{"id":"https://openalex.org/W3205546585","doi":"https://doi.org/10.1109/jetcas.2021.3120103","title":"Hardware-Efficient Residual Neural Network Execution in Line-Buffer Depth-First Processing","display_name":"Hardware-Efficient Residual Neural Network Execution in Line-Buffer Depth-First Processing","publication_year":2021,"publication_date":"2021-10-15","ids":{"openalex":"https://openalex.org/W3205546585","doi":"https://doi.org/10.1109/jetcas.2021.3120103","mag":"3205546585"},"language":"en","primary_location":{"id":"doi:10.1109/jetcas.2021.3120103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jetcas.2021.3120103","pdf_url":null,"source":{"id":"https://openalex.org/S142323794","display_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","issn_l":"2156-3357","issn":["2156-3357","2156-3365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Emerging and Selected Topics in Circuits 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":"https://openalex.org/A5043501540","display_name":"Man Shi","orcid":"https://orcid.org/0000-0003-1675-6235"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":true,"raw_author_name":"Man Shi","raw_affiliation_strings":["Department of Electrical Engineering (ESAT), MICAS, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering (ESAT), MICAS, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037588129","display_name":"Pouya Houshmand","orcid":"https://orcid.org/0000-0003-2935-8842"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Pouya Houshmand","raw_affiliation_strings":["Department of Electrical Engineering (ESAT), MICAS, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering (ESAT), MICAS, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017238376","display_name":"Linyan Mei","orcid":"https://orcid.org/0000-0001-8649-3923"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Linyan Mei","raw_affiliation_strings":["Department of Electrical Engineering (ESAT), MICAS, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering (ESAT), MICAS, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5012150553","display_name":"Marian Verhelst","orcid":"https://orcid.org/0000-0003-3495-9263"},"institutions":[{"id":"https://openalex.org/I99464096","display_name":"KU Leuven","ror":"https://ror.org/05f950310","country_code":"BE","type":"education","lineage":["https://openalex.org/I99464096"]}],"countries":["BE"],"is_corresponding":false,"raw_author_name":"Marian Verhelst","raw_affiliation_strings":["Department of Electrical Engineering (ESAT), MICAS, KU Leuven, Leuven, Belgium"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering (ESAT), MICAS, KU Leuven, Leuven, Belgium","institution_ids":["https://openalex.org/I99464096"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5043501540"],"corresponding_institution_ids":["https://openalex.org/I99464096"],"apc_list":null,"apc_paid":null,"fwci":0.8646,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.7595098,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":"11","issue":"4","first_page":"690","last_page":"700"},"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9986000061035156,"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":0.996999979019165,"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":0.7823766469955444},{"id":"https://openalex.org/keywords/residual","display_name":"Residual","score":0.6983907222747803},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6041462421417236},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5616403222084045},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.5035259127616882},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.47385266423225403},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4621587097644806},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.42725273966789246},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.40281668305397034},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.36857038736343384},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.35749393701553345},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3382393419742584},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2017623782157898}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7823766469955444},{"id":"https://openalex.org/C155512373","wikidata":"https://www.wikidata.org/wiki/Q287450","display_name":"Residual","level":2,"score":0.6983907222747803},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6041462421417236},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5616403222084045},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.5035259127616882},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.47385266423225403},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4621587097644806},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.42725273966789246},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.40281668305397034},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.36857038736343384},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.35749393701553345},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3382393419742584},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2017623782157898},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/jetcas.2021.3120103","is_oa":false,"landing_page_url":"https://doi.org/10.1109/jetcas.2021.3120103","pdf_url":null,"source":{"id":"https://openalex.org/S142323794","display_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","issn_l":"2156-3357","issn":["2156-3357","2156-3365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Journal on Emerging and Selected Topics in Circuits and Systems","raw_type":"journal-article"},{"id":"pmh:oai:lirias2repo.kuleuven.be:20.500.12942/687970","is_oa":false,"landing_page_url":"https://lirias.kuleuven.be/bitstream/20.500.12942/687970/2/Hardware-Efficient_Residual_Neural_Network_Execution_in_Line-Buffer_Depth-First_Processing.