{"id":"https://openalex.org/W2971337223","doi":"https://doi.org/10.1109/icip.2019.8802962","title":"DCT Based Information-Preserving Pooling for Deep Neural Networks","display_name":"DCT Based Information-Preserving Pooling for Deep Neural Networks","publication_year":2019,"publication_date":"2019-08-26","ids":{"openalex":"https://openalex.org/W2971337223","doi":"https://doi.org/10.1109/icip.2019.8802962","mag":"2971337223"},"language":"en","primary_location":{"id":"doi:10.1109/icip.2019.8802962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8802962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"},"type":"conference-paper","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":false,"raw_author_name":"Yuhao Xu","raw_affiliation_strings":["University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"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":["University of Tokyo, Tokyo, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Tokyo, Tokyo, Japan","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"894","last_page":"898"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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/T10500","display_name":"Sparse and Compressive Sensing Techniques","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"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/T11019","display_name":"Image Enhancement Techniques","score":0.9980999827384949,"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/pooling","display_name":"Pooling","score":0.9318195581436157},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.8789228796958923},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.70389723777771},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6747251749038696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6037837862968445},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4965129494667053},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.4817228615283966},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.45661821961402893},{"id":"https://openalex.org/keywords/discrete-fourier-transform","display_name":"Discrete Fourier transform (general)","score":0.42874276638031006},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3355766534805298},{"id":"https://openalex.org/keywords/fourier-transform","display_name":"Fourier transform","score":0.33389806747436523},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.2514297366142273},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19320416450500488},{"id":"https://openalex.org/keywords/fractional-fourier-transform","display_name":"Fractional Fourier transform","score":0.09582820534706116},{"id":"https://openalex.org/keywords/fourier-analysis","display_name":"Fourier analysis","score":0.06507858633995056}],"concepts":[{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.9318195581436157},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.8789228796958923},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.70389723777771},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6747251749038696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6037837862968445},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4965129494667053},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.4817228615283966},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45661821961402893},{"id":"https://openalex.org/C57733114","wikidata":"https://www.wikidata.org/wiki/Q1006032","display_name":"Discrete Fourier transform (general)","level":5,"score":0.42874276638031006},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3355766534805298},{"id":"https://openalex.org/C102519508","wikidata":"https://www.wikidata.org/wiki/Q6520159","display_name":"Fourier transform","level":2,"score":0.33389806747436523},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.2514297366142273},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19320416450500488},{"id":"https://openalex.org/C76563020","wikidata":"https://www.wikidata.org/wiki/Q4817582","display_name":"Fractional Fourier transform","level":4,"score":0.09582820534706116},{"id":"https://openalex.org/C203024314","wikidata":"https://www.wikidata.org/wiki/Q1365258","display_name":"Fourier analysis","level":3,"score":0.06507858633995056},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip.2019.8802962","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip.2019.8802962","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Image Processing (ICIP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.9100000262260437,"id":"https://metadata.un.org/sdg/7"}],"awards":[{"id":"https://openalex.org/G5912977134","display_name":"Building World Knowledge by Grounding Language and Multimedia","funder_award_id":"19H04166","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":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1686810756","https://openalex.org/W1789336918","https://openalex.org/W1836465849","https://openalex.org/W1839118408","https://openalex.org/W1840106123","https://openalex.org/W1907282891","https://openalex.org/W1922123711","https://openalex.org/W2031614119","https://openalex.org/W2060365990","https://openalex.org/W2061171222","https://openalex.org/W2097117768","https://openalex.org/W2118858186","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2311654837","https://openalex.org/W2554242204","https://openalex.org/W2559156603","https://openalex.org/W2802252728","https://openalex.org/W2896786907","https://openalex.org/W2949117887","https://openalex.org/W2963340555","https://openalex.org/W2963574257","https://openalex.org/W2964012402","https://openalex.org/W2964121744","https://openalex.org/W3118608800","https://openalex.org/W3217577904","https://openalex.org/W6631190155","https://openalex.org/W6637373629","https://openalex.org/W6638020065","https://openalex.org/W6638667902","https://openalex.org/W6638946568","https://openalex.org/W6639736908","https://openalex.org/W6640442106","https://openalex.org/W6677919164","https://openalex.org/W6681583683","https://openalex.org/W6684191040","https://openalex.org/W6729623471","https://openalex.org/W6787972765"],"related_works":["https://openalex.org/W2559156603","https://openalex.org/W4287394948","https://openalex.org/W4300832495","https://openalex.org/W2987852271","https://openalex.org/W2967990525","https://openalex.org/W2949066288","https://openalex.org/W3119356360","https://openalex.org/W3202075396","https://openalex.org/W4214604401","https://openalex.org/W2137224175"],"abstract_inverted_index":{"Pooling":[0],"is":[1,46],"used":[2],"in":[3,15],"most":[4],"of":[5,89],"deep":[6,67],"convolutional":[7],"neural":[8,68],"networks":[9],"as":[10,48],"a":[11,57],"feature":[12],"downsampling":[13],"method,":[14],"order":[16],"to":[17,34,71],"reduce":[18],"computation":[19],"complexity":[20],"and":[21,96,104],"increase":[22],"the":[23,28,72,87,93,112],"receptive":[24],"field":[25],"size.":[26],"Since":[27],"traditional":[29],"max/average":[30],"pooling":[31,40,64,77,116,120],"layers":[32,101],"tend":[33],"cause":[35],"severe":[36],"information":[37,81],"loss,":[38],"spectral":[39],"with":[41,127],"discrete":[42],"Fourier":[43],"transform":[44,61,94],"(DFT)":[45],"considered":[47],"an":[49],"advisable":[50],"alternative.":[51],"In":[52],"this":[53],"paper,":[54],"we":[55,91],"propose":[56],"novel":[58],"2D-discrete":[59],"cosine":[60],"(2D-DCT)":[62],"based":[63,115],"method":[65],"for":[66,102],"networks.":[69],"Due":[70],"energy":[73],"compaction":[74],"property,":[75],"DCT":[76,114],"preserves":[78],"considerably":[79],"more":[80],"than":[82],"DFT.":[83],"Moreover,":[84],"inspired":[85],"by":[86],"separability":[88],"DCT,":[90],"precompute":[92],"matrices":[95],"embed":[97],"them":[98],"into":[99],"linear":[100],"parallelization":[103],"acceleration":[105],"on":[106,122],"GPUs.":[107],"Experimental":[108],"results":[109],"indicate":[110],"that":[111],"proposed":[113],"layer":[117],"outperforms":[118],"previous":[119],"methods":[121],"multiple":[123],"image":[124],"classification":[125],"datasets":[126],"negligible":[128],"extra":[129],"time":[130],"consumption.":[131]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}