{"id":"https://openalex.org/W4319878735","doi":"https://doi.org/10.1109/access.2023.3244072","title":"EUNNet: Efficient UN-Normalized Convolution Layer for Stable Training of Deep Residual Networks Without Batch Normalization Layer","display_name":"EUNNet: Efficient UN-Normalized Convolution Layer for Stable Training of Deep Residual Networks Without Batch Normalization Layer","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4319878735","doi":"https://doi.org/10.1109/access.2023.3244072"},"language":"en","primary_location":{"id":"doi:10.1109/access.2023.3244072","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3244072","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10041931.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10041931.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036257492","display_name":"Khanh-Binh Nguyen","orcid":"https://orcid.org/0000-0002-9948-1400"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Khanh-Binh Nguyen","raw_affiliation_strings":["Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-9948-1400","affiliations":[{"raw_affiliation_string":"Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091341639","display_name":"Jaehyuk Choi","orcid":"https://orcid.org/0000-0003-4700-1900"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaehyuk Choi","raw_affiliation_strings":["Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon, South Korea"],"raw_orcid":"https://orcid.org/0000-0003-4700-1900","affiliations":[{"raw_affiliation_string":"Department of Semiconductor Systems Engineering, Sungkyunkwan University, Suwon, South Korea","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5026627679","display_name":"Joon-Sung Yang","orcid":"https://orcid.org/0000-0002-1502-5353"},"institutions":[{"id":"https://openalex.org/I193775966","display_name":"Yonsei University","ror":"https://ror.org/01wjejq96","country_code":"KR","type":"education","lineage":["https://openalex.org/I193775966"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Joon-Sung Yang","raw_affiliation_strings":["School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","School of Electrical and Electronic Engineering and Department of Systems Semiconductor Engineering, Yonsei University, Seoul, South Korea"],"raw_orcid":"https://orcid.org/0000-0002-1502-5353","affiliations":[{"raw_affiliation_string":"School of Electrical and Electronic Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]},{"raw_affiliation_string":"School of Electrical and Electronic Engineering and Department of Systems Semiconductor Engineering, Yonsei University, Seoul, South Korea","institution_ids":["https://openalex.org/I193775966"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.6938,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.66426236,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"11","issue":null,"first_page":"76977","last_page":"76988"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11609","display_name":"Geophysical Methods and Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean Engineering"},"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/T11609","display_name":"Geophysical Methods and Applications","score":0.9998000264167786,"subfield":{"id":"https://openalex.org/subfields/2212","display_name":"Ocean 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/T10036","display_name":"Advanced Neural Network Applications","score":0.9965000152587891,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12169","display_name":"Non-Destructive Testing Techniques","score":0.9889000058174133,"subfield":{"id":"https://openalex.org/subfields/2210","display_name":"Mechanical 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/normalization","display_name":"Normalization (sociology)","score":0.7418618202209473},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6840606331825256},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.675792396068573},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6296093463897705},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.59707111120224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.40931880474090576},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3750857412815094},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.20454555749893188},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1707243025302887},{"id":"https://openalex.org/keywords/composite-material","display_name":"Composite material","score":0.11030182242393494}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7418618202209473},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6840606331825256},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.675792396068573},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6296093463897705},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.59707111120224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.40931880474090576},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3750857412815094},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.20454555749893188},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1707243025302887},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.11030182242393494},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2023.3244072","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3244072","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10041931.