{"id":"https://openalex.org/W2985703348","doi":"https://doi.org/10.1145/3371154","title":"Optimizing Deep Learning Inference on Embedded Systems Through Adaptive Model Selection","display_name":"Optimizing Deep Learning Inference on Embedded Systems Through Adaptive Model Selection","publication_year":2020,"publication_date":"2020-01-31","ids":{"openalex":"https://openalex.org/W2985703348","doi":"https://doi.org/10.1145/3371154","mag":"2985703348"},"language":"en","primary_location":{"id":"doi:10.1145/3371154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3371154","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"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 Embedded Computing Systems","raw_type":"journal-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1911.04946","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5037544057","display_name":"Vicent Sanz Marco","orcid":null},"institutions":[{"id":"https://openalex.org/I98285908","display_name":"The University of Osaka","ror":"https://ror.org/035t8zc32","country_code":"JP","type":"education","lineage":["https://openalex.org/I98285908"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Vicent Sanz Marco","raw_affiliation_strings":["Osaka University, Japan","Osaka Univ., Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Osaka University, Japan","institution_ids":["https://openalex.org/I98285908"]},{"raw_affiliation_string":"Osaka Univ., Japan","institution_ids":["https://openalex.org/I98285908"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005781775","display_name":"Ben Taylor","orcid":"https://orcid.org/0000-0003-1089-6886"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Ben Taylor","raw_affiliation_strings":["Lancaster University, United Kingdom","Lancaster University United Kingdom"],"raw_orcid":"https://orcid.org/0000-0003-1089-6886","affiliations":[{"raw_affiliation_string":"Lancaster University, United Kingdom","institution_ids":["https://openalex.org/I67415387"]},{"raw_affiliation_string":"Lancaster University United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100401045","display_name":"Zheng Wang","orcid":"https://orcid.org/0000-0001-6157-0662"},"institutions":[{"id":"https://openalex.org/I130828816","display_name":"University of Leeds","ror":"https://ror.org/024mrxd33","country_code":"GB","type":"education","lineage":["https://openalex.org/I130828816"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Zheng Wang","raw_affiliation_strings":["University of Leeds, United Kingdom","University of Leeds,   United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Leeds, United Kingdom","institution_ids":["https://openalex.org/I130828816"]},{"raw_affiliation_string":"University of Leeds,   United Kingdom","institution_ids":["https://openalex.org/I130828816"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5059109166","display_name":"Yehia Elkhatib","orcid":"https://orcid.org/0000-0003-4639-436X"},"institutions":[{"id":"https://openalex.org/I67415387","display_name":"Lancaster University","ror":"https://ror.org/04f2nsd36","country_code":"GB","type":"education","lineage":["https://openalex.org/I67415387"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Yehia Elkhatib","raw_affiliation_strings":["Lancaster University, United Kingdom","Lancaster University United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Lancaster University, United Kingdom","institution_ids":["https://openalex.org/I67415387"]},{"raw_affiliation_string":"Lancaster University United Kingdom","institution_ids":["https://openalex.org/I67415387"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.3916,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.5999669,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":"19","issue":"1","first_page":"1","last_page":"28"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9994999766349792,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9984999895095825,"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":0.8358457088470459},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7476989030838013},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6605049967765808},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5860629677772522},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5543924570083618},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.5487268567085266},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5331973433494568},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.45241448283195496},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.43945860862731934},{"id":"https://openalex.org/keywords/latency","display_name":"Latency (audio)","score":0.4187449812889099}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8358457088470459},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7476989030838013},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6605049967765808},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5860629677772522},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5543924570083618},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.5487268567085266},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5331973433494568},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.45241448283195496},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.43945860862731934},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.4187449812889099},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","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},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1145/3371154","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3371154","pdf_url":null,"source":{"id":"https://openalex.org/S136160450","display_name":"ACM Transactions on Embedded Computing Systems","issn_l":"1539-9087","issn":["1539-9087","1558-3465"],"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 Embedded Computing Systems","raw_type":"journal-article"},{"id":"pmh:oai:eprints.whiterose.ac.uk:153294","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306400854","display_name":"White Rose Research Online (University of Leeds, The University of Sheffield, University of York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I2800616092","host_organization_name":"White Rose University Consortium","host_organization_lineage":["https://openalex.org/I2800616092"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Article"},{"id":"pmh:oai:arXiv.org:1911.04946","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04946","pdf_url":"https://arxiv.org/pdf/1911.04946","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"mag:2985703348","is_oa":true,"landing_page_url":"http://arxiv.org/pdf/1911.04946.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1911.04946","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1911.04946","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1911.04946","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1911.04946","pdf_url":"https://arxiv.org/pdf/1911.04946","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G171719035","display_name":null,"funder_award_id":"EP/M015734/1,EP/M01567X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G3056170115","display_name":null,"funder_award_id":"EP/M01567X/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"},{"id":"https://openalex.org/G4422763032","display_name":null,"funder_award_id":"EP/M015734/1","funder_id":"https://openalex.org/F4320334627","funder_display_name":"Engineering and Physical Sciences Research Council"}],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":85,"referenced_works":["https://openalex.org/W1558412961","https://openalex.org/W1832693441","https://openalex.org/W1861492603","https://openalex.org/W1972119323","https://openalex.org/W1982020565","https://openalex.org/W1987564528","https://openalex.org/W2033139628","https://openalex.org/W2056579078","https://openalex.org/W2070897293","https://openalex.org/W2081984813","https://openalex.org/W2083304636","https://openalex.org/W2099680095","https://openalex.org/W2117539524","https://openalex.org/W2144172034","https://openalex.org/W2155541015","https://openalex.org/W2160121678","https://openalex.org/W2160241055","https://openalex.org/W2166536280","https://openalex.org/W2171585602","https://openalex.org/W2172166488","https://openalex.org/W2193413348","https://openalex.org/W2194775991","https://openalex.org/W2231774493","https://openalex.org/W2251931977","https://openalex.org/W2270218991","https://openalex.org/W2285660444","https://openalex.org/W2300242332","https://openalex.org/W2302255633","https://openalex.org/W2325939864","https://openalex.org/W2340722533","https://openalex.org/W2346957300","https://openalex.org/W2408019865","https://openalex.org/W2419597278","https://openalex.org/W2525778437","https://openalex.org/W2525951180","https://openalex.org/W2546536770","https://openalex.org/W2565684518","https://openalex.org/W2581511846","https://openalex.org/W2586408124","https://openalex.org/W2592422436","https://openalex.org/W2594987874","https://openalex.org/W2605258629","https://openalex.org/W2611626712","https://openalex.org/W2612445135","https://openalex.org/W2613168994","https://openalex.org/W2615947440","https://openalex.org/W2618440624","https://openalex.org/W2618564128","https://openalex.org/W2626129225","https://openalex.org/W2738799638","https