{"id":"https://openalex.org/W3197490098","doi":"https://doi.org/10.1109/socc49529.2020.9524773","title":"Efficient Inference of Large-Scale and Lightweight Convolutional Neural Networks on FPGA","display_name":"Efficient Inference of Large-Scale and Lightweight Convolutional Neural Networks on FPGA","publication_year":2020,"publication_date":"2020-09-08","ids":{"openalex":"https://openalex.org/W3197490098","doi":"https://doi.org/10.1109/socc49529.2020.9524773","mag":"3197490098"},"language":"en","primary_location":{"id":"doi:10.1109/socc49529.2020.9524773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/socc49529.2020.9524773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 33rd International System-on-Chip Conference (SOCC)","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/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":false,"raw_author_name":"Xiao Wu","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"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/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":"Yufei Ma","raw_affiliation_strings":["School of Electronic Science and Engineering, Nanjing University, Nanjing, China"],"raw_orcid":null,"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":"https://orcid.org/0000-0002-7227-4786"},"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"],"raw_orcid":null,"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":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.0854,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.41493218,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"168","last_page":"173"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9976000189781189,"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"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8363691568374634},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7695776224136353},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.734965443611145},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.7071094512939453},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5707598924636841},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5283083915710449},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.4881940484046936},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.4851987659931183},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47497671842575073},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.4660341143608093},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.4345395565032959},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4201257824897766},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.4111676812171936},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.35017871856689453},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.31189680099487305},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.29185324907302856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2727968692779541},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09417584538459778}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8363691568374634},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7695776224136353},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.734965443611145},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.7071094512939453},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5707598924636841},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5283083915710449},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.4881940484046936},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.4851987659931183},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47497671842575073},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.4660341143608093},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4345395565032959},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4201257824897766},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4111676812171936},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.35017871856689453},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.31189680099487305},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.29185324907302856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2727968692779541},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09417584538459778},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/socc49529.2020.9524773","is_oa":false,"landing_page_url":"https://doi.org/10.1109/socc49529.2020.9524773","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE 33rd International System-on-Chip Conference (SOCC)","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":24,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2117539524","https://openalex.org/W2163605009","https://openalex.org/W2584311934","https://openalex.org/W2612445135","https://openalex.org/W2613718673","https://openalex.org/W2616014673","https://openalex.org/W2707890836","https://openalex.org/W2789333991","https://openalex.org/W2883780447","https://openalex.org/W2887936511","https://openalex.org/W2912949188","https://openalex.org/W2963122961","https://openalex.org/W2963125010","https://openalex.org/W2963163009","https://openalex.org/W2963287528","https://openalex.org/W2963674932","https://openalex.org/W2963918968","https://openalex.org/W2989331028","https://openalex.org/W4297775537","https://openalex.org/W6638632666","https://openalex.org/W6739917289","https://openalex.org/W6753767121","https://openalex.org/W6754259177"],"related_works":["https://openalex.org/W2953234277","https://openalex.org/W2626256601","https://openalex.org/W147410782","https://openalex.org/W2900413183","https://openalex.org/W4390975304","https://openalex.org/W3022252430","https://openalex.org/W4287804464","https://openalex.org/W3103989898","https://openalex.org/W3211292372","https://openalex.org/W803346624"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4],"achieved":[5],"significant":[6],"accuracy":[7],"improvement":[8,75],"in":[9,33,49],"many":[10],"intelligent":[11],"applications":[12],"at":[13],"the":[14,36,45,55,72,77,86,107,118,122,128,135,142,147,164,183,188],"cost":[15],"of":[16,81,109,134,187],"intensive":[17],"convolution":[18,39,68,83,124],"operations":[19],"and":[20,58,96,112,125,131,145,202,212],"massive":[21],"data":[22,79,87,132,143],"movements.":[23],"To":[24,90],"efficiently":[25,105],"deploy":[26],"CNNs":[27],"on":[28,100,196,206],"low":[29],"power":[30],"embedded":[31],"platforms":[32],"real":[34],"time,":[35],"depthwise":[37,82,123],"separable":[38],"has":[40],"been":[41],"proposed":[42,103,179,191],"to":[43,70,104,140,162,170,180],"replace":[44],"standard":[46,160],"convolution,":[47],"especially":[48],"lightweight":[50,113,213],"CNNs,":[51,209],"which":[52],"remarkably":[53],"reduces":[54,85],"computation":[56],"complexity":[57],"model":[59,177],"size.":[60],"However,":[61],"it":[62],"is":[63,102,178,194],"difficult":[64],"for":[65],"a":[66,94,175],"general":[67],"engine":[69],"obtain":[71],"theoretical":[73],"performance":[74,176,205],"as":[76],"decreased":[78],"dependency":[80],"significantly":[84],"reuse":[88],"opportunity.":[89],"address":[91],"this":[92],"issue,":[93],"flexible":[95],"highperformance":[97],"accelerator":[98,193],"based":[99],"FPGA":[101,201],"process":[106],"inference":[108],"both":[110,207],"large-scale":[111,208],"CNNs.":[114],"Firstly,":[115],"by":[116],"sharing":[117],"activation":[119],"dataflow":[120],"between":[121],"pooling":[126],"layers,":[127],"control":[129],"logic":[130,148],"bus":[133],"two":[136,152],"layers":[137,153],"are":[138],"reused":[139],"maximize":[141],"utilization":[144],"minimize":[146],"overhead.":[149],"Furthermore,":[150],"these":[151],"can":[154],"be":[155],"processed":[156],"either":[157],"directly":[158],"after":[159],"convolutions":[161],"eliminate":[163],"external":[165],"memory":[166],"accesses":[167],"or":[168],"independently":[169],"gain":[171],"better":[172],"flexibility.":[173],"Thirdly,":[174],"automatically":[181],"explore":[182],"optimal":[184],"design":[185],"options":[186],"accelerator.":[189],"The":[190],"hardware":[192],"evaluated":[195],"Intel":[197],"Arria":[198],"10":[199],"SoC":[200],"demonstrates":[203],"state-of-the-art":[204],"e.g.,":[210,215],"VGG,":[211],"ones,":[214],"MobileNet.":[216]},"counts_by_year":[{"year":2024,"cited_by_count":4},{"year":2021,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}