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:fc2cb48f38cb41ac81b0a24e88da86fb","is_oa":true,"landing_page_url":"https://doaj.org/article/fc2cb48f38cb41ac81b0a24e88da86fb","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 11, Pp 76977-76988 (2023)","raw_type":"article"},{"id":"pmh:oai:figshare.com:article/28612697","is_oa":true,"landing_page_url":"https://figshare.com/articles/journal_contribution/EUNNet_Efficient_UN-Normalized_Convolution_Layer_for_Stable_Training_of_Deep_Residual_Networks_Without_Batch_Normalization_Layer/28612697","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Text"}],"best_oa_location":{"id":"doi:10.1109/access.2023.3244072","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2023.3244072","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/10041931.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4319878735.pdf","grobid_xml":"https://content.openalex.org/works/W4319878735.grobid-xml"},"referenced_works_count":45,"referenced_works":["https://openalex.org/W1677182931","https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2338908902","https://openalex.org/W2502312327","https://openalex.org/W2549139847","https://openalex.org/W2617242334","https://openalex.org/W2618530766","https://openalex.org/W2765407302","https://openalex.org/W2792643794","https://openalex.org/W2952258850","https://openalex.org/W2954903132","https://openalex.org/W2963966020","https://openalex.org/W2992308087","https://openalex.org/W3048030262","https://openalex.org/W3061525482","https://openalex.org/W3118608800","https://openalex.org/W4250482878","https://openalex.org/W4287660544","https://openalex.org/W4288621368","https://openalex.org/W4293455017","https://openalex.org/W4385245566","https://openalex.org/W6631943919","https://openalex.org/W6677704767","https://openalex.org/W6687566353","https://openalex.org/W6703652217","https://openalex.org/W6724804524","https://openalex.org/W6729059855","https://openalex.org/W6733590821","https://openalex.org/W6734171162","https://openalex.org/W6738534199","https://openalex.org/W6739901393","https://openalex.org/W6747683314","https://openalex.org/W6751923770","https://openalex.org/W6754615192","https://openalex.org/W6755310813","https://openalex.org/W6757468910","https://openalex.org/W6762718338","https://openalex.org/W6779724054","https://openalex.org/W6781575362","https://openalex.org/W6783000698","https://openalex.org/W6785989746","https://openalex.org/W6787972765","https://openalex.org/W6788627230","https://openalex.org/W6790428460"],"related_works":["https://openalex.org/W2051487156","https://openalex.org/W2591697403","https://openalex.org/W2944728705","https://openalex.org/W2904022177","https://openalex.org/W2073681303","https://openalex.org/W2359348847","https://openalex.org/W3011538607","https://openalex.org/W4294432981","https://openalex.org/W4321441197","https://openalex.org/W4297807321"],"abstract_inverted_index":{"Batch":[0],"Normalization":[1],"(BN)":[2],"is":[3],"an":[4,87],"essential":[5],"component":[6],"of":[7,69,103,118,123],"the":[8,53,66,80,104,119,133,137],"Deep":[9,96],"Neural":[10,112],"Networks":[11,98],"(DNNs)":[12],"architectures.":[13],"It":[14],"helps":[15,93],"improve":[16],"stability,":[17],"convergence,":[18],"and":[19,77,153,161],"generalization.":[20],"However,":[21],"studies":[22],"are":[23,33],"showing":[24],"that":[25,132],"BN":[26,39],"might":[27],"introduce":[28,109],"several":[29,46],"concerns.":[30],"Although":[31],"there":[32],"methods":[34,145],"for":[35],"training":[36,54,67],"DNNs":[37],"without":[38,72],"using":[40,73,101],"proper":[41,74],"weight":[42,75],"initialization,":[43],"they":[44],"require":[45],"learnable":[47],"scalars":[48],"or":[49,139],"accurate":[50],"fine-tuning":[51,82,160],"to":[52,64,78,164],"hyperparameters.":[55],"As":[56],"a":[57],"result,":[58],"in":[59,146],"this":[60],"study,":[61],"we":[62,108],"aim":[63],"stabilize":[65],"process":[68],"un-normalized":[70,95],"networks":[71],"initialization":[76],"minimize":[79],"hyperparameters":[81,102,165],"step.":[83],"We":[84],"propose":[85],"EUNConv,":[86],"Efficient":[88,110],"UN-normalized":[89,111],"Convolutional":[90],"layer,":[91],"which":[92,115],"train":[94],"Residual":[97],"(ResNets)":[99],"by":[100],"normalized":[105],"networks.":[106],"Furthermore,":[107],"Network":[113],"(EUNNet),":[114],"replaces":[116],"all":[117],"conventional":[120],"convolutional":[121],"layers":[122],"ResNets":[124],"with":[125],"our":[126],"proposed":[127,134],"EUNConv.":[128],"Experimental":[129],"results":[130],"show":[131],"EUNNet":[135,157],"achieves":[136],"same":[138],"even":[140],"better":[141],"performance":[142],"than":[143,166],"previous":[144,167],"various":[147],"tasks:":[148],"image":[149],"recognition,":[150],"object":[151],"detection,":[152],"segmentation.":[154],"In":[155],"particular,":[156],"requires":[158],"less":[159,162],"sensitivity":[163],"methods.":[168]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}