{"id":"https://openalex.org/W2382313035","doi":"https://doi.org/10.1145/2939672.2939839","title":"Compressing Convolutional Neural Networks in the Frequency Domain","display_name":"Compressing Convolutional Neural Networks in the Frequency Domain","publication_year":2016,"publication_date":"2016-08-08","ids":{"openalex":"https://openalex.org/W2382313035","doi":"https://doi.org/10.1145/2939672.2939839","mag":"2382313035"},"language":"en","primary_location":{"id":"doi:10.1145/2939672.2939839","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2939672.2939839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","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/A5100734874","display_name":"Wenlin Chen","orcid":"https://orcid.org/0000-0002-0939-0733"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wenlin Chen","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5011507387","display_name":"James T. Wilson","orcid":"https://orcid.org/0000-0001-5017-0954"},"institutions":[{"id":"https://openalex.org/I98677209","display_name":"University of Edinburgh","ror":"https://ror.org/01nrxwf90","country_code":"GB","type":"education","lineage":["https://openalex.org/I98677209"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"James Wilson","raw_affiliation_strings":["University of Edinburgh, Edinburgh, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Edinburgh, Edinburgh, United Kingdom","institution_ids":["https://openalex.org/I98677209"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073763227","display_name":"Stephen Tyree","orcid":null},"institutions":[{"id":"https://openalex.org/I4210127875","display_name":"Nvidia (United States)","ror":"https://ror.org/03jdj4y14","country_code":"US","type":"company","lineage":["https://openalex.org/I4210127875"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Stephen Tyree","raw_affiliation_strings":["Nvidia, Santa Clara, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nvidia, Santa Clara, CA, USA","institution_ids":["https://openalex.org/I4210127875"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006380227","display_name":"Kilian Q. Weinberger","orcid":null},"institutions":[{"id":"https://openalex.org/I205783295","display_name":"Cornell University","ror":"https://ror.org/05bnh6r87","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kilian Q. Weinberger","raw_affiliation_strings":["Cornell University, Ithaca, NY, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Cornell University, Ithaca, NY, USA","institution_ids":["https://openalex.org/I205783295"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100393445","display_name":"Yixin Chen","orcid":"https://orcid.org/0000-0002-3704-4432"},"institutions":[{"id":"https://openalex.org/I204465549","display_name":"Washington University in St. Louis","ror":"https://ror.org/01yc7t268","country_code":"US","type":"education","lineage":["https://openalex.org/I204465549"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yixin Chen","raw_affiliation_strings":["Washington University in St. Louis, St. Louis, MO, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Washington University in St. Louis, St. Louis, MO, USA","institution_ids":["https://openalex.org/I204465549"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":139,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1475","last_page":"1484"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10812","display_name":"Human Pose and Action Recognition","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/T11019","display_name":"Image Enhancement Techniques","score":0.9983000159263611,"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/computer-science","display_name":"Computer science","score":0.8388233184814453},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.8262764811515808},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7974894046783447},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6073816418647766},{"id":"https://openalex.org/keywords/discrete-cosine-transform","display_name":"Discrete cosine transform","score":0.5875985622406006},{"id":"https://openalex.org/keywords/frequency-domain","display_name":"Frequency domain","score":0.5134099721908569},{"id":"https://openalex.org/keywords/convolutional-code","display_name":"Convolutional code","score":0.49223318696022034},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.444031685590744},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37686029076576233},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.35608163475990295},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3278244137763977},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2883710265159607},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.16691207885742188},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15524688363075256},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.102763831615448}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8388233184814453},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.8262764811515808},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7974894046783447},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6073816418647766},{"id":"https://openalex.org/C2221639","wikidata":"https://www.wikidata.org/wiki/Q2877","display_name":"Discrete cosine transform","level":3,"score":0.5875985622406006},{"id":"https://openalex.org/C19118579","wikidata":"https://www.wikidata.org/wiki/Q786423","display_name":"Frequency domain","level":2,"score":0.5134099721908569},{"id":"https://openalex.org/C157899210","wikidata":"https://www.wikidata.org/wiki/Q1395022","display_name":"Convolutional code","level":3,"score":0.49223318696022034},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.444031685590744},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37686029076576233},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.35608163475990295},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3278244137763977},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2883710265159607},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.16691207885742188},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15524688363075256},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.102763831615448},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2939672.2939839","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2939672.2939839","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G8915916487","display_name":null,"funder_award_id":"CCF-1215302, IIS-1343896, DBI-1356669, CNS-1320921, IIA-1355406, IIS-1149882, EFRI-1137211","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320308943","display_name":"Microsoft