{"id":"https://openalex.org/W2903778355","doi":"https://doi.org/10.1145/3283452","title":"Instruction Driven Cross-layer CNN Accelerator for Fast Detection on FPGA","display_name":"Instruction Driven Cross-layer CNN Accelerator for Fast Detection on FPGA","publication_year":2018,"publication_date":"2018-09-30","ids":{"openalex":"https://openalex.org/W2903778355","doi":"https://doi.org/10.1145/3283452","mag":"2903778355"},"language":"en","primary_location":{"id":"doi:10.1145/3283452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3283452","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","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":null,"display_name":"Jincheng Yu","orcid":"https://orcid.org/0000-0002-6556-7468"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jincheng Yu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-6556-7468","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034555845","display_name":"Guangjun Ge","orcid":"https://orcid.org/0000-0001-5855-6480"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangjun Ge","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5855-6480","affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102712817","display_name":"Yiming Hu","orcid":"https://orcid.org/0009-0006-2418-976X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiming Hu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5086217226","display_name":"Xuefei Ning","orcid":"https://orcid.org/0000-0003-2209-8312"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuefei Ning","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5090846991","display_name":"Jiantao Qiu","orcid":"https://orcid.org/0000-0002-1328-2639"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiantao Qiu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101189530","display_name":"Kaiyuan Guo","orcid":"https://orcid.org/0009-0001-0621-9543"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kaiyuan Guo","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100445061","display_name":"Yu Wang","orcid":"https://orcid.org/0000-0001-6108-5157"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Wang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5023755254","display_name":"Huazhong Yang","orcid":"https://orcid.org/0000-0003-2421-353X"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huazhong Yang","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":8,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.59,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.88228897,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":"11","issue":"3","first_page":"1","last_page":"23"},"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":0.9987999796867371,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9958000183105469,"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":0.9088765978813171},{"id":"https://openalex.org/keywords/loop-unrolling","display_name":"Loop unrolling","score":0.8278090953826904},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7608426213264465},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5763647556304932},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5703806281089783},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.53434818983078},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.48332762718200684},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4776671826839447},{"id":"https://openalex.org/keywords/efficient-energy-use","display_name":"Efficient energy use","score":0.461139053106308},{"id":"https://openalex.org/keywords/gate-array","display_name":"Gate array","score":0.43831437826156616},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.39344239234924316},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.3588681221008301},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.3461337089538574},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3454109728336334},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.27116915583610535},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2697490453720093},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.15135234594345093},{"id":"https://openalex.org/keywords/compiler","display_name":"Compiler","score":0.11103066802024841}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9088765978813171},{"id":"https://openalex.org/C76970557","wikidata":"https://www.wikidata.org/wiki/Q1869750","display_name":"Loop unrolling","level":3,"score":0.8278090953826904},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7608426213264465},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5763647556304932},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5703806281089783},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.53434818983078},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.48332762718200684},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4776671826839447},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.461139053106308},{"id":"https://openalex.org/C114237110","wikidata":"https://www.wikidata.org/wiki/Q114901","display_name":"Gate array","level":3,"score":0.43831437826156616},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.39344239234924316},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.3588681221008301},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.3461337089538574},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3454109728336334},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27116915583610535},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2697490453720093},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.15135234594345093},{"id":"https://openalex.org/C169590947","wikidata":"https://www.wikidata.org/wiki/Q47506","display_name":"Compiler","level":2,"score":0.11103066802024841},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3283452","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3283452","pdf_url":null,"source":{"id":"https://openalex.org/S112809824","display_name":"ACM