{"id":"https://openalex.org/W3204449597","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534135","title":"DCT-based Fast Spectral Convolution for Deep Convolutional Neural Networks","display_name":"DCT-based Fast Spectral Convolution for Deep Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3204449597","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534135","mag":"3204449597"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5029688192","display_name":"Yuhao Xu","orcid":"https://orcid.org/0000-0003-0334-2260"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Yuhao Xu","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050229964","display_name":"Hideki Nakayama","orcid":"https://orcid.org/0000-0001-8726-2780"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Hideki Nakayama","raw_affiliation_strings":["Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan"],"affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, The University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5029688192"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.3876,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.61572994,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9976999759674072,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9976999759674072,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9936000108718872,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9925000071525574,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.8087680339813232},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7693566679954529},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.7418510317802429},{"id":"https://openalex.org/keywords/convolution-theorem","display_name":"Convolution theorem","score":0.6479894518852234},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.6459090113639832},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6426243782043457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5514720678329468},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5136474967002869},{"id":"https://openalex.org/keywords/circular-convolution","display_name":"Circular convolution","score":0.46390220522880554},{"id":"https://openalex.org/keywords/overlap\u2013add-method","display_name":"Overlap\u2013add method","score":0.45759329199790955},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4446057677268982},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.4219960570335388},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.41936972737312317},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.41542819142341614},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41236236691474915},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.40417325496673584},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3769722580909729},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.19589164853096008},{"id":"https://openalex.org/keywords/fractional-fourier-transform","display_name":"Fractional Fourier transform","score":0.15607210993766785},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.1360868513584137},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.11728471517562866},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.11034694314002991},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.09083938598632812},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.0703602135181427}],"concepts":[{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.8087680339813232},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7693566679954529},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.7418510317802429},{"id":"https://openalex.org/C79587385","wikidata":"https://www.wikidata.org/wiki/Q2638931","display_name":"Convolution theorem","level":5,"score":0.6479894518852234},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.6459090113639832},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6426243782043457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5514720678329468},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5136474967002869},{"id":"https://openalex.org/C194980680","wikidata":"https://www.wikidata.org/wiki/Q245450","display_name":"Circular convolution","level":5,"score":0.46390220522880554},{"id":"https://openalex.org/C181002996","wikidata":"https://www.wikidata.org/wiki/Q1611641","display_name":"Overlap\u2013add method","level":5,"score":0.45759329199790955},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4446057677268982},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.4219960570335388},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.41936972737312317},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.41542819142341614},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41236236691474915},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.40417325496673584},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3769722580909729},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.19589164853096008},{"id":"https://openalex.org/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.15607210993766785},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.1360868513584137},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.11728471517562866},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.11034694314002991},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.09083938598632812},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.0703602135181427},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534135","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534135","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1839118408","https://openalex.org/W1922123711","https://openalex.org/W1977993134","https://openalex.org/W2061171222","https://openalex.org/W2095705004","https://openalex.org/W2097117768","https://openalex.org/W2117539524","https://openalex.org/W2128749318","https://openalex.org/W2138692623","https://openalex.org/W2163605009","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2255738257","https://openalex.org/W2311654837","https://openalex.org/W2554242204","https://openalex.org/W2584616277","https://openalex.org/W2609675817","https://openalex.org/W2618530766","https://openalex.org/W2896786907","https://openalex.org/W2963340555","https://openalex.org/W2963751813","https://openalex.org/W2971337223","https://openalex.org/W2987748894","https://openalex.org/W3022930687","https://openalex.org/W3034771037","https://openalex.org/W3118608800","https://openalex.org/W3217577904","https://openalex.org/W6637373629","https://openalex.org/W6638020065","https://openalex.org/W6638946568","https://openalex.org/W6640442106","https://openalex.org/W6674330103","https://openalex.org/W6681583683","https://openalex.org/W6691901705","https://openalex.org/W6729623471","https://openalex.org/W6777058707"],"related_works":["https://openalex.org/W2133436097","https://openalex.org/W2170755202","https://openalex.org/W4386106541","https://openalex.org/W2106721858","https://openalex.org/W61755830","https://openalex.org/W2053055950","https://openalex.org/W2110104525","https://openalex.org/W2483197055","https://openalex.org/W2162994284","https://openalex.org/W2162611351"],"abstract_inverted_index":{"Spectral":[0],"representations":[1],"have":[2],"been":[3],"introduced":[4],"into":[5,86],"deep":[6],"convolutional":[7,84],"neural":[8],"networks":[9,200],"(CNNs)":[10],"mainly":[11],"for":[12,74],"accelerating":[13],"convolutions":[14],"and":[15,23,67,83,102,189],"mitigating":[16],"information":[17],"loss.":[18],"However,":[19],"repeated":[20,153],"domain":[21,89,114,154],"transformations":[22,155],"complex":[24],"arithmetic":[25],"of":[26,36,65,132],"commonly-used":[27],"Fourier":[28],"transform":[29,43,78],"(DFT,":[30],"FFT)":[31],"seriously":[32],"limit":[33],"the":[34,62,79,87,98,112,119,129,139,157,174,199],"applicability":[35],"spectral":[37,71,99,142,170,190,195],"networks.":[38],"In":[39],"contrast,":[40],"discrete":[41],"cosine":[42],"(DCT)-based":[44],"methods":[45],"are":[46],"more":[47],"promising":[48],"owing":[49],"to":[50,108,151,172],"computations":[51],"with":[52,169,186],"merely":[53],"real":[54,127],"numbers.":[55],"Hence":[56],"in":[57,111],"this":[58],"work,":[59],"we":[60,77,145,162],"investigate":[61],"convolution":[63,72,110,196],"theorem":[64],"DCT":[66,124],"propose":[68],"a":[69,147,164],"faster":[70],"method":[73,134],"CNNs.":[75],"First,":[76],"input":[80],"feature":[81,100],"map":[82,101],"kernel":[85,179],"frequency":[88],"via":[90],"DCT.":[91],"We":[92],"then":[93],"perform":[94],"element-wise":[95],"multiplication":[96],"between":[97],"kernel,":[103],"which":[104],"is":[105,135],"mathematically":[106],"equivalent":[107],"symmetric":[109],"spatial":[113,121,188],"but":[115],"much":[116],"cheaper":[117],"than":[118,138],"straightforward":[120],"convolution.":[122,143],"Since":[123],"only":[125],"involves":[126],"arithmetic,":[128],"computational":[130],"complexity":[131],"our":[133,192],"significantly":[136],"smaller":[137],"traditional":[140,187],"FFT-based":[141],"Besides,":[144],"introduce":[146],"network":[148],"optimization":[149],"strategy":[150,168],"suppress":[152],"leveraging":[156],"intrinsically":[158],"extended":[159],"kernels.":[160],"Furthermore,":[161],"present":[163],"partial":[165],"symmetry":[166],"breaking":[167],"dropout":[171],"mitigate":[173],"performance":[175],"degradation":[176],"caused":[177],"by":[178],"symmetry.":[180],"Experimental":[181],"results":[182],"demonstrate":[183],"that":[184],"compared":[185],"methods,":[191],"proposed":[193],"DCT-based":[194],"effectively":[197],"accelerates":[198],"while":[201],"achieving":[202],"comparable":[203],"accuracy.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1}],"updated_date":"2026-03-28T08:17:26.163206","created_date":"2025-10-10T00:00:00"}