{"id":"https://openalex.org/W4312439279","doi":"https://doi.org/10.1109/access.2022.3210710","title":"Principal Components of Neural Convolution Filters","display_name":"Principal Components of Neural Convolution Filters","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W4312439279","doi":"https://doi.org/10.1109/access.2022.3210710"},"language":"en","primary_location":{"id":"doi:10.1109/access.2022.3210710","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3210710","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09905565.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","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/ielx7/6287639/6514899/09905565.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056404527","display_name":"Shota Fukuzaki","orcid":"https://orcid.org/0000-0002-3527-690X"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shota Fukuzaki","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Keio University, Yokohama-shi, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0002-3527-690X","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Keio University, Yokohama-shi, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5090181402","display_name":"Masaaki Ikehara","orcid":"https://orcid.org/0000-0003-3461-1507"},"institutions":[{"id":"https://openalex.org/I203951103","display_name":"Keio University","ror":"https://ror.org/02kn6nx58","country_code":"JP","type":"education","lineage":["https://openalex.org/I203951103"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Masaaki Ikehara","raw_affiliation_strings":["Department of Electronics and Electrical Engineering, Keio University, Yokohama-shi, Kanagawa, Japan"],"raw_orcid":"https://orcid.org/0000-0003-3461-1507","affiliations":[{"raw_affiliation_string":"Department of Electronics and Electrical Engineering, Keio University, Yokohama-shi, Kanagawa, Japan","institution_ids":["https://openalex.org/I203951103"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I203951103"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0979,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38927424,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"10","issue":null,"first_page":"104328","last_page":"104336"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9997000098228455,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9977999925613403,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9973000288009644,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/principal-component-analysis","display_name":"Principal component analysis","score":0.7320719361305237},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6623996496200562},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6394645571708679},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5794931054115295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.566635251045227},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.49108362197875977},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4442934989929199},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.43643203377723694},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4245268702507019},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.30398035049438477},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.24868062138557434}],"concepts":[{"id":"https://openalex.org/C27438332","wikidata":"https://www.wikidata.org/wiki/Q2873","display_name":"Principal component analysis","level":2,"score":0.7320719361305237},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6623996496200562},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6394645571708679},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5794931054115295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.566635251045227},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.49108362197875977},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4442934989929199},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.43643203377723694},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4245268702507019},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.30398035049438477},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.24868062138557434},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2022.3210710","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3210710","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09905565.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:79198cb885784b219b3f32d3c1fea579","is_oa":true,"landing_page_url":"https://doaj.org/article/79198cb885784b219b3f32d3c1fea579","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 10, Pp 104328-104336 (2022)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2022.3210710","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2022.3210710","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/6514899/09905565.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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5452022097","display_name":"Research on rapid and accurate image restoration by fusion of signal processing and deep learning","funder_award_id":"20K04472","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4312439279.pdf","grobid_xml":"https://content.openalex.org/works/W4312439279.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2161004254","https://openalex.org/W2183341477","https://openalex.org/W2294798173","https://openalex.org/W2601564443","https://openalex.org/W2963107874","https://openalex.org/W2963446712","https://openalex.org/W2964301459","https://openalex.org/W2965279030","https://openalex.org/W2966926453","https://openalex.org/W3048030262","https://openalex.org/W3118608800","https://openalex.org/W3128633047","https://openalex.org/W3153412194","https://openalex.org/W3203623872","https://openalex.org/W3207523779","https://openalex.org/W4212863985","https://openalex.org/W6637373629","https://openalex.org/W6684191040","https://openalex.org/W6739901393","https://openalex.org/W6769209158","https://openalex.org/W6781575362","https://openalex.org/W6788627230","https://openalex.org/W6790428460","https://openalex.org/W6793164127","https://openalex.org/W6795140394","https://openalex.org/W6796931752","https://openalex.org/W6799081378"],"related_works":["https://openalex.org/W1975632186","https://openalex.org/W3027745756","https://openalex.org/W3205213561","https://openalex.org/W4386858688","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4380302312","https://openalex.org/W4390971171","https://openalex.org/W4385338604","https://openalex.org/W3081626085"],"abstract_inverted_index":{"Convolutions":[0],"in":[1,140],"neural":[2,13,116],"networks":[3],"are":[4],"still":[5],"essential":[6],"on":[7,18,98,156],"various":[8],"vision":[9],"tasks.":[10],"To":[11],"develop":[12,127],"convolutions,":[14],"this":[15],"study":[16],"focuses":[17],"Structured":[19],"Receptive":[20],"Field":[21],"(SRF),":[22],"representing":[23],"a":[24,28,77,128,141],"convolution":[25,40,117],"filter":[26,49,62,105],"as":[27],"linear":[29,142],"combination":[30,143],"of":[31,48,103,144],"widely":[32],"acting":[33],"designed":[34],"components.":[35,90,146,200],"Although":[36],"SRF":[37,82],"can":[38,84],"represent":[39,85],"filters":[41,87],"with":[42,88,167,175,189,198,203,233],"fewer":[43,89],"components":[44,110,177,205],"than":[45,181,187,196,209,214],"the":[46,52,99,108,123,138,148,160,164,168,182,215],"number":[47],"bins,":[50],"N-Jet,":[51,210],"sole":[53],"component":[54,79,92,124,129],"system":[55,80,93],"implementation,":[56],"requires":[57],"ten":[58,199],"trainable":[59],"parameters":[60],"per":[61],"to":[63,75,121,132],"improve":[64],"accuracy":[65],"even":[66],"for":[67,81,115,163,217],"3":[68,70],"\u00d7":[69],"convolutions.":[71,170],"Hence,":[72],"we":[73,126,151],"aim":[74],"formulate":[76],"new":[78],"that":[83],"valid":[86],"Our":[91],"named":[94],"\u201cOtX\u201d":[95],"is":[96],"based":[97],"Principal":[100],"Component":[101],"Analysis":[102],"well-trained":[104],"weights":[106],"because":[107,225],"extracted":[109],"will":[111],"also":[112],"be":[113],"principal":[114],"filters.":[118],"In":[119,147],"addition":[120],"proposing":[122],"system,":[125],"scaling":[130],"method":[131],"defuse":[133],"massive":[134],"scale":[135],"differences":[136],"among":[137],"coefficients":[139],"OtX":[145,174,202,219,226],"experimental":[149],"section,":[150],"train":[152],"image":[153],"classification":[154],"models":[155,166],"CIFAR-100":[157],"dataset":[158],"under":[159],"hyperparameters":[161],"tuned":[162],"original":[165],"standard":[169,183,216,223],"For":[171],"NFNet-F0":[172],"classifier,":[173],"six":[176,190],"performs":[178,227],"0.5%":[179,212],"better":[180,186,213],"convolution,":[184],"3.1%":[185],"N-Jet":[188,197,232],"components,":[191],"and":[192,237],"only":[193],"0.1%":[194],"worse":[195],"Besides,":[201],"nine":[204],"provides":[206],"stabler":[207],"training":[208,238],"performing":[211],"NFNet-F0.":[218],"suits":[220],"when":[221],"replacing":[222],"convolutions":[224],"at":[228],"least":[229],"comparably":[230],"against":[231],"further":[234],"parameter":[235],"efficiency":[236],"stability.":[239]},"counts_by_year":[{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}