{"id":"https://openalex.org/W3193704648","doi":"https://doi.org/10.1109/icip42928.2021.9506696","title":"Knowledge Transferred Fine-Tuning for Anti-Aliased Convolutional Neural Network in Data-Limited Situation","display_name":"Knowledge Transferred Fine-Tuning for Anti-Aliased Convolutional Neural Network in Data-Limited Situation","publication_year":2021,"publication_date":"2021-08-23","ids":{"openalex":"https://openalex.org/W3193704648","doi":"https://doi.org/10.1109/icip42928.2021.9506696","mag":"3193704648"},"language":"en","primary_location":{"id":"doi:10.1109/icip42928.2021.9506696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","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/A5063110877","display_name":"Satoshi Suzuki","orcid":"https://orcid.org/0000-0002-1423-3767"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]},{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Satoshi Suzuki","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation,Japan","University of Electro-Communications, Japan","NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"University of Electro-Communications, Japan","institution_ids":["https://openalex.org/I20529979"]},{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006634833","display_name":"Shoichiro Takeda","orcid":"https://orcid.org/0000-0002-7138-4983"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shoichiro Takeda","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation,Japan","NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060947560","display_name":"Ryuichi Tanida","orcid":"https://orcid.org/0000-0002-5379-3150"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ryuichi Tanida","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation,Japan","NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5079940782","display_name":"Hideaki Kimata","orcid":"https://orcid.org/0000-0003-1287-6862"},"institutions":[{"id":"https://openalex.org/I2251713219","display_name":"NTT (Japan)","ror":"https://ror.org/00berct97","country_code":"JP","type":"company","lineage":["https://openalex.org/I2251713219"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideaki Kimata","raw_affiliation_strings":["NTT Media Intelligence Laboratories, NTT Corporation,Japan","NTT Media Intelligence Laboratories, NTT Corporation, Japan"],"affiliations":[{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation,Japan","institution_ids":["https://openalex.org/I2251713219"]},{"raw_affiliation_string":"NTT Media Intelligence Laboratories, NTT Corporation, Japan","institution_ids":["https://openalex.org/I2251713219"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5064042196","display_name":"Hayaru Shouno","orcid":"https://orcid.org/0000-0002-2412-0184"},"institutions":[{"id":"https://openalex.org/I20529979","display_name":"University of Electro-Communications","ror":"https://ror.org/02x73b849","country_code":"JP","type":"education","lineage":["https://openalex.org/I20529979"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hayaru Shouno","raw_affiliation_strings":["University of Electro-Communications,Department of Informatics,Japan"],"affiliations":[{"raw_affiliation_string":"University of Electro-Communications,Department of Informatics,Japan","institution_ids":["https://openalex.org/I20529979"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5063110877"],"corresponding_institution_ids":["https://openalex.org/I20529979","https://openalex.org/I2251713219"],"apc_list":null,"apc_paid":null,"fwci":0.0961,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.38669935,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"864","last_page":"868"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9987999796867371,"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":0.9987999796867371,"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/T12676","display_name":"Machine Learning and ELM","score":0.9959999918937683,"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"}},{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9957000017166138,"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":0.7527905702590942},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7361546754837036},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.42116862535476685}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527905702590942},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7361546754837036},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.42116862535476685}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip42928.2021.9506696","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip42928.2021.9506696","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Conference on Image Processing (ICIP)","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":26,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1690739335","https://openalex.org/W1821462560","https://openalex.org/W2010315761","https://openalex.org/W2101926813","https://openalex.org/W2108598243","https://openalex.org/W2134120396","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2203224402","https://openalex.org/W2296073425","https://openalex.org/W2803023299","https://openalex.org/W2804935296","https://openalex.org/W2810989615","https://openalex.org/W2913314773","https://openalex.org/W2963460174","https://openalex.org/W3035006120","https://openalex.org/W6637373629","https://openalex.org/W6637551013","https://openalex.org/W6638444622","https://openalex.org/W6638523607","https://openalex.org/W6684191040","https://openalex.org/W6751751081","https://openalex.org/W6752549325","https://openalex.org/W6758857762","https://openalex.org/W6780028523"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4293226380","https://openalex.org/W4396696052","https://openalex.org/W4402327032"],"abstract_inverted_index":{"Anti-aliased":[0],"convolutional":[1],"neural":[2],"networks":[3],"(CNNs)":[4],"introduce":[5],"blur":[6,39,42],"filters":[7,43],"to":[8,13,20,27,53,78,114],"intermediate":[9,108],"representations":[10,109],"in":[11,110],"CNNs":[12],"achieve":[14],"high":[15],"accuracy.":[16],"A":[17],"promising":[18],"way":[19],"build":[21],"a":[22,29,126,134],"new":[23],"antialiased":[24],"CNN":[25,113,117],"is":[26,67],"fine-tune":[28],"pre-trained":[30,47,112],"CNN,":[31],"which":[32],"can":[33],"easily":[34],"be":[35],"found":[36],"online,":[37],"with":[38],"filters.":[40],"However,":[41],"drastically":[44],"degrade":[45],"the":[46,50,55,64,69,79,94,97,105,111,115,149],"representation,":[48],"so":[49],"fine-tuning":[51,70,151],"needs":[52],"rebuild":[54],"representation":[56],"by":[57],"using":[58,125],"massive":[59],"training":[60,65,81],"data.":[61,82],"Therefore,":[62],"if":[63],"data":[66],"limited,":[68],"cannot":[71],"work":[72],"well":[73],"because":[74],"it":[75],"induces":[76],"overfitting":[77],"limited":[80],"To":[83],"tackle":[84],"this":[85,87],"problem,":[86],"paper":[88],"proposes":[89],"\u201cknowledge":[90],"transferred":[91],"fine-tuning\u201d.":[92],"On":[93],"basis":[95],"of":[96,99],"idea":[98],"knowledge":[100,106,124,132],"transfer,":[101],"our":[102,145],"method":[103,146],"transfers":[104,130,138],"from":[107],"anti-aliased":[116],"while":[118],"fine-tuning.":[119],"We":[120],"transfer":[121],"only":[122],"essential":[123],"pixel-level":[127],"loss":[128,136],"that":[129,137,144],"detailed":[131],"and":[133],"global-level":[135],"coarse":[139],"knowledge.":[140],"Experimental":[141],"results":[142],"demonstrate":[143],"significantly":[147],"outperforms":[148],"simple":[150],"method.":[152]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-25T08:12:03.925757","created_date":"2025-10-10T00:00:00"}