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306401954","display_name":"Lirias (KU Leuven)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I99464096","host_organization_name":"KU Leuven","host_organization_lineage":["https://openalex.org/I99464096"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"Ieee Journal On Emerging And Selected Topics In Circuits And Systems, vol. 11 (4), (690-700)","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8399999737739563,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320327336","display_name":"Vlaamse regering","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":30,"referenced_works":["https://openalex.org/W1686810756","https://openalex.org/W2108598243","https://openalex.org/W2117696986","https://openalex.org/W2194775991","https://openalex.org/W2442974303","https://openalex.org/W2756829667","https://openalex.org/W2787700404","https://openalex.org/W2792893539","https://openalex.org/W2798838583","https://openalex.org/W2884687835","https://openalex.org/W2915589364","https://openalex.org/W2921126577","https://openalex.org/W2963163009","https://openalex.org/W2963470893","https://openalex.org/W3035414587","https://openalex.org/W3092502001","https://openalex.org/W3107716502","https://openalex.org/W3118608800","https://openalex.org/W3118709344","https://openalex.org/W3124269386","https://openalex.org/W3134750800","https://openalex.org/W4249932213","https://openalex.org/W4297775537","https://openalex.org/W6637373629","https://openalex.org/W6737664043","https://openalex.org/W6748556992","https://openalex.org/W6749781174","https://openalex.org/W6759263581","https://openalex.org/W6787972765","https://openalex.org/W6791634667"],"related_works":["https://openalex.org/W2560215812","https://openalex.org/W2949601986","https://openalex.org/W2788972299","https://openalex.org/W2521347458","https://openalex.org/W4391621807","https://openalex.org/W2498789492","https://openalex.org/W2729981612","https://openalex.org/W2990636717","https://openalex.org/W4301867275","https://openalex.org/W2790610275"],"abstract_inverted_index":{"Deep":[0],"convolutional":[1],"neural":[2],"networks":[3],"(CNNs)":[4],"provide":[5],"State-of-the-Art":[6],"(SotA)":[7],"results":[8],"in":[9,75,123,179,194,212],"a":[10,150,164,172],"variety":[11],"of":[12,105,139,163,174],"machine":[13],"learning":[14],"(ML)":[15],"applications,":[16],"such":[17,83],"as":[18],"image":[19],"classification":[20],"and":[21,30,71,113,132,145,170,176,191,223],"object":[22],"detection.":[23],"The":[24],"trends":[25,44],"towards":[26],"higher-resolution":[27],"input":[28],"images":[29],"large-scale":[31],"model":[32],"structures":[33],"have":[34],"brought":[35],"drastic":[36],"performance":[37],"improvements":[38],"for":[39,86,118,168],"these":[40,43],"tasks.":[41],"Yet,":[42],"also":[45],"pose":[46],"increased":[47],"stress":[48],"on":[49,61,141],"hardware":[50],"resources.":[51],"Recent":[52],"work":[53],"proposed":[54,129,151],"an":[55],"advanced":[56],"layer":[57],"fusion":[58],"method":[59,200],"relying":[60],"the":[62,89,106,115,128,137,156,184,197,210,213,228,239],"line-buffer":[63],"depth-first":[64,107],"(LBDF)":[65],"processing,":[66],"to":[67,196,209,237],"reduce":[68],"memory":[69,73,92,96,143,147,204,236],"usage":[70],"off-chip":[72],"accesses":[74],"high":[76],"resolution":[77],"CNN":[78],"processing.":[79],"However,":[80],"when":[81],"deploying":[82],"LBDF":[84],"approach":[85],"residual":[87,120,161,165],"networks,":[88],"required":[90],"external":[91,146],"access":[93],"or":[94],"on-chip":[95,142,203,230,235],"capacity":[97],"drastically":[98],"increases":[99],"again,":[100],"hence":[101],"canceling":[102],"many":[103],"benefits":[104],"approach.":[108],"This":[109],"paper,":[110],"therefore,":[111],"outlines":[112],"analyzes":[114],"possible":[116],"methods":[117,158],"handling":[119],"connections":[121],"(RC)":[122],"combination":[124],"with":[125],"LBDF.":[126],"With":[127],"ReLU-based":[130],"compression":[131],"tiling":[133],"techniques,":[134],"we":[135],"minimize":[136],"overhead":[138],"RC":[140],"requirements":[144],"accesses.":[148],"Moreover,":[149],"hybrid":[152,217],"strategy,":[153],"optimally":[154],"combining":[155],"different":[157,160],"across":[159],"blocks":[162],"network,":[166],"yields":[167],"ResNet20":[169],"SqueezeNet":[171],"reduction":[173],"24.7%":[175],"45.1%":[177],"respectively":[178,193],"inference":[180],"energy":[181,222],"cost.":[182],"Also":[183],"execution":[185],"latency":[186,225],"is":[187],"reduced":[188],"by":[189],"19.4%":[190],"46.7%":[192],"comparison":[195],"best":[198,214],"single":[199],"under":[201],"certain":[202],"budgets.":[205],"In":[206],"addition,":[207],"compared":[208],"SotAs,":[211],"case,":[215],"our":[216],"strategy":[218],"only":[219,232],"consumes":[220],"43%":[221],"29.9%":[224],"while":[226],"use":[227],"same":[229,240],"memories;":[231],"requires":[233],"27.4%":[234],"achieve":[238],"performance.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"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"}