{"id":"https://openalex.org/W2964231161","doi":"https://doi.org/10.1109/iscas.2019.8702780","title":"Towards a Uniform Architecture for the Efficient Implementation of 2D and 3D Deconvolutional Neural Networks on FPGAs","display_name":"Towards a Uniform Architecture for the Efficient Implementation of 2D and 3D Deconvolutional Neural Networks on FPGAs","publication_year":2019,"publication_date":"2019-05-01","ids":{"openalex":"https://openalex.org/W2964231161","doi":"https://doi.org/10.1109/iscas.2019.8702780","mag":"2964231161"},"language":"en","primary_location":{"id":"doi:10.1109/iscas.2019.8702780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2019.8702780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Circuits and Systems (ISCAS)","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/A5102857675","display_name":"De\u2010Guang Wang","orcid":"https://orcid.org/0000-0003-0357-0183"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Deguang Wang","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037428152","display_name":"Junzhong Shen","orcid":"https://orcid.org/0000-0001-6233-6800"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junzhong Shen","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101937502","display_name":"Mei Wen","orcid":"https://orcid.org/0000-0002-5875-3297"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mei Wen","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100710936","display_name":"Chunyuan Zhang","orcid":"https://orcid.org/0000-0002-0944-2708"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyuan Zhang","raw_affiliation_strings":["National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Parallel and Distributed Processing, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"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/T11105","display_name":"Advanced Image Processing Techniques","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/T11105","display_name":"Advanced Image Processing Techniques","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/T10531","display_name":"Advanced Vision and Imaging","score":0.9990000128746033,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9980999827384949,"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":0.8091462850570679},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.8015618324279785},{"id":"https://openalex.org/keywords/deconvolution","display_name":"Deconvolution","score":0.6260408759117126},{"id":"https://openalex.org/keywords/acceleration","display_name":"Acceleration","score":0.6031675934791565},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.5978887677192688},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.5910168886184692},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.5244355797767639},{"id":"https://openalex.org/keywords/cellular-neural-network","display_name":"Cellular neural network","score":0.5040165781974792},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4772603213787079},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.47157567739486694},{"id":"https://openalex.org/keywords/computational-science","display_name":"Computational science","score":0.44041427969932556},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.43385404348373413},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.41544532775878906},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.40562668442726135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3909482955932617},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.3007582426071167},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.19412630796432495}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8091462850570679},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.8015618324279785},{"id":"https://openalex.org/C174576160","wikidata":"https://www.wikidata.org/wiki/Q1183700","display_name":"Deconvolution","level":2,"score":0.6260408759117126},{"id":"https://openalex.org/C117896860","wikidata":"https://www.wikidata.org/wiki/Q11376","display_name":"Acceleration","level":2,"score":0.6031675934791565},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.5978887677192688},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.5910168886184692},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.5244355797767639},{"id":"https://openalex.org/C812465","wikidata":"https://www.wikidata.org/wiki/Q5058375","display_name":"Cellular neural network","level":3,"score":0.5040165781974792},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4772603213787079},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.47157567739486694},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.44041427969932556},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.43385404348373413},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41544532775878906},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.40562668442726135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3909482955932617},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3007582426071167},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.19412630796432495},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","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/C74650414","wikidata":"https://www.wikidata.org/wiki/Q11397","display_name":"Classical mechanics","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/iscas.2019.8702780","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iscas.2019.8702780","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Symposium on Circuits and Systems (ISCAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.8899999856948853,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2094756095","https://openalex.org/W2276486856","https://openalex.org/W2503339013","https://openalex.org/W2546066744","https://openalex.org/W2604130399","https://openalex.org/W2737762472","https://openalex.org/W2891976760","https://openalex.org/W2895738878","https://openalex.org/W2962914239","https://openalex.org/W2963577671","https://openalex.org/W2963684088","https://openalex.org/W6685352114","https://openalex.org/W6729001083","https://openalex.org/W6735608572"],"related_works":["https://openalex.org/W3090782779","https://openalex.org/W4251527294","https://openalex.org/W4250106855","https://openalex.org/W2037261263","https://openalex.org/W4319952061","https://openalex.org/W4280636456","https://openalex.org/W4388913998","https://openalex.org/W4310584535","https://openalex.org/W4295935044","https://openalex.org/W3159906349"],"abstract_inverted_index":{"Three-dimensional":[0],"deconvolution":[1],"is":[2],"widely":[3],"used":[4],"in":[5,36,124,139],"many":[6],"computer":[7],"vision":[8],"applications.":[9],"However,":[10],"most":[11],"previous":[12],"works":[13],"have":[14,40],"only":[15],"focused":[16],"on":[17,24,54,63,75,83],"accelerating":[18],"2D":[19,47,59,71,91],"deconvolutional":[20],"neural":[21],"networks":[22],"(DCNNs)":[23],"FPGAs,":[25],"while":[26],"the":[27,55,84],"acceleration":[28,56],"of":[29,57,119,134],"3D":[30,61,73,93],"DCNNs":[31,62,74],"has":[32],"not":[33],"been":[34],"studied":[35],"depth":[37],"as":[38],"they":[39],"higher":[41],"computational":[42],"complexity":[43],"and":[44,60,72,92,109,131],"sparsity":[45],"than":[46],"DCNNs.":[48],"In":[49],"this":[50],"paper,":[51],"we":[52,95,114],"focus":[53],"both":[58],"FPGAs":[64],"by":[65],"proposing":[66],"efficient":[67],"schemes":[68],"for":[69,88],"mapping":[70],"a":[76,128,144],"uniform":[77],"architecture.":[78],"By":[79],"implementing":[80],"our":[81],"design":[82],"Xilinx":[85],"VC709":[86],"platform":[87],"four":[89],"real-life":[90],"DCNNs,":[94],"can":[96,115],"achieve":[97,116],"up":[98,120,135],"to":[99,121,127,136,143],"3.0":[100],"TOPS":[101],"with":[102,107],"high":[103],"hardware":[104],"efficiency.":[105],"Comparisons":[106],"CPU":[108,129],"GPU":[110,145],"solutions":[111],"demonstrate":[112],"that":[113],"an":[117,132],"improvement":[118,133],"63.3":[122],"\u00d7":[123,138],"throughput":[125],"relative":[126],"solution":[130],"8.3":[137],"energy":[140],"efficiency":[141],"compared":[142],"solution.":[146]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}