://openalex.org/W2739515247","https://openalex.org/W2754395205","https://openalex.org/W2758475033","https://openalex.org/W2762847354","https://openalex.org/W2784409032","https://openalex.org/W2790205036","https://openalex.org/W2797932837","https://openalex.org/W2798687821","https://openalex.org/W2802808949","https://openalex.org/W2804309962","https://openalex.org/W2896542121","https://openalex.org/W2902340222","https://openalex.org/W2921127294","https://openalex.org/W2944726758","https://openalex.org/W2949117887","https://openalex.org/W2951978180","https://openalex.org/W2962724414","https://openalex.org/W2962883027","https://openalex.org/W2963122961","https://openalex.org/W2963403868","https://openalex.org/W2963557522","https://openalex.org/W2963626623","https://openalex.org/W2963674932","https://openalex.org/W2963679688","https://openalex.org/W2964050280","https://openalex.org/W2964299589","https://openalex.org/W2964308564","https://openalex.org/W2969338443","https://openalex.org/W2988635181","https://openalex.org/W2997476292","https://openalex.org/W3099785009","https://openalex.org/W3101804962","https://openalex.org/W3104331387","https://openalex.org/W3163667142","https://openalex.org/W4214583996"],"related_works":["https://openalex.org/W3144599012","https://openalex.org/W2802855137","https://openalex.org/W2797932837","https://openalex.org/W3198042046","https://openalex.org/W3206030841","https://openalex.org/W2982334233","https://openalex.org/W2770323544","https://openalex.org/W2972304044","https://openalex.org/W3085407149","https://openalex.org/W3118277784","https://openalex.org/W3005857843","https://openalex.org/W2896769682","https://openalex.org/W3134677209","https://openalex.org/W3165698711","https://openalex.org/W2939464253","https://openalex.org/W2535731875","https://openalex.org/W2947694249","https://openalex.org/W2899742314","https://openalex.org/W2605831051","https://openalex.org/W3088864312"],"abstract_inverted_index":{"Deep":[0],"neural":[1,200],"networks":[2],"(DNNs)":[3],"are":[4],"becoming":[5],"a":[6,76,98,115,122,128,142,153,181,190,207,214,231],"key":[7],"enabling":[8],"technique":[9],"for":[10,97,127,158],"many":[11,35],"application":[12],"domains.":[13],"However,":[14],"on-device":[15],"inference":[16,107,211,235],"on":[17,86,180,246],"battery-powered,":[18],"resource-constrained":[19],"embedding":[20],"systems":[21],"is":[22,42],"often":[23,43,59],"infeasible":[24],"due":[25,45],"to":[26,46,80,95,113,119,125,151,156,166],"prohibitively":[27],"long":[28],"inferencing":[29,63],"time":[30,212,236],"and":[31,106,131,145,173,188,198],"resource":[32],"requirements":[33],"of":[34,54,70,84,192,249],"DNNs.":[36],"Offloading":[37],"computation":[38],"into":[39],"the":[40,52,68,103,132,148,220,238,247],"cloud":[41],"unacceptable":[44],"privacy":[47],"concerns,":[48],"high":[49],"latency,":[50],"or":[51],"lack":[53],"connectivity.":[55],"Although":[56],"compression":[57],"algorithms":[58],"succeed":[60],"in":[61,210,217,234],"reducing":[62],"times,":[64],"they":[65],"come":[66],"at":[67],"cost":[69],"reduced":[71],"accuracy.":[72],"This":[73],"article":[74],"presents":[75],"new,":[77,159],"alternative":[78],"approach":[79,90,165,179],"enable":[81],"efficient":[82],"execution":[83],"DNNs":[85],"embedded":[87,184],"devices.":[88],"Our":[89],"dynamically":[91],"determines":[92],"which":[93],"DNN":[94,124,154,169,194,224],"use":[96,126,157],"given":[99,129],"input":[100,130],"by":[101,139],"considering":[102],"desired":[104],"accuracy":[105,218],"time.":[108],"It":[109],"employs":[110],"machine":[111,174,227],"learning":[112,186],"develop":[114],"low-cost":[116],"predictive":[117,143],"model":[118,144,150,155,242],"quickly":[120],"select":[121,152],"pre-trained":[123],"optimization":[133],"constraint.":[134],"We":[135,162,176],"achieve":[136,206,230],"this":[137],"first":[138],"offline":[140],"training":[141],"then":[146],"using":[147],"learned":[149],"unseen":[160],"inputs.":[161],"apply":[163],"our":[164,178],"two":[167],"representative":[168],"domains:":[170],"image":[171,203],"classification":[172],"translation.":[175,250],"evaluate":[177],"Jetson":[182],"TX2":[183],"deep":[185],"platform":[187],"consider":[189],"range":[191],"influential":[193],"models":[195],"including":[196],"convolutional":[197],"recurrent":[199],"networks.":[201],"For":[202,226],"classification,":[204],"we":[205,229],"1.8x":[208],"reduction":[209,233],"with":[213,243],"7.52%":[215],"improvement":[216],"over":[219,237],"most":[221,239],"capable":[222,240],"single":[223,241],"model.":[225],"translation,":[228],"1.34x":[232],"little":[244],"impact":[245],"quality":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}