{"id":"https://openalex.org/W4317418649","doi":"https://doi.org/10.1109/gcce56475.2022.10014037","title":"Instance-wise Center Loss for Efficient Training of Deep Convolutional Neural Networks","display_name":"Instance-wise Center Loss for Efficient Training of Deep Convolutional Neural Networks","publication_year":2022,"publication_date":"2022-10-18","ids":{"openalex":"https://openalex.org/W4317418649","doi":"https://doi.org/10.1109/gcce56475.2022.10014037"},"language":"en","primary_location":{"id":"doi:10.1109/gcce56475.2022.10014037","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce56475.2022.10014037","pdf_url":null,"source":{"id":"https://openalex.org/S4363607800","display_name":"2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)","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/A5078928046","display_name":"Koki Madono","orcid":"https://orcid.org/0000-0002-5214-8539"},"institutions":[{"id":"https://openalex.org/I150744194","display_name":"Waseda University","ror":"https://ror.org/00ntfnx83","country_code":"JP","type":"education","lineage":["https://openalex.org/I150744194"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Koki Madono","raw_affiliation_strings":["Waseda University/AIST"],"affiliations":[{"raw_affiliation_string":"Waseda University/AIST","institution_ids":["https://openalex.org/I150744194"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040292386","display_name":"Masayuki Tanaka","orcid":"https://orcid.org/0000-0002-5756-1904"},"institutions":[{"id":"https://openalex.org/I114531698","display_name":"Tokyo Institute of Technology","ror":"https://ror.org/0112mx960","country_code":"JP","type":"education","lineage":["https://openalex.org/I114531698"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masayuki Tanaka","raw_affiliation_strings":["Tokyo Institute of Technology/AIST"],"affiliations":[{"raw_affiliation_string":"Tokyo Institute of Technology/AIST","institution_ids":["https://openalex.org/I114531698"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031341888","display_name":"Masaki Onishi","orcid":"https://orcid.org/0000-0002-4580-4868"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Masaki Onishi","raw_affiliation_strings":["AIST"],"affiliations":[{"raw_affiliation_string":"AIST","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5078928046"],"corresponding_institution_ids":["https://openalex.org/I150744194"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18886354,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"692","last_page":"696"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9395999908447266,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9395999908447266,"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/T10320","display_name":"Neural Networks and Applications","score":0.9383999705314636,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7548274993896484},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7464883923530579},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.5548787117004395},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5475782155990601},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5424275398254395},{"id":"https://openalex.org/keywords/center","display_name":"Center (category theory)","score":0.456351101398468},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42141392827033997}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7548274993896484},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7464883923530579},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.5548787117004395},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5475782155990601},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5424275398254395},{"id":"https://openalex.org/C2779463800","wikidata":"https://www.wikidata.org/wiki/Q5062222","display_name":"Center (category theory)","level":2,"score":0.456351101398468},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42141392827033997},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C8010536","wikidata":"https://www.wikidata.org/wiki/Q160398","display_name":"Crystallography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/gcce56475.2022.10014037","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/gcce56475.2022.10014037","pdf_url":null,"source":{"id":"https://openalex.org/S4363607800","display_name":"2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)","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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE 11th Global Conference on Consumer Electronics (GCCE)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W2112796928","https://openalex.org/W2194775991","https://openalex.org/W2520774990","https://openalex.org/W2523246573","https://openalex.org/W2549139847","https://openalex.org/W2746314669","https://openalex.org/W2963430102","https://openalex.org/W2963775347","https://openalex.org/W2964137095","https://openalex.org/W2994088087","https://openalex.org/W3118608800","https://openalex.org/W3171007011","https://openalex.org/W4295727797","https://openalex.org/W6600609147","https://openalex.org/W6727249380","https://openalex.org/W6743428213","https://openalex.org/W6751795773","https://openalex.org/W6770979763","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W4312417841","https://openalex.org/W2731899572","https://openalex.org/W3133861977","https://openalex.org/W4200173597","https://openalex.org/W3116150086","https://openalex.org/W2999805992","https://openalex.org/W3166467183","https://openalex.org/W4220996320","https://openalex.org/W2763109982","https://openalex.org/W3192840557"],"abstract_inverted_index":{"Intermediate":[0],"feature":[1,25],"regularization":[2,15,75,91,96],"is":[3,54],"a":[4],"critical":[5],"technique":[6,76],"in":[7],"machine":[8],"learning":[9],"for":[10],"computer":[11],"vision":[12],"applications":[13],"and":[14,27],"techniques":[16],"have":[17],"been":[18],"developed.":[19],"Such":[20],"methods":[21],"primarily":[22],"focus":[23,38],"on":[24,39],"regularization,":[26],"we":[28],"propose":[29],"an":[30,71],"efficient":[31],"training":[32],"strategy":[33],"with":[34],"augmented":[35,45,60],"images.":[36],"We":[37,69],"the":[40,47,56,62,86],"logit":[41,57],"consistency":[42],"of":[43,58],"images":[44,59],"from":[46,61],"same":[48,63],"base":[49,64],"image.":[50],"The":[51],"key":[52,80],"concept":[53],"that":[55,85],"image":[65],"should":[66],"be":[67],"consistent.":[68],"introduce":[70],"instance-wise":[72,88],"center":[73,89],"loss":[74,90],"to":[77],"realize":[78],"this":[79],"concept.":[81],"Experimental":[82],"results":[83],"demonstrate":[84],"proposed":[87],"effectively":[92],"improves":[93],"over":[94],"existing":[95],"techniques.":[97]},"counts_by_year":[],"updated_date":"2025-12-24T23:09:58.560324","created_date":"2025-10-10T00:00:00"}