddacb9f1e404d6c9566de10b2220d88 |
| PMID | 37241531 |
| PQID | 2819444459 |
| PQPubID | 2032359 |
| ParticipantIDs | doaj_primary_oai_doaj_org_article_9ddacb9f1e404d6c9566de10b2220d88 unpaywall_primary_10_3390_mi14050908 pubmedcentral_primary_oai_pubmedcentral_nih_gov_10224338 proquest_miscellaneous_2820014427 proquest_journals_2819444459 gale_infotracacademiconefile_A750992464 pubmed_primary_37241531 crossref_citationtrail_10_3390_mi14050908 crossref_primary_10_3390_mi14050908 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2023-04-23 |
| PublicationDateYYYYMMDD | 2023-04-23 |
| PublicationDate_xml | – month: 04 year: 2023 text: 2023-04-23 day: 23 |
| PublicationDecade | 2020 |
| PublicationPlace | Switzerland |
| PublicationPlace_xml | – name: Switzerland – name: Basel |
| PublicationTitle | Micromachines (Basel) |
| PublicationTitleAlternate | Micromachines (Basel) |
| PublicationYear | 2023 |
| Publisher | MDPI AG MDPI |
| Publisher_xml | – name: MDPI AG – name: MDPI |
| References | ref_13 ref_12 ref_10 ref_19 Chen (ref_26) 2016; 52 ref_17 Spantidi (ref_11) 2022; 11 ref_15 Amrouch (ref_3) 2020; 39 Mittal (ref_14) 2012; 21 Li (ref_16) 2016; 25 ref_25 ref_24 ref_22 ref_21 ref_20 ref_1 Spantidi (ref_18) 2022; 41 ref_2 Krizhevsky (ref_23) 2017; 60 ref_27 ref_9 ref_8 ref_5 ref_4 ref_7 ref_6 |
| References_xml | – ident: ref_7 – ident: ref_5 – ident: ref_21 doi: 10.1109/CVPR.2016.90 – volume: 52 start-page: 127 year: 2016 ident: ref_26 article-title: Eyeriss: An energy-efficient reconfigurable accelerator for deep convolutional neural networks publication-title: IEEE J. Solid-State Circuits doi: 10.1109/JSSC.2016.2616357 – ident: ref_24 doi: 10.1109/CVPR.2015.7298594 – ident: ref_19 doi: 10.1109/CVPR.2009.5206848 – volume: 39 start-page: 3842 year: 2020 ident: ref_3 article-title: NPU Thermal Management publication-title: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. doi: 10.1109/TCAD.2020.3012753 – ident: ref_12 doi: 10.1109/CVPR.2016.237 – ident: ref_6 – volume: 60 start-page: 84 year: 2017 ident: ref_23 article-title: Imagenet classification with deep convolutional neural networks publication-title: Commun. Acm doi: 10.1145/3065386 – ident: ref_8 – volume: 41 start-page: 3838 year: 2022 ident: ref_18 article-title: Energy-Efficient DNN Inference on Approximate Accelerators through Formal Property Exploration publication-title: IEEE Trans. Comput. Aided Des. Integr. Circuits Syst. doi: 10.1109/TCAD.2022.3197522 – ident: ref_25 – ident: ref_27 – ident: ref_15 doi: 10.1109/QoMEX.2013.6603194 – ident: ref_10 – volume: 25 start-page: 3775 year: 2016 ident: ref_16 article-title: Sparse representation-based image quality index with adaptive sub-dictionaries publication-title: IEEE Trans. Image Process. – volume: 21 start-page: 4695 year: 2012 ident: ref_14 article-title: No-reference image quality assessment in the spatial domain publication-title: IEEE Trans. Image Process. doi: 10.1109/TIP.2012.2214050 – volume: 11 start-page: 112 year: 2022 ident: ref_11 article-title: Targeting DNN Inference via Efficient Utilization of Heterogeneous Precision DNN Accelerators publication-title: IEEE Trans. Emerg. Top. Comput. doi: 10.1109/TETC.2022.3178730 – ident: ref_13 – ident: ref_2 doi: 10.1109/ISQED54688.2022.9806282 – ident: ref_17 doi: 10.1109/CVPR52729.2023.01544 – ident: ref_22 – ident: ref_9 doi: 10.1007/978-3-030-01234-2_48 – ident: ref_20 – ident: ref_4 doi: 10.1109/CVPR42600.2020.00225 – ident: ref_1 doi: 10.1109/ICCAD51958.2021.9643491 |
