{"id":"https://openalex.org/W3090303800","doi":"https://doi.org/10.1145/3410463.3414642","title":"Fast Convolutional Neural Networks with Fine-Grained FFTs","display_name":"Fast Convolutional Neural Networks with Fine-Grained FFTs","publication_year":2020,"publication_date":"2020-09-30","ids":{"openalex":"https://openalex.org/W3090303800","doi":"https://doi.org/10.1145/3410463.3414642","mag":"3090303800"},"language":"en","primary_location":{"id":"doi:10.1145/3410463.3414642","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410463.3414642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","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/A5100778270","display_name":"Yulin Zhang","orcid":"https://orcid.org/0000-0001-7231-3880"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Yulin Zhang","raw_affiliation_strings":["University of Delaware, Newark, DE, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100452126","display_name":"Xiaoming Li","orcid":"https://orcid.org/0000-0002-3059-9793"},"institutions":[{"id":"https://openalex.org/I86501945","display_name":"University of Delaware","ror":"https://ror.org/01sbq1a82","country_code":"US","type":"education","lineage":["https://openalex.org/I86501945"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xiaoming Li","raw_affiliation_strings":["University of Delaware, Newark, DE, USA"],"affiliations":[{"raw_affiliation_string":"University of Delaware, Newark, DE, USA","institution_ids":["https://openalex.org/I86501945"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100778270"],"corresponding_institution_ids":["https://openalex.org/I86501945"],"apc_list":null,"apc_paid":null,"fwci":0.1954,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.50119312,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"255","last_page":"265"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9980999827384949,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9972000122070312,"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/speedup","display_name":"Speedup","score":0.9332366585731506},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7831127643585205},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7390608191490173},{"id":"https://openalex.org/keywords/fast-fourier-transform","display_name":"Fast Fourier transform","score":0.6945275068283081},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6676337122917175},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.6249030828475952},{"id":"https://openalex.org/keywords/redundancy","display_name":"Redundancy (engineering)","score":0.6108740568161011},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.48057031631469727},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4341449737548828},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.4293849766254425},{"id":"https://openalex.org/keywords/data-redundancy","display_name":"Data redundancy","score":0.4140194058418274},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.36296966671943665},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3526604175567627},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3228874206542969},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2725268006324768}],"concepts":[{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.9332366585731506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7831127643585205},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7390608191490173},{"id":"https://openalex.org/C75172450","wikidata":"https://www.wikidata.org/wiki/Q623950","display_name":"Fast Fourier transform","level":2,"score":0.6945275068283081},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6676337122917175},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.6249030828475952},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.6108740568161011},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.48057031631469727},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4341449737548828},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.4293849766254425},{"id":"https://openalex.org/C7545210","wikidata":"https://www.wikidata.org/wiki/Q838123","display_name":"Data redundancy","level":2,"score":0.4140194058418274},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.36296966671943665},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3526604175567627},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3228874206542969},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2725268006324768},{"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:10.1145/3410463.3414642","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3410463.3414642","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the ACM International Conference on Parallel Architectures and Compilation Techniques","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W753012316","https://openalex.org/W1005811612","https://openalex.org/W1487564550","https://openalex.org/W1505943803","https://openalex.org/W1530262073","https://openalex.org/W1667652561","https://openalex.org/W1789336918","https://openalex.org/W1843951383","https://openalex.org/W1922123711","https://openalex.org/W2015861736","https://openalex.org/W2035476608","https://openalex.org/W2040062623","https://openalex.org/W2097117768","https://openalex.org/W2112796928","https://openalex.org/W2120284346","https://openalex.org/W2132105090","https://openalex.org/W2147800946","https://openalex.org/W2155893237","https://openalex.org/W2163605009","https://openalex.org/W2172654076","https://openalex.org/W2194775991","https://openalex.org/W2255738257","https://openalex.org/W2342840547","https://openalex.org/W2346804249","https://openalex.org/W2384495648","https://openalex.org/W2397599589","https://openalex.org/W2402144811","https://openalex.org/W2432982300","https://openalex.org/W2504108613","https://openalex.org/W2521727659","https://openalex.org/W2530879419","https://openalex.org/W2603276336","https://openalex.org/W2752853835","https://openalex.org/W2912918068","https://openalex.org/W2919115771","https://openalex.org/W2949117887","https://openalex.org/W2963542991","https://openalex.org/W4206196235","https://openalex.org/W4212774754"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2027972911","https://openalex.org/W2146343568","https://openalex.org/W2013643406","https://openalex.org/W2157978810","https://openalex.org/W1969153118","https://openalex.org/W3157543420"],"abstract_inverted_index":{"The":[0,16,52,65],"Convolutional":[1],"Neural":[2],"Networks":[3],"(CNNs)":[4],"architecture":[5],"is":[6,21,70],"one":[7,175],"of":[8,19,67,84,97,106,176,220],"the":[9,24,28,39,46,95,104,107,111,125,155,168,177,221],"most":[10,178],"widely":[11,179],"used":[12,180],"deep":[13],"learning":[14],"tools.":[15],"execution":[17],"time":[18,25],"CNNs":[20,32,181,209],"dominated":[22],"by":[23,110,184],"spent":[26],"on":[27,131,147,160,202],"convolution":[29,40,54,140,191],"steps.":[30],"Most":[31],"implementations":[33],"adopt":[34],"an":[35],"approach":[36],"that":[37,71],"lowers":[38],"into":[41],"a":[42,116,138,194,218],"matrix-based":[43],"operation":[44],"through":[45],"im2col":[47,112],"(image":[48],"to":[49,93,120],"column)":[50],"process.":[51],"transformed":[53],"then":[55],"can":[56],"be":[57],"easily":[58],"parallelized":[59],"with":[60,141,188],"highly":[61],"efficient":[62],"BLAS":[63],"libraries.":[64,182],"contribution":[66],"this":[68,81,100,132],"paper":[69],"we":[72,102,136,200],"observe":[73,201],"significant":[74],"but":[75],"intricately":[76],"patterned":[77],"data":[78,118],"redundancy":[79,87,108],"in":[80,193,210],"matrix":[82,126,134],"representation":[83,127],"convolution.":[85,129],"This":[86],"has":[88],"not":[89],"been":[90],"exploited":[91],"before":[92],"improve":[94],"performance":[96],"CNNs.":[98],"In":[99],"paper,":[101],"analyze":[103],"origin":[105],"generated":[109],"process,":[113],"and":[114,150,159,163,214],"reveal":[115],"new":[117,190],"pattern":[119],"more":[121],"mathematically":[122],"concisely":[123],"describe":[124],"for":[128,206,217],"Based":[130],"redundancy-minimized":[133],"representation,":[135],"implement":[137],"FFT-based":[139],"finer":[142],"FFT":[143,157],"granularity.":[144],"It":[145],"achieves":[146],"average":[148,161,203],"23%":[149],"maximum":[151,164],"50%":[152],"speedup":[153,166,205,216],"over":[154,167],"regular":[156],"convolution,":[158],"93%":[162],"286%":[165],"Im2col+GEMM":[169],"method":[170,192],"from":[171],"NVIDIA's":[172],"cuDNN":[173],"library,":[174],"Moreover,":[183],"replacing":[185],"existing":[186],"methods":[187],"our":[189],"popular":[195],"deep-learning":[196],"programming":[197],"framework":[198],"Caffe,":[199],"74%":[204],"multiple":[207],"synthetic":[208],"closer-to-real-world":[211],"application":[212],"scenarios":[213],"25%":[215],"variant":[219],"VGG":[222],"network.":[223]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}