{"id":"https://openalex.org/W2789227401","doi":"https://doi.org/10.1145/3174243.3174991","title":"A Low-Power Deconvolutional Accelerator for Convolutional Neural Network Based Segmentation on FPGA","display_name":"A Low-Power Deconvolutional Accelerator for Convolutional Neural Network Based Segmentation on FPGA","publication_year":2018,"publication_date":"2018-02-15","ids":{"openalex":"https://openalex.org/W2789227401","doi":"https://doi.org/10.1145/3174243.3174991","mag":"2789227401"},"language":"en","primary_location":{"id":"doi:10.1145/3174243.3174991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3174243.3174991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","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/A5101818400","display_name":"Shuanglong Liu","orcid":"https://orcid.org/0000-0002-1513-1981"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Shuanglong Liu","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103060695","display_name":"Xinyu Niu","orcid":"https://orcid.org/0000-0003-0202-9408"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyu Niu","raw_affiliation_strings":["Corerain Technologies Ltd., Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Corerain Technologies Ltd., Shenzhen, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057940557","display_name":"Wayne Luk","orcid":"https://orcid.org/0000-0002-6750-927X"},"institutions":[{"id":"https://openalex.org/I47508984","display_name":"Imperial College London","ror":"https://ror.org/041kmwe10","country_code":"GB","type":"education","lineage":["https://openalex.org/I47508984"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Wayne Luk","raw_affiliation_strings":["Imperial College London, London, United Kingdom"],"affiliations":[{"raw_affiliation_string":"Imperial College London, London, United Kingdom","institution_ids":["https://openalex.org/I47508984"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5101818400"],"corresponding_institution_ids":["https://openalex.org/I47508984"],"apc_list":null,"apc_paid":null,"fwci":0.2089,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.52209884,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"293","last_page":"293"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9979000091552734,"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":0.9979000091552734,"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":0.9950000047683716,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.989799976348877,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8524608016014099},{"id":"https://openalex.org/keywords/deconvolution","display_name":"Deconvolution","score":0.7431973218917847},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.735089123249054},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7280870676040649},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.6303447484970093},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5557218194007874},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5198419690132141},{"id":"https://openalex.org/keywords/digital-signal-processing","display_name":"Digital signal processing","score":0.5034679770469666},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4408543109893799},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.41590258479118347},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.37230372428894043},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3089408576488495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8524608016014099},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.7431973218917847},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.735089123249054},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7280870676040649},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.6303447484970093},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5557218194007874},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5198419690132141},{"id":"https://openalex.org/C84462506","wikidata":"https://www.wikidata.org/wiki/Q173142","display_name":"Digital signal processing","level":2,"score":0.5034679770469666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4408543109893799},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41590258479118347},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.37230372428894043},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3089408576488495}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3174243.3174991","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3174243.3174991","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 ACM/SIGDA International Symposium on Field-Programmable Gate Arrays","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","id":"https://metadata.un.org/sdg/11","score":0.41999998688697815}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3204400881","https://openalex.org/W3214410901","https://openalex.org/W3204296682","https://openalex.org/W3183118997","https://openalex.org/W2917767146","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044"],"abstract_inverted_index":{"Convolutional":[0],"Neural":[1],"Networks":[2],"(CNNs)":[3],"based":[4],"algorithms":[5,49,73],"have":[6],"been":[7,64],"successful":[8],"in":[9,30],"solving":[10],"image":[11,44,219],"recognition":[12],"problems,":[13],"showing":[14],"very":[15],"large":[16],"accuracy":[17],"improvement.":[18],"In":[19,77],"recent":[20],"years,":[21],"deconvolution":[22,48,72,86,146],"layers":[23],"are":[24,50],"widely":[25],"used":[26,185],"as":[27,43,106,108],"key":[28],"components":[29],"the":[31,47,68,96,102,123,133,145,195],"state-of-the-art":[32],"CNNs":[33],"for":[34,88,101,109,127,217],"end-to-end":[35],"training":[36],"and":[37,82,144,158,194,203,209],"models":[38],"to":[39,57,120,186,212],"support":[40],"tasks":[41],"such":[42],"segmentation.":[45],"However,":[46],"computationally":[51],"intensive":[52],"which":[53,168],"limits":[54],"their":[55],"applicability":[56],"real":[58],"time":[59],"applications.":[60],"Particularly,":[61],"there":[62],"has":[63],"little":[65],"research":[66],"on":[67,74,132,141,173,181,191],"efficient":[69],"implementations":[70],"of":[71,151,162,178,200,225],"FPGA":[75],"platforms.":[76],"this":[78],"work,":[79],"we":[80,137],"propose":[81],"develop":[83],"fully":[84],"customized":[85],"architecture":[87],"CNN-based":[89],"segmentation":[90,180],"algorithms.":[91],"Besides,":[92],"memory":[93],"sharing":[94],"between":[95],"computation":[97],"modules":[98],"is":[99,118,184],"proposed":[100],"FPGA-based":[103],"CNN":[104,130,189],"accelerator":[105,147,190],"well":[107],"other":[110],"optimization":[111],"techniques.":[112],"Furthermore,":[113],"a":[114,149,159,198,222],"hardware":[115,125],"mapping":[116],"framework":[117],"developed":[119],"automatically":[121],"generate":[122],"high-throughput":[124],"design":[126],"any":[128],"given":[129],"model":[131],"target":[134],"device.":[135],"Finally,":[136],"implement":[138],"our":[139,188],"designs":[140,172],"Xilinx":[142],"Zynq-7030":[143,192],"achieves":[148,197],"performance":[150,160,199],"25.6":[152],"GOPS":[153,202],"under":[154],"200MHz":[155],"working":[156],"frequency":[157],"density":[161],"0.064":[163],"GOPS/DSP":[164,205],"using":[165,206],"32-bit":[166],"quantization,":[167,208],"significantly":[169],"outperforms":[170],"previous":[171],"FPGAs.":[174],"A":[175],"real-time":[176],"application":[177],"scene":[179],"Cityscapes":[182],"Dataset":[183],"evaluate":[187],"board,":[193],"system":[196],"57.2":[201],"0.143":[204],"16-bit":[207],"supports":[210],"up":[211],"2":[213],"frames":[214],"per":[215],"second":[216],"512x512":[218],"inputs":[220],"with":[221],"power":[223],"consumption":[224],"only":[226],"3.2W.":[227]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}