{"id":"https://openalex.org/W4392944129","doi":"https://doi.org/10.1109/iceic61013.2024.10457126","title":"Extreme Pruning Technique Based on Filter Deactivation Using Sparsity Training for Deep Convolutional Neural Networks","display_name":"Extreme Pruning Technique Based on Filter Deactivation Using Sparsity Training for Deep Convolutional Neural Networks","publication_year":2024,"publication_date":"2024-01-28","ids":{"openalex":"https://openalex.org/W4392944129","doi":"https://doi.org/10.1109/iceic61013.2024.10457126"},"language":"en","primary_location":{"id":"doi:10.1109/iceic61013.2024.10457126","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic61013.2024.10457126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5104187328","display_name":"Kwanghyun Koo","orcid":null},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Kwanghyun Koo","raw_affiliation_strings":["Seoul National University of Science and Technology,Research Center for Electrical and Information Technology,Department of Electrical and Information Engineering,Seoul,Korea,01811"],"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology,Research Center for Electrical and Information Technology,Department of Electrical and Information Engineering,Seoul,Korea,01811","institution_ids":["https://openalex.org/I118373667"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100371185","display_name":"Hyun Kim","orcid":"https://orcid.org/0000-0002-7962-657X"},"institutions":[{"id":"https://openalex.org/I118373667","display_name":"Seoul National University of Science and Technology","ror":"https://ror.org/00chfja07","country_code":"KR","type":"education","lineage":["https://openalex.org/I118373667"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hyun Kim","raw_affiliation_strings":["Seoul National University of Science and Technology,Research Center for Electrical and Information Technology,Department of Electrical and Information Engineering,Seoul,Korea,01811"],"affiliations":[{"raw_affiliation_string":"Seoul National University of Science and Technology,Research Center for Electrical and Information Technology,Department of Electrical and Information Engineering,Seoul,Korea,01811","institution_ids":["https://openalex.org/I118373667"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5104187328"],"corresponding_institution_ids":["https://openalex.org/I118373667"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08257632,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.7192999720573425,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.7192999720573425,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T14158","display_name":"Optical Systems and Laser Technology","score":0.6876999735832214,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13717","display_name":"Advanced Algorithms and Applications","score":0.6863999962806702,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7775580883026123},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7743836641311646},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6897188425064087},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6237527132034302},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5552778840065002},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4819785952568054},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4723910987377167},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44998595118522644},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.43399107456207275},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42458951473236084},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.19003671407699585}],"concepts":[{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7775580883026123},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7743836641311646},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6897188425064087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6237527132034302},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5552778840065002},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4819785952568054},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4723910987377167},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44998595118522644},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.43399107456207275},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42458951473236084},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.19003671407699585},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iceic61013.2024.10457126","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/iceic61013.2024.10457126","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Conference on Electronics, Information, and Communication (ICEIC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3581515534","display_name":null,"funder_award_id":"2020M3H2AI078119","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2119144962","https://openalex.org/W2194775991","https://openalex.org/W2981958729","https://openalex.org/W3082058622","https://openalex.org/W3122390253","https://openalex.org/W4285059684","https://openalex.org/W4312914306","https://openalex.org/W4378717094","https://openalex.org/W4382119403","https://openalex.org/W4383501700","https://openalex.org/W6677580257"],"related_works":["https://openalex.org/W4293226380","https://openalex.org/W4226493464","https://openalex.org/W4312417841","https://openalex.org/W3193565141","https://openalex.org/W3133861977","https://openalex.org/W2951211570","https://openalex.org/W3167935049","https://openalex.org/W3103566983","https://openalex.org/W3029198973","https://openalex.org/W3000197790"],"abstract_inverted_index":{"Pruning":[0],"represents":[1],"a":[2,14,30,81,109,117,146,159,184,220,234],"significant":[3],"compression":[4,63,95],"performance":[5,208,235],"in":[6,18,42,108,139,152,175,247],"deep":[7],"convolutional":[8],"neural":[9],"networks":[10],"and":[11,24,58,217],"has":[12,131],"been":[13],"subject":[15],"of":[16,44,75,134,155,198,209,237,245],"research":[17],"two":[19],"major":[20],"directions:":[21],"filter":[22,163],"pruning":[23,119,130,143,149,222],"weight":[25,69,142],"pruning.":[26],"Filter":[27],"pruning,":[28,70,158,231],"as":[29,37,162],"method":[31,120,228],"for":[32,84,229],"eliminating":[33],"3-dimensional":[34],"parameters":[35,246],"known":[36,161],"filters,":[38],"exhibits":[39],"notable":[40],"advantages":[41],"terms":[43],"high":[45,94,148],"acceleration":[46,107],"performance.":[47,64,96],"However,":[48],"it":[49,98,103],"presents":[50],"challenges":[51],"when":[52,102,249],"applied":[53],"to":[54,79,89,92,105,137,187],"complex":[55,85],"network":[56,86,211],"structures":[57,87],"may":[59],"yield":[60],"relatively":[61,147],"lower":[62],"On":[65],"the":[66,73,125,132,153,176,199,207,210,226,252],"other":[67],"hand,":[68],"which":[71],"involves":[72],"removal":[74],"1-dimensional":[76],"parameters,":[77],"proves":[78],"be":[80],"viable":[82],"option":[83],"due":[88],"its":[90],"ability":[91],"achieve":[93,219,233],"Nevertheless,":[97],"does":[99],"have":[100],"limitations":[101],"comes":[104],"achieving":[106,145],"general":[110],"GPU":[111],"environment.":[112],"To":[113],"solve":[114],"this":[115,180],"problem,":[116],"kernel":[118,157,230],"was":[121],"proposed":[122,227],"that":[123,201],"removes":[124],"2-dimensional":[126],"parameter":[127],"kernels.":[128],"Kernel":[129],"advantage":[133,197],"being":[135],"easier":[136],"accelerate":[138],"hardware":[140],"than":[141],"while":[144,239],"rate.":[150,223],"Nonetheless,":[151],"process":[154],"employing":[156],"phenomenon":[160],"deactivation":[164],"emerges,":[165],"where":[166],"certain":[167],"filters":[168,191,203],"generate":[169],"outputs":[170],"but":[171],"remain":[172],"entirely":[173],"unused":[174],"subsequent":[177],"layer.":[178],"In":[179],"paper,":[181],"we":[182,232],"present":[183],"novel":[185],"approach":[186],"create":[188],"more":[189],"deactivated":[190,202],"through":[192],"sparsity":[193],"training":[194],"by":[195],"taking":[196],"fact":[200],"do":[204],"not":[205],"affect":[206],"even":[212],"if":[213],"they":[214],"are":[215],"removed,":[216],"consequently":[218],"higher":[221],"By":[224],"applying":[225],"enhancement":[236],"0.22%,":[238],"successfully":[240],"removing":[241],"an":[242],"additional":[243],"2.58%":[244],"ResNet-110":[248],"evaluated":[250],"on":[251],"CIFAR-10":[253],"dataset.":[254]},"counts_by_year":[],"updated_date":"2025-12-22T23:10:17.713674","created_date":"2025-10-10T00:00:00"}