{"id":"https://openalex.org/W3114436701","doi":"https://doi.org/10.1109/hpec43674.2020.9286185","title":"A Hybrid-Pipelined Architecture for FPGA-based Binary Weight DenseNet with High Performance-Efficiency","display_name":"A Hybrid-Pipelined Architecture for FPGA-based Binary Weight DenseNet with High Performance-Efficiency","publication_year":2020,"publication_date":"2020-09-22","ids":{"openalex":"https://openalex.org/W3114436701","doi":"https://doi.org/10.1109/hpec43674.2020.9286185","mag":"3114436701"},"language":"en","primary_location":{"id":"doi:10.1109/hpec43674.2020.9286185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","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/A5109541631","display_name":"Shihao Zeng","orcid":null},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shihao Zeng","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5007538828","display_name":"Yihua Huang","orcid":"https://orcid.org/0000-0003-1806-0936"},"institutions":[{"id":"https://openalex.org/I157773358","display_name":"Sun Yat-sen University","ror":"https://ror.org/0064kty71","country_code":"CN","type":"education","lineage":["https://openalex.org/I157773358"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihua Huang","raw_affiliation_strings":["School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Electronics and Information Technology, Sun Yat-sen University, Guangzhou, China","institution_ids":["https://openalex.org/I157773358"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5109541631"],"corresponding_institution_ids":["https://openalex.org/I157773358"],"apc_list":null,"apc_paid":null,"fwci":0.0977,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.42802648,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994000196456909,"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":0.9994000196456909,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.996399998664856,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.995199978351593,"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":0.8558685779571533},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7795992493629456},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.639146089553833},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6218248605728149},{"id":"https://openalex.org/keywords/binary-number","display_name":"Binary number","score":0.618636429309845},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.5757785439491272},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5413550734519958},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.5007803440093994},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.39043134450912476},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.37368297576904297},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3546642065048218},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.33961284160614014},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.1434001624584198},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.09716600179672241},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.08456039428710938},{"id":"https://openalex.org/keywords/arithmetic","display_name":"Arithmetic","score":0.07092815637588501},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.06678596138954163}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8558685779571533},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7795992493629456},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.639146089553833},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6218248605728149},{"id":"https://openalex.org/C48372109","wikidata":"https://www.wikidata.org/wiki/Q3913","display_name":"Binary number","level":2,"score":0.618636429309845},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.5757785439491272},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5413550734519958},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.5007803440093994},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.39043134450912476},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.37368297576904297},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3546642065048218},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.33961284160614014},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.1434001624584198},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.09716600179672241},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.08456039428710938},{"id":"https://openalex.org/C94375191","wikidata":"https://www.wikidata.org/wiki/Q11205","display_name":"Arithmetic","level":1,"score":0.07092815637588501},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.06678596138954163},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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/hpec43674.2020.9286185","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpec43674.2020.9286185","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE High Performance Extreme Computing Conference (HPEC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.6000000238418579}],"awards":[{"id":"https://openalex.org/G143808469","display_name":null,"funder_award_id":"61771494","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W2117539524","https://openalex.org/W2300242332","https://openalex.org/W2616014673","https://openalex.org/W2767737961","https://openalex.org/W2800421099","https://openalex.org/W2883927138","https://openalex.org/W2913631362","https://openalex.org/W2929170389","https://openalex.org/W2935524202","https://openalex.org/W2937598226","https://openalex.org/W2963446712","https://openalex.org/W6620707391","https://openalex.org/W6698200048"],"related_works":["https://openalex.org/W2111241003","https://openalex.org/W2355315220","https://openalex.org/W4200391368","https://openalex.org/W2210979487","https://openalex.org/W2316202402","https://openalex.org/W2074043759","https://openalex.org/W2082487009","https://openalex.org/W2373535795","https://openalex.org/W2565094479","https://openalex.org/W3103262449"],"abstract_inverted_index":{"The":[0,128],"DenseNet":[1,41],"achieves":[2],"remarkable":[3],"performance":[4],"in":[5,61],"various":[6],"computer":[7],"vision":[8],"tasks":[9],"with":[10,66],"much":[11],"fewer":[12],"parameters":[13],"and":[14,42,78,115,141,146],"operations.":[15],"However,":[16],"there":[17],"are":[18],"few":[19],"acceleration":[20,50],"designs":[21],"about":[22],"the":[23,35,40,52,67,92,97,102,105,122,136,147,155],"DenseNet,":[24,55],"due":[25],"to":[26,75,90,151],"its":[27],"dense-connectivity":[28],"structure.":[29],"In":[30],"this":[31],"paper,":[32],"we":[33],"apply":[34],"binary":[36,53,106],"weight":[37,54,107],"method":[38,84],"on":[39,112,118],"then":[43,116],"propose":[44],"a":[45,62,69,82],"hybrid-pipelined":[46],"architecture":[47,133],"for":[48,96],"FPGA-based":[49],"of":[51,85,124,138],"which":[56,153],"can":[57,134],"be":[58],"stored":[59],"entirely":[60],"chip.":[63],"To":[64,100],"deal":[65],"dense-connectivity,":[68],"reusable":[70],"convolution":[71],"unit":[72],"is":[73,88,110,149],"developed":[74],"support":[76],"conv1\u00d71":[77],"conv3\u00d73":[79],"efficiently.":[80],"Moreover,":[81],"theoretical":[83],"system":[86],"parallelism":[87],"proposed":[89,103],"guide":[91],"top-level":[93],"pipelined":[94],"design":[95],"maximum":[98],"efficiency.":[99],"evaluate":[101],"architecture,":[104],"DenseNet-100":[108],"model":[109],"trained":[111],"CIFAR10":[113],"dataset":[114],"implemented":[117],"VX690T":[119],"FPGA,":[120],"at":[121,144],"cost":[123],"4.18%":[125],"accuracy":[126],"loss.":[127],"experiment":[129],"demonstrates":[130],"that":[131],"our":[132],"achieve":[135],"throughput":[137],"514":[139],"GOPS":[140],"889":[142],"FPS":[143],"200MHz,":[145],"performance-efficiency":[148],"up":[150],"62.4%,":[152],"outperforms":[154],"most":[156],"related":[157],"works.":[158]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}