Transactions on Reconfigurable Technology and Systems","issn_l":"1936-7406","issn":["1936-7406","1936-7414"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Reconfigurable Technology and Systems","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","display_name":"Affordable and clean energy","score":0.8999999761581421}],"awards":[{"id":"https://openalex.org/G2399109260","display_name":null,"funder_award_id":"No. 61622403, 61621091","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4563124395","display_name":null,"funder_award_id":"2018YFB0105005","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program 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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1487564550","https://openalex.org/W1536680647","https://openalex.org/W1686810756","https://openalex.org/W2037227137","https://openalex.org/W2048266589","https://openalex.org/W2067523571","https://openalex.org/W2094756095","https://openalex.org/W2102605133","https://openalex.org/W2117539524","https://openalex.org/W2125203716","https://openalex.org/W2152839228","https://openalex.org/W2155893237","https://openalex.org/W2193145675","https://openalex.org/W2276486856","https://openalex.org/W2289252105","https://openalex.org/W2469490737","https://openalex.org/W2515287984","https://openalex.org/W2520083297","https://openalex.org/W2523838129","https://openalex.org/W2525740295","https://openalex.org/W2565305208","https://openalex.org/W2574797063","https://openalex.org/W2584616277","https://openalex.org/W2585774018","https://openalex.org/W2613574453","https://openalex.org/W2627042741","https://openalex.org/W2729080111","https://openalex.org/W2737762472","https://openalex.org/W2765815218","https://openalex.org/W2785545076","https://openalex.org/W2951460453","https://openalex.org/W2963037989","https://openalex.org/W2964299589","https://openalex.org/W3106250896","https://openalex.org/W4212788319","https://openalex.org/W4230989867","https://openalex.org/W4232973962"],"related_works":["https://openalex.org/W3213934210","https://openalex.org/W3212577482","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4389580120","https://openalex.org/W4388913998","https://openalex.org/W4390467929","https://openalex.org/W4281393566","https://openalex.org/W4310584535","https://openalex.org/W4295935044"],"abstract_inverted_index":{"In":[0,114,132],"recent":[1],"years,":[2],"Convolutional":[3],"Neural":[4],"Networks":[5],"(CNNs)":[6],"have":[7,15],"been":[8,52],"widely":[9,53],"applied":[10],"in":[11,19,91,292],"computer":[12],"vision":[13],"and":[14,69,151,178,197,235,290,298],"achieved":[16],"significant":[17],"improvements":[18],"object":[20,156,284],"detection":[21,33,41,206,229,285,310],"tasks.":[22],"Although":[23],"there":[24],"are":[25,107],"many":[26],"optimizing":[27],"methods":[28],"to":[29,39,62,116,135,189],"speed":[30],"up":[31],"CNN-based":[32],"algorithms,":[34,286,304],"it":[35],"is":[36,81],"still":[37],"difficult":[38],"deploy":[40,204],"algorithms":[42,207,311],"on":[43,238,255,273],"real-time":[44],"low-power":[45],"systems.":[46],"Field-Programmable":[47],"Gate":[48],"Array":[49],"(FPGA)":[50],"has":[51],"explored":[54],"as":[55],"a":[56,110,171,186,281],"platform":[57],"for":[58,109,155,283],"accelerating":[59],"CNN":[60,79,112,145,172,258],"due":[61],"its":[63],"promising":[64],"performance,":[65],"high":[66],"energy":[67,76,201,293],"efficiency,":[68],"flexibility.":[70],"Previous":[71],"works":[72],"show":[73],"that":[74,167],"the":[75,84,93,104,117,121,127,137,148,152,160,180,191,199,209,218,225,228,239,256,261,265,274,305,308],"consumption":[77],"of":[78,130,139,164,227,267,307],"accelerators":[80,102],"dominated":[82],"by":[83,251,314],"memory":[85,118],"access.":[86],"By":[87],"fusing":[88],"multiple":[89],"layers":[90,175],"CNN,":[92,165],"intermediate":[94,181,245],"data":[95,182,246],"transfer":[96,247],"can":[97,124,169,223,248],"be":[98,249],"reduced.":[99],"However,":[100],"previous":[101],"with":[103,176,193,212,260,296,302],"cross-layer":[105,153,262],"scheduling":[106,236],"designed":[108],"particular":[111],"model.":[113],"addition":[115],"access":[119],"optimization,":[120],"Winograd":[122,149,194],"algorithm":[123,150],"greatly":[125],"improve":[126,136],"computational":[128],"performance":[129,266],"convolution.":[131],"this":[133],"article,":[134],"flexibility":[138],"hardware,":[140],"we":[141,168,216],"design":[142],"an":[143],"instruction-driven":[144],"accelerator,":[146],"supporting":[147],"scheduling,":[154],"detection.":[157],"We":[158,184,231,278],"modify":[159],"loop":[161],"unrolling":[162],"order":[163],"so":[166],"schedule":[170],"across":[173],"different":[174],"instructions":[177,192],"eliminate":[179],"transfer.":[183],"propose":[185],"hardware":[187,269],"architecture":[188],"support":[190],"computation":[195,214],"units":[196],"reach":[198],"state-of-the-art":[200],"efficiency.":[202],"To":[203],"image":[205],"onto":[208],"proposed":[210],"accelerator":[211,234,270],"fixed-point":[213,219,309],"units,":[215],"adopt":[217],"fine-tune":[220],"method,":[221],"which":[222,287],"guarantee":[224],"accuracy":[226,306],"algorithms.":[230],"evaluate":[232],"our":[233,268],"policy":[237],"Xilinx":[240],"KU115":[241],"FPGA":[242],"platform.":[243],"The":[244],"reduced":[250],"more":[252],"than":[253,316],"90%":[254],"VGG-D":[257],"model":[259,276],"strategy.":[263],"Thus,":[264],"reaches":[271],"1700GOP/s":[272],"classification":[275],"VGG-D.":[277],"also":[279],"implement":[280],"framework":[282],"achieves":[288],"2.3\u00d7":[289],"50\u00d7":[291],"efficiency":[294],"compared":[295],"GPU":[297],"CPU,":[299],"respectively.":[300],"Compared":[301],"floating-point":[303],"only":[312],"drops":[313],"less":[315],"1%.":[317]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":3},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":5},{"year":2020,"cited_by_count":7},{"year":2019,"cited_by_count":3}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}