Research","ror":"https://ror.org/00d0nc645"},{"id":"https://openalex.org/F4320337395","display_name":"Division of Emerging Frontiers in Research and Innovation","ror":"https://ror.org/0388pet74"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":67,"referenced_works":["https://openalex.org/W104184427","https://openalex.org/W175700287","https://openalex.org/W202805564","https://openalex.org/W753012316","https://openalex.org/W1487583988","https://openalex.org/W1554663460","https://openalex.org/W1583837637","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1724438581","https://openalex.org/W1789336918","https://openalex.org/W1849277567","https://openalex.org/W1895577753","https://openalex.org/W1902934009","https://openalex.org/W1903029394","https://openalex.org/W1905882502","https://openalex.org/W1916685473","https://openalex.org/W1922123711","https://openalex.org/W1994197834","https://openalex.org/W1996901117","https://openalex.org/W2016053056","https://openalex.org/W2030265202","https://openalex.org/W2031614119","https://openalex.org/W2040903332","https://openalex.org/W2062118960","https://openalex.org/W2070996757","https://openalex.org/W2085927849","https://openalex.org/W2101926813","https://openalex.org/W2102605133","https://openalex.org/W2107789863","https://openalex.org/W2108598243","https://openalex.org/W2112490010","https://openalex.org/W2112796928","https://openalex.org/W2114508814","https://openalex.org/W2121775913","https://openalex.org/W2131524184","https://openalex.org/W2134797427","https://openalex.org/W2145287260","https://openalex.org/W2146502635","https://openalex.org/W2155217764","https://openalex.org/W2155541015","https://openalex.org/W2163605009","https://openalex.org/W2167215970","https://openalex.org/W2218318129","https://openalex.org/W2294370754","https://openalex.org/W2308045930","https://openalex.org/W2335728318","https://openalex.org/W2488789499","https://openalex.org/W2559655401","https://openalex.org/W2594481151","https://openalex.org/W2597289420","https://openalex.org/W2604272474","https://openalex.org/W2752885492","https://openalex.org/W2950182411","https://openalex.org/W2951845198","https://openalex.org/W2952432176","https://openalex.org/W2952881492","https://openalex.org/W2952899695","https://openalex.org/W2962706528","https://openalex.org/W2962988160","https://openalex.org/W2963674932","https://openalex.org/W2998508934","https://openalex.org/W3000138670","https://openalex.org/W3099206234","https://openalex.org/W3118608800","https://openalex.org/W4246219036","https://openalex.org/W4299828299"],"related_works":["https://openalex.org/W1916685473","https://openalex.org/W2055682261","https://openalex.org/W1993363272","https://openalex.org/W2186390138","https://openalex.org/W2060035984","https://openalex.org/W2790129917","https://openalex.org/W2992856432","https://openalex.org/W2100638064","https://openalex.org/W2127787376","https://openalex.org/W2534655758"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNN)":[3],"are":[4,14,113,176],"increasingly":[5],"used":[6],"in":[7,80,96],"many":[8,48],"areas":[9],"of":[10,18,25,30,44,87,109],"computer":[11],"vision.":[12],"They":[13],"particularly":[15],"attractive":[16],"because":[17],"their":[19],"ability":[20],"to":[21,93,123,139,172,192],"\"absorb\"":[22],"great":[23],"quantities":[24],"labeled":[26],"data":[27,185],"through":[28],"millions":[29],"parameters.":[31],"However,":[32],"as":[33,51],"model":[34,165],"sizes":[35],"increase,":[36],"so":[37],"do":[38],"the":[39,45,103,107,124,150],"storage":[40,99],"and":[41,53,59,84,98,116,133,187],"memory":[42,97],"requirements":[43],"classifiers,":[46],"hindering":[47],"applications":[49],"such":[50],"image":[52],"speech":[54],"recognition":[55],"on":[56,102,183],"mobile":[57],"phones":[58],"other":[60],"devices.":[61],"In":[62],"this":[63],"paper,":[64],"we":[65,118,167],"present":[66],"a":[67,88,128,135,155],"novel":[68],"net-":[69],"work":[70],"architecture,":[71],"Frequency-Sensitive":[72],"Hashed":[73],"Nets":[74],"(FreshNets),":[75],"which":[76,175],"exploits":[77],"inherent":[78],"redundancy":[79],"both":[81],"convolutional":[82,111],"layers":[83,86],"fully-connected":[85],"deep":[89],"learning":[90],"model,":[91],"leading":[92],"dramatic":[94],"savings":[95],"consumption.":[100],"Based":[101],"key":[104],"observation":[105],"that":[106,189],"weights":[108,122],"learned":[110,158],"filters":[112],"typically":[114],"smooth":[115],"low-frequency,":[117],"first":[119],"convert":[120],"filter":[121],"frequency":[125,142],"domain":[126],"with":[127,159],"discrete":[129],"cosine":[130],"transform":[131],"(DCT)":[132],"use":[134],"low-cost":[136],"hash":[137,145,152,170],"function":[138],"randomly":[140],"group":[141],"parameters":[143,148],"into":[144],"buckets.":[146],"All":[147],"assigned":[149],"same":[151],"bucket":[153],"share":[154],"single":[156],"value":[157],"standard":[160],"back-propagation.":[161],"To":[162],"further":[163],"reduce":[164],"size,":[166],"allocate":[168],"fewer":[169],"buckets":[171],"high-frequency":[173],"components,":[174],"generally":[177],"less":[178],"important.":[179],"We":[180],"evaluate":[181],"FreshNets":[182],"eight":[184],"sets,":[186],"show":[188],"it":[190],"leads":[191],"better":[193],"compressed":[194],"performance":[195],"than":[196],"several":[197],"relevant":[198],"baselines.":[199]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":11},{"year":2023,"cited_by_count":18},{"year":2022,"cited_by_count":12},{"year":2021,"cited_by_count":24},{"year":2020,"cited_by_count":17},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":17},{"year":2017,"cited_by_count":14},{"year":2016,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}