| SSID | ssj0000779007 |
| Score | 2.2846959 |
| Snippet | Deep Neural Networks (DNNs) have achieved impressive performance in various image recognition tasks, but their large model sizes make them challenging to... |
| SourceID | doaj unpaywall pubmedcentral proquest gale pubmed crossref |
| SourceType | Open Website Open Access Repository Aggregation Database Index Database Enrichment Source |
| StartPage | 908 |
| SubjectTerms | Accuracy Artificial neural networks Classification Datasets Deep Neural Networks Embedded systems Energy consumption Human subjects image difficulty Neural networks Pruning Sparsity Support vector machines |
| SummonAdditionalLinks | – databaseName: ProQuest Technology Collection dbid: 8FG link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwfV3Nb9MwFH-CcQAOiM8R2FAQkxBI0eLYdeITKhtlIFFxYNJulr-yTerS0rWa9t_zXuJmLaDlaFuR_fy-bf8ewJ73pnTSE8w-45lwRZVVRsrMlxiLeSVRW9JD4R9jeXQsvp8MTmLC7TJeq1zpxFZR-6mjHPk-HfgI_Abq0-x3RlWj6HQ1ltC4C_dYgZxEL8VHX_scS05gennZoZJyjO73L84xoEAbSdUk1-xQC9f_r1Jes0p_35i8v2xm5vrKTCZr5mj0GB5FPzIddhv_BO6E5ik8XEMXfAYfD7tq8-m3C1Qa6SFlZwho4zobXpk5NozH6c_5khIjz-F49OXXwVEWSyNkDi30IisV0pe8s7p0DBnd1oWy3HGP9tm60gjFbC689coYx9AKD4RD-hSoZr0pasVfwFYzbcJLSLkMqOICMyYMRG0rU4dglKkVOiqMO5PAhxWhtIu44VS-YqIxfiCi6huiJvCuHzvr0DL-O-oz0bsfQQjXbcN0fqqjwGiFXOSsqlkQuBDpMI6TPrDcokOT-wp_8p52S5Mc4nScic8JcFGEaKWH5AphcClFAjurDdVRQC_1DTsl8LbvRtGi8xLThOmSxtCFMyGKMoHtbv_7OfOSXB_OEqg2OGNjUZs9zflZC9_dgvhxjivY65noFmq9un36r-FBgX4XHXAVfAe2FvNl2EU_aWHftMLwB7IBEOg priority: 102 providerName: ProQuest – databaseName: Unpaywall dbid: UNPAY link: http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwELdQ9wA8jG8WGCiISQikLHHsOPETKoxpIFHtgUrlyXJsByq6tOoapvHXc5e4oR0IIfqYXKtc7-t3tvM7Qg6s1bkRFmn2KYu4SYuo0EJENodezEoB2RJfFP44Eidj_mGSTfyC27k_Vgmt-LRN0mmSpxHg60lMeZzFMiniha1ef_crSVRAdWOFQLLPHYEbTAOyMx6dDj_jRLn1dztOUga9fXw2hXYCKiTOktyoQi1Z_-8peaMmXT0veb2pF_ryQs9mG8Xo-BZRazW6MyjfDptVeWh-XGF4_H89b5Ndj1PDYedYd8g1V98lNzfYC--RV0fdNPvw_RkkpfAIV3-QyOMyGl7oJVwYjcLTZYMLL_fJ-Pjdp7cnkR-9EBlAAKsol2A_RH9VbigEUlmlsmSGWaj_pck1l7RMuC2t1NpQqPIZNxDJKaRxq9NKsgdkUM9rt0dCJhykUEe1dhmvykJXzmmpKwlAiDKjA_JybQplPC85jseYKehP0Gzql9kC8ryXXXRsHH-UeoMW7SWQQbu9MF9-UT4glQQvNaWsqOOgiDDQJwrraFICYEpsAT_yAv1BYZzD4xjtX1cApZAxSw0RakHzKnhA9tcuo3wCOFe4P8nhk8mAPOtvQ-jifoyu3bxBGTzQxnmaB-Rh52H9M7McoRWjASm2fG9Lqe079fRrSw_ekgQyBhoc9G76l3_r0b-JPSY3UsB3uJGWsn0yWC0b9wTw2Kp86oPuJwzaLm4 priority: 102 providerName: Unpaywall |
| Title | Dynamic Image Difficulty-Aware DNN Pruning |
| URI | https://www.ncbi.nlm.nih.gov/pubmed/37241531 https://www.proquest.com/docview/2819444459 https://www.proquest.com/docview/2820014427 https://pubmed.ncbi.nlm.nih.gov/PMC10224338 https://www.mdpi.com/2072-666X/14/5/908/pdf?version=1682238603 https://doaj.org/article/9ddacb9f1e404d6c9566de10b2220d88 |
