{"id":"https://openalex.org/W3002531560","doi":"https://doi.org/10.1109/icecs46596.2019.8964870","title":"A Tile-based Fused-Layer Approach to Accelerate DCNNs on Low-Density FPGAs","display_name":"A Tile-based Fused-Layer Approach to Accelerate DCNNs on Low-Density FPGAs","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W3002531560","doi":"https://doi.org/10.1109/icecs46596.2019.8964870","mag":"3002531560"},"language":"en","primary_location":{"id":"doi:10.1109/icecs46596.2019.8964870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icecs46596.2019.8964870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS)","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/A5102843319","display_name":"Ahmet Erdem","orcid":"https://orcid.org/0000-0001-5140-6463"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Ahmet Erdem","raw_affiliation_strings":["Politecnico di Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068521571","display_name":"Danijela Babic","orcid":null},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Danijela Babic","raw_affiliation_strings":["Politecnico di Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031461662","display_name":"Cristina Silvano","orcid":"https://orcid.org/0000-0003-1668-0883"},"institutions":[{"id":"https://openalex.org/I93860229","display_name":"Politecnico di Milano","ror":"https://ror.org/01nffqt88","country_code":"IT","type":"education","lineage":["https://openalex.org/I93860229"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Cristina Silvano","raw_affiliation_strings":["Politecnico di Milano"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Politecnico di Milano","institution_ids":["https://openalex.org/I93860229"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I93860229"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"37","last_page":"40"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9997000098228455,"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":0.9979000091552734,"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":0.8192455768585205},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.7314815521240234},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.6836414337158203},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6468585729598999},{"id":"https://openalex.org/keywords/locality","display_name":"Locality","score":0.6260725855827332},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.5632442235946655},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.5276550054550171},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.48408758640289307},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.47992143034935},{"id":"https://openalex.org/keywords/memory-bandwidth","display_name":"Memory bandwidth","score":0.4484250843524933},{"id":"https://openalex.org/keywords/layer","display_name":"Layer (electronics)","score":0.4367184638977051},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.34130439162254333},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.29484987258911133},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.28562310338020325},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.0946921706199646}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8192455768585205},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.7314815521240234},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.6836414337158203},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6468585729598999},{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.6260725855827332},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.5632442235946655},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.5276550054550171},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.48408758640289307},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.47992143034935},{"id":"https://openalex.org/C188045654","wikidata":"https://www.wikidata.org/wiki/Q17148339","display_name":"Memory bandwidth","level":2,"score":0.4484250843524933},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.4367184638977051},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.34130439162254333},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.29484987258911133},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28562310338020325},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0946921706199646},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C178790620","wikidata":"https://www.wikidata.org/wiki/Q11351","display_name":"Organic chemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/icecs46596.2019.8964870","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icecs46596.2019.8964870","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 26th IEEE International Conference on Electronics, Circuits and Systems (ICECS)","raw_type":"proceedings-article"},{"id":"pmh:oai:re.public.polimi.it:11311/1146032","is_oa":false,"landing_page_url":"http://hdl.handle.net/11311/1146032","pdf_url":null,"source":{"id":"https://openalex.org/S4306400312","display_name":"Virtual Community of Pathological Anatomy (University of Castilla La Mancha)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I79189158","host_organization_name":"University of Castilla-La Mancha","host_organization_lineage":["https://openalex.org/I79189158"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/conferenceObject"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2094756095","https://openalex.org/W2565305208","https://openalex.org/W4249932213","https://openalex.org/W6637373629"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W17155033","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4376647684"],"abstract_inverted_index":{"Accelerating":[0],"Deep":[1],"Convolutional":[2],"Neural":[3],"Networks":[4],"on":[5,118,161],"FPGAs":[6],"is":[7],"achieving":[8],"a":[9,14,30,54,66,69,80,92,119,140,162],"lot":[10],"of":[11,17,83,108,126,134,151],"interest":[12],"across":[13],"wide":[15],"range":[16],"applications":[18],"such":[19],"as":[20],"image":[21],"recognition":[22],"and":[23,34,61],"classification.":[24],"Although":[25],"memory":[26,46,102,135],"requirement":[27],"still":[28],"represents":[29],"challenge":[31],"for":[32],"fast":[33],"efficient":[35],"inference":[36],"workloads,":[37],"fused-accelerated":[38],"layers":[39,86],"have":[40,155],"been":[41,156],"recently":[42],"proposed":[43],"to":[44,58,68,89,113,132,139,158],"mitigate":[45],"bandwidth":[47],"problems.":[48],"In":[49,73],"this":[50],"scenario,":[51],"we":[52,77],"propose":[53,78],"tiled-based":[55,148],"fused-layer":[56],"approach":[57,112],"exploit":[59],"temporal":[60],"spatial":[62],"locality":[63],"in":[64,87],"mapping":[65],"DCNN":[67],"specialized":[70],"low-density":[71,93,163],"FPGA.":[72],"our":[74,109],"tile-based":[75],"approach,":[76],"applying":[79],"fusing":[81],"depth":[82],"two":[84],"convolutional":[85],"order":[88],"fit":[90],"into":[91],"FPGA":[94],"without":[95],"affecting":[96],"the":[97,101,106,115],"performance,":[98],"while":[99,129],"reducing":[100],"bandwidth.":[103],"We":[104,121],"demonstrated":[105],"effectiveness":[107],"two-fused":[110],"layer":[111],"accelerate":[114],"VGG16":[116,152],"network":[117],"Zynq-7020.":[120,164],"achieved":[122],"an":[123],"average":[124],"speedup":[125],"1.44x":[127],"times,":[128],"saving":[130],"up":[131],"61%":[133],"transactions":[136],"with":[137],"respect":[138],"baseline":[141],"represented":[142],"by":[143],"tiled-only":[144],"(not-fused)":[145],"version.":[146],"A":[147],"fully-fused":[149],"version":[150],"would":[153],"not":[154],"feasible":[157],"be":[159],"mapped":[160]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2020-01-30T00:00:00"}