{"id":"https://openalex.org/W4205884968","doi":"https://doi.org/10.1109/tcsi.2021.3131581","title":"A Flexible and Efficient FPGA Accelerator for Various Large-Scale and Lightweight CNNs","display_name":"A Flexible and Efficient FPGA Accelerator for Various Large-Scale and Lightweight CNNs","publication_year":2021,"publication_date":"2021-12-07","ids":{"openalex":"https://openalex.org/W4205884968","doi":"https://doi.org/10.1109/tcsi.2021.3131581"},"language":"en","primary_location":{"id":"doi:10.1109/tcsi.2021.3131581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2021.3131581","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems I: Regular Papers","raw_type":"journal-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/A5091293910","display_name":"Xiao Wu","orcid":"https://orcid.org/0000-0001-8306-6889"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xiao Wu","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068840674","display_name":"Yufei Ma","orcid":"https://orcid.org/0000-0002-2670-524X"},"institutions":[{"id":"https://openalex.org/I20231570","display_name":"Peking University","ror":"https://ror.org/02v51f717","country_code":"CN","type":"education","lineage":["https://openalex.org/I20231570"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yufei Ma","raw_affiliation_strings":["Institute for Artificial Intelligence and the School of Integrated Circuits, Peking University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute for Artificial Intelligence and the School of Integrated Circuits, Peking University, Beijing, China","institution_ids":["https://openalex.org/I4210100255","https://openalex.org/I20231570"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100785858","display_name":"Meiqi Wang","orcid":"https://orcid.org/0000-0001-9553-3640"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Meiqi Wang","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100696999","display_name":"Zhongfeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongfeng Wang","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Electronic Science and Engineering, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5091293910"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":5.7166,"has_fulltext":false,"cited_by_count":84,"citation_normalized_percentile":{"value":0.97155776,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":98,"max":100},"biblio":{"volume":"69","issue":"3","first_page":"1185","last_page":"1198"},"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9980000257492065,"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/computer-science","display_name":"Computer science","score":0.779194712638855},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6750575304031372},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.6742199659347534},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.6405208110809326},{"id":"https://openalex.org/keywords/microblaze","display_name":"MicroBlaze","score":0.6304898262023926},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5634530186653137},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.512687087059021},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.48588961362838745},{"id":"https://openalex.org/keywords/reconfigurability","display_name":"Reconfigurability","score":0.4543227255344391},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4355294108390808},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4318165183067322},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.42642587423324585},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4201353192329407},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.41649138927459717},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4154013395309448},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.3652704954147339},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.31471431255340576},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3034334182739258},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.2917499840259552},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.1199817955493927},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09612557291984558}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.779194712638855},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6750575304031372},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.6742199659347534},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.6405208110809326},{"id":"https://openalex.org/C2777575374","wikidata":"https://www.wikidata.org/wiki/Q1644704","display_name":"MicroBlaze","level":3,"score":0.6304898262023926},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5634530186653137},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.512687087059021},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.48588961362838745},{"id":"https://openalex.org/C2780149590","wikidata":"https://www.wikidata.org/wiki/Q7302742","display_name":"Reconfigurability","level":2,"score":0.4543227255344391},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4355294108390808},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4318165183067322},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.42642587423324585},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4201353192329407},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.41649138927459717},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4154013395309448},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.3652704954147339},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.31471431255340576},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3034334182739258},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.2917499840259552},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.1199817955493927},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09612557291984558},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsi.2021.3131581","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsi.2021.3131581","pdf_url":null,"source":{"id":"https://openalex.org/S116977442","display_name":"IEEE