| UnpaywallVersion | publishedVersion |
| Volume | 14 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAFT databaseName: Open Access Digital Library customDbUrl: eissn: 2072-666X dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0000779007 issn: 2072-666X databaseCode: KQ8 dateStart: 20100101 isFulltext: true titleUrlDefault: http://grweb.coalliance.org/oadl/oadl.html providerName: Colorado Alliance of Research Libraries – providerCode: PRVAON databaseName: DOAJ Open Access Full Text customDbUrl: eissn: 2072-666X dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0000779007 issn: 2072-666X databaseCode: DOA dateStart: 20100101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVEBS databaseName: Inspec with Full Text customDbUrl: eissn: 2072-666X dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0000779007 issn: 2072-666X databaseCode: ADMLS dateStart: 20110901 isFulltext: true titleUrlDefault: https://www.ebsco.com/products/research-databases/inspec-full-text providerName: EBSCOhost – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources customDbUrl: eissn: 2072-666X dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0000779007 issn: 2072-666X databaseCode: M~E dateStart: 20100101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVAQN databaseName: PubMed Central customDbUrl: eissn: 2072-666X dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0000779007 issn: 2072-666X databaseCode: RPM dateStart: 20160101 isFulltext: true titleUrlDefault: https://www.ncbi.nlm.nih.gov/pmc/ providerName: National Library of Medicine – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: http://www.proquest.com/pqcentral?accountid=15518 eissn: 2072-666X dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0000779007 issn: 2072-666X databaseCode: BENPR dateStart: 20100301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Technology Collection customDbUrl: eissn: 2072-666X dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0000779007 issn: 2072-666X databaseCode: 8FG dateStart: 20100301 isFulltext: true titleUrlDefault: https://search.proquest.com/technologycollection1 providerName: ProQuest |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1ba9RAFD5ofdA-iNc22i4RC6IQupOZnWQet5e1CoZFXKhPw9xCC9u0bHcp_feek6Qxq6Iv5i3JEGa-M-eWmfkOwJ73JnPSE80-44lwaZ7kRsrEZ5iLeSXRWtJB4S-FPJmJz6ej016pL9oT1tADN8DtK_yas6pkQQyFlw7jeekDG1p0bEOf18d80Y31kqnaBhON3jBr-Eg55vX7F-eYSqB3pDqSPQ9UE_X_bo57_ujXvZIPV9WVub0x83nPEU2ewOM2gozHTc-fwr1QPYPNHq_gc_hw1NSZjz9doLmIj-i_DFFs3CbjG7PAB0URTxcr-iXyAmaT42-HJ0lbFCFx6JuXSaYQWYrLyswxnOK2TJXljnv0zNZlRihmESjrlTGOof8dCYc6lqKB9SYtFX8JG9VlFbYh5jKgcQvMmDASpc1NGYJRplQYojDuTATv74DSrmUMp8IVc42ZA4Gqf4Iawduu7VXDk_HHVgeEd9eCuK3rByhx3Upc_0viEbwjaWnSQOyOM-1BAhwUcVnpMQVBmFZKEcHOnUB1q5rXmlYOBV4jFcGb7jUqFa2UmCpcrqgNbTUTIs0i2Grk3_WZZxT0cBZBvjYz1ga1_qY6P6uJu2v6Ps5xBHvdJPoLWq_-B1qv4VGKcRktgKV8BzaWi1XYxThqaQdwP598HMCDg-Ni-nVQKxDezYrp-PsPf1weAQ |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1bb9MwFD6axsPgAXEnMCCIIQRStCR2k_gBoUIpLdsqHjZpb8a3wKQuLV2rqn-K38g5ua0FtLfl0bYi-_jcbX8HYM9alZrEEsx-xAJu4izIVJIENsVYzIoEtSU9FD4aJYMT_vW0c7oFv5u3MHStstGJpaK2E0M58n068OH4dcSH6a-AqkbR6WpTQqNiiwO3WmLIdvF-2MP9fR3H_c_HnwZBXVUgMGjc5kEqcGrk2OSpiZBHdB4LzQyzaNq0SRUXkQ651VYoZSI0YB1ukElj1FBWxTmBL6HKv8EZY4TVn_W_tDmdkMD7wrRCQWVMhPvnZxjAoE2m6pVrdq8sD_CvEVizgn_f0NxZFFO1WqrxeM389e_A7dpv9bsVo92FLVfcg1traIb34V2vqm7vD89RSfk9ygYRsMcq6C7VDBtGI__bbEGJmAdwci1EewjbxaRwj8FniUOV6iKlXIfnOlO5c0qoXKBjFDGjPHjbEEqaGqecymWMJcYrRFR5SVQPXrVjpxU6x39HfSR6tyMIUbtsmMx-yFpApUCuNVrkkeO4kMRg3JhYF4UaHajQZviTN7RbkuQep2NU_XwBF0UIWrJLrhcGswn3YLfZUFkrhAt5yb4evGy7UZTpfEYVbrKgMXTBjfM49eBRtf_tnFlKrhaLPMg2OGNjUZs9xdnPEi68BA1kDFew1zLRFdR6cvX0X8DO4PjoUB4ORwdP4WaMPh8drsVsF7bns4V7hj7aXD8vBcOH79ctiX8AN-pNwA |
| linkToPdf | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3db9MwED9NnQTsAfFNYEAQQwikqEnsJvHDhDq6amVQVYhJewuO7YxKbVq6VlX_Rf4q7lInawHtbXm0rcg-36ft-x3AgdYyVpEmmP2AeVyFiZfIKPJ0jLGYFhFqS0oU_tqPTs745_PW-Q78rnJh6FllpRNLRa0nis7Im3Thw_FriWZun0UMOt2P018eVZCim9aqnIa0ZRb0YQk3ZpM8Ts1qieHc5WGvg3v_Ngy7x98_nXi24oCn0PDNvVjgtMnpyWMVIP9keSgypphGs5epWHIRZD7XmRZSqgCNW4srZOAQtZeWYU7ATGgOdmPKF23A7tFxf_CtPvHxCdrPj9cYqYwJvzkeYniDFptqW25YxbJ4wL8mYsNG_v1-8_aimMrVUo5GG8axew_uWq_Wba_Z8D7smOIB7G1gHT6ED51VIcdD5fbGqMLcDp0VEezHymsv5Qwb-n13MFvQMc0jOLsRsj2GRjEpzFNwWWRQ4ZpAStPieZbI3BgpZC7QbQqYkg68rwiVKotiTsU0RilGM0TU9IqoDrypx07X2B3_HXVE9K5HEN522TCZXaRWfFOBPK0ykQeG40IihVFlpE3gZ-he-TrBn7yj3UpJK-B0lLTJDbgowtdK2-SYYagbcQf2qw1Nrbq4TK-Y24HXdTcKOt3eyMJMFjSGnr9xHsYOPFnvfz1nFpMjxgIHki3O2FrUdk8x_FmCiZeQgozhCg5qJrqGWs-un_4ruIVSmX7p9U-fw50QHUK6eQvZPjTms4V5gQ7cPHtpJcOFHzctjH8ADPtYmg |
| linkToUnpaywall | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3db9MwELdQ9wA8jG8WGCiISQikLHHsOPETKoxpIFHtgUrlyXJsByq6tOoapvHXc5e4oR0IIfqYXKtc7-t3tvM7Qg6s1bkRFmn2KYu4SYuo0EJENodezEoB2RJfFP44Eidj_mGSTfyC27k_Vgmt-LRN0mmSpxHg60lMeZzFMiniha1ef_crSVRAdWOFQLLPHYEbTAOyMx6dDj_jRLn1dztOUga9fXw2hXYCKiTOktyoQi1Z_-8peaMmXT0veb2pF_ryQs9mG8Xo-BZRazW6MyjfDptVeWh-XGF4_H89b5Ndj1PDYedYd8g1V98lNzfYC--RV0fdNPvw_RkkpfAIV3-QyOMyGl7oJVwYjcLTZYMLL_fJ-Pjdp7cnkR-9EBlAAKsol2A_RH9VbigEUlmlsmSGWaj_pck1l7RMuC2t1NpQqPIZNxDJKaRxq9NKsgdkUM9rt0dCJhykUEe1dhmvykJXzmmpKwlAiDKjA_JybQplPC85jseYKehP0Gzql9kC8ryXXXRsHH-UeoMW7SWQQbu9MF9-UT4glQQvNaWsqOOgiDDQJwrraFICYEpsAT_yAv1BYZzD4xjtX1cApZAxSw0RakHzKnhA9tcuo3wCOFe4P8nhk8mAPOtvQ-jifoyu3bxBGTzQxnmaB-Rh52H9M7McoRWjASm2fG9Lqe079fRrSw_ekgQyBhoc9G76l3_r0b-JPSY3UsB3uJGWsn0yWC0b9wTw2Kp86oPuJwzaLm4 |
| 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=Dynamic+Image+Difficulty-Aware+DNN+Pruning&rft.jtitle=Micromachines+%28Basel%29&rft.au=Pentsos%2C+Vasileios&rft.au=Spantidi%2C+Ourania&rft.au=Anagnostopoulos%2C+Iraklis&rft.date=2023-04-23&rft.issn=2072-666X&rft.eissn=2072-666X&rft.volume=14&rft.issue=5&rft_id=info:doi/10.3390%2Fmi14050908&rft_id=info%3Apmid%2F37241531&rft.externalDocID=37241531 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2072-666X&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2072-666X&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2072-666X&client=summon |