Transactions on Circuits and Systems I Regular Papers","issn_l":"1549-8328","issn":["1549-8328","1558-0806"],"is_oa":false,"is_in_doaj":false,"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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Circuits and Systems I: Regular Papers","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.47999998927116394}],"awards":[{"id":"https://openalex.org/G2612603","display_name":null,"funder_award_id":"2021300341","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G4112626697","display_name":null,"funder_award_id":"61774082","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1686810756","https://openalex.org/W1923697677","https://openalex.org/W2117539524","https://openalex.org/W2553910756","https://openalex.org/W2592939477","https://openalex.org/W2616014673","https://openalex.org/W2618530766","https://openalex.org/W2789333991","https://openalex.org/W2795915628","https://openalex.org/W2810861508","https://openalex.org/W2883780447","https://openalex.org/W2887936511","https://openalex.org/W2902895686","https://openalex.org/W2943277244","https://openalex.org/W2943690741","https://openalex.org/W2955425717","https://openalex.org/W2963122961","https://openalex.org/W2963125010","https://openalex.org/W2963684088","https://openalex.org/W2963918968","https://openalex.org/W2964309882","https://openalex.org/W2972295109","https://openalex.org/W2989331028","https://openalex.org/W3008408165","https://openalex.org/W3009636589","https://openalex.org/W3025341614","https://openalex.org/W3089500695","https://openalex.org/W3089552161","https://openalex.org/W3093826489","https://openalex.org/W3164217046","https://openalex.org/W3197490098","https://openalex.org/W3202177182","https://openalex.org/W3210597831","https://openalex.org/W4293406525","https://openalex.org/W4297775537","https://openalex.org/W4298289240","https://openalex.org/W6637373629","https://openalex.org/W6637568146","https://openalex.org/W6640295612","https://openalex.org/W6685352114","https://openalex.org/W6717372056","https://openalex.org/W6729763630","https://openalex.org/W6737664043","https://openalex.org/W6762718338"],"related_works":["https://openalex.org/W2290089017","https://openalex.org/W2807127337","https://openalex.org/W2586397364","https://openalex.org/W2135707884","https://openalex.org/W4285429137","https://openalex.org/W4293243607","https://openalex.org/W2108269296","https://openalex.org/W2163252286","https://openalex.org/W2053477252","https://openalex.org/W3085540031"],"abstract_inverted_index":{"To":[0,35,88],"enable":[1],"efficient":[2],"deployment":[3],"of":[4,72,94],"convolutional":[5],"neural":[6],"networks":[7],"(CNNs)":[8],"on":[9,106,145,156,201],"embedded":[10],"platforms":[11],"for":[12,47,162],"different":[13],"computer":[14],"vision":[15,65],"applications,":[16],"several":[17],"convolution":[18,26,29,33,45],"variants":[19],"have":[20],"been":[21],"introduced,":[22],"such":[23],"as":[24],"depthwise":[25],"(DWCV),":[27],"transposed":[28],"(TPCV),":[30],"and":[31,54,77,96,159,179],"dilated":[32],"(DLCV).":[34],"address":[36],"the":[37,85,90,110,140,168,197,202],"utilization":[38],"degradation":[39],"issue":[40],"occurred":[41],"in":[42],"a":[43,51,74,98,129,172],"general":[44],"engine":[46],"these":[48],"emerging":[49],"operators,":[50],"highly":[52],"flexible":[53],"reconfigurable":[55],"hardware":[56],"accelerator":[57,142,169],"is":[58,81,103,133,143,187],"proposed":[59,82,104,141],"to":[60,68,83,117,135,176,183],"efficiently":[61],"support":[62],"various":[63],"CNN-based":[64],"tasks.":[66],"Firstly,":[67],"avoid":[69],"workload":[70],"imbalance":[71],"TPCV,":[73],"zero":[75,92],"transfer":[76],"skipping":[78],"(ZTS)":[79],"method":[80,102],"reorganize":[84],"computation":[86],"process.":[87],"eliminate":[89],"redundant":[91],"calculations":[93],"TPCV":[95],"DLCV,":[97],"sparsity-alike":[99],"processing":[100,173],"(SAP)":[101],"based":[105],"weight-oriented":[107],"dataflow.":[108],"Secondly,":[109],"DWCV":[111],"or":[112,165],"pooling":[113],"layers":[114],"are":[115],"configured":[116],"be":[118],"directly":[119],"executed":[120],"after":[121],"standard":[122],"convolutions":[123],"without":[124],"external":[125],"memory":[126],"accesses.":[127],"Furthermore,":[128],"programmable":[130],"execution":[131],"schedule":[132],"introduced":[134],"gain":[136],"better":[137,195],"flexibility.":[138],"Finally,":[139],"evaluated":[144,200],"Intel":[146],"Arria":[147],"10":[148],"SoC":[149],"FPGA.":[150],"Experimental":[151],"results":[152],"show":[153],"state-of-the-art":[154],"performance":[155],"both":[157],"large-scale":[158],"lightweight":[160],"CNNs":[161],"image":[163],"segmentation":[164],"classification.":[166],"Specifically,":[167],"can":[170],"achieve":[171],"speed":[174],"up":[175,182],"339.9":[177],"FPS":[178],"computational":[180],"efficiency":[181],"0.58":[184],"GOPS/DSP,":[185],"which":[186],"<inline-formula":[188],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[189],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">":[190],"<tex-math":[191],"notation=\"LaTeX\">$3.3\\times":[192],"$":[193],"</tex-math></inline-formula>":[194],"than":[196],"prior":[198],"art":[199],"same":[203],"network.":[204]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":23},{"year":2024,"cited_by_count":30},{"year":2023,"cited_by_count":22},{"year":2022,"cited_by_count":7}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}