{"id":"https://openalex.org/W4393899650","doi":"https://doi.org/10.1117/12.3023487","title":"Efficient single- and multi-DNN inference using TensorRT framework","display_name":"Efficient single- and multi-DNN inference using TensorRT framework","publication_year":2024,"publication_date":"2024-04-03","ids":{"openalex":"https://openalex.org/W4393899650","doi":"https://doi.org/10.1117/12.3023487"},"language":"en","primary_location":{"id":"doi:10.1117/12.3023487","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.3023487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixteenth International Conference on Machine Vision (ICMV 2023)","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/A5031899675","display_name":"Vyacheslav Zhdanovskiy","orcid":"https://orcid.org/0000-0002-5079-9530"},"institutions":[{"id":"https://openalex.org/I153845743","display_name":"Moscow Institute of Physics and Technology","ror":"https://ror.org/00v0z9322","country_code":"RU","type":"education","lineage":["https://openalex.org/I153845743"]}],"countries":["RU"],"is_corresponding":true,"raw_author_name":"Vyacheslav Zhdanovskiy","raw_affiliation_strings":["Moscow Institute of Physics and Technology (Russian Federation)","NVI Research LLC (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"Moscow Institute of Physics and Technology (Russian Federation)","institution_ids":["https://openalex.org/I153845743"]},{"raw_affiliation_string":"NVI Research LLC (Russian Federation)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066717365","display_name":"Lev Teplyakov","orcid":"https://orcid.org/0000-0003-2720-8795"},"institutions":[{"id":"https://openalex.org/I4210107660","display_name":"Institute for Information Transmission Problems","ror":"https://ror.org/013w2d378","country_code":"RU","type":"facility","lineage":["https://openalex.org/I1313323035","https://openalex.org/I4210097085","https://openalex.org/I4210107660"]}],"countries":["RU"],"is_corresponding":false,"raw_author_name":"Lev Teplyakov","raw_affiliation_strings":["Institute for Information Transmission Problems (Russian Federation)","NVI Research LLC (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"Institute for Information Transmission Problems (Russian Federation)","institution_ids":["https://openalex.org/I4210107660"]},{"raw_affiliation_string":"NVI Research LLC (Russian Federation)","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109699022","display_name":"Philipp Belyaev","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philipp Belyaev","raw_affiliation_strings":["NVI Research LLC (Russian Federation)"],"affiliations":[{"raw_affiliation_string":"NVI Research LLC (Russian Federation)","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5031899675"],"corresponding_institution_ids":["https://openalex.org/I153845743"],"apc_list":null,"apc_paid":null,"fwci":0.265,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.4753304,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"43","last_page":"43"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":1.0,"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":1.0,"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":0.9950000047683716,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9868999719619751,"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":0.8384052515029907},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7250427007675171},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.6759622097015381},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.6669981479644775},{"id":"https://openalex.org/keywords/scheduling","display_name":"Scheduling (production processes)","score":0.6197893023490906},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4546710252761841},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.44702696800231934},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.309647798538208},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.30203837156295776},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.07470902800559998},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.06934422254562378}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8384052515029907},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7250427007675171},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.6759622097015381},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.6669981479644775},{"id":"https://openalex.org/C206729178","wikidata":"https://www.wikidata.org/wiki/Q2271896","display_name":"Scheduling (production processes)","level":2,"score":0.6197893023490906},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4546710252761841},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.44702696800231934},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.309647798538208},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.30203837156295776},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.07470902800559998},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.06934422254562378},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1117/12.3023487","is_oa":false,"landing_page_url":"https://doi.org/10.1117/12.3023487","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Sixteenth International Conference on Machine Vision (ICMV 2023)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":31,"referenced_works":["https://openalex.org/W164384110","https://openalex.org/W2782970864","https://openalex.org/W2885010062","https://openalex.org/W3014810041","https://openalex.org/W3087507349","https://openalex.org/W3087858202","https://openalex.org/W3096609285","https://openalex.org/W3156943756","https://openalex.org/W3169512402","https://openalex.org/W3184606595","https://openalex.org/W4200328352","https://openalex.org/W4210338699","https://openalex.org/W4220925575","https://openalex.org/W4226023410","https://openalex.org/W4238701792","https://openalex.org/W4251989754","https://openalex.org/W4295312788","https://openalex.org/W4302296459","https://openalex.org/W4322730957","https://openalex.org/W4367043644","https://openalex.org/W6606696249","https://openalex.org/W6637151318","https://openalex.org/W6748208869","https://openalex.org/W6753585227","https://openalex.org/W6762718338","https://openalex.org/W6766978945","https://openalex.org/W6783441721","https://openalex.org/W6803585744","https://openalex.org/W6810770509","https://openalex.org/W6810870312","https://openalex.org/W6850499879"],"related_works":["https://openalex.org/W3062287","https://openalex.org/W2380390332","https://openalex.org/W2742145873","https://openalex.org/W2023572661","https://openalex.org/W4245975140","https://openalex.org/W2532592438","https://openalex.org/W1977763331","https://openalex.org/W2062253548","https://openalex.org/W3042419602","https://openalex.org/W2966649771"],"abstract_inverted_index":{"In":[0,29],"the":[1,92,99,111],"recent":[2],"years,":[3],"there":[4],"has":[5],"been":[6],"a":[7,34,41,71,74,95,106,122,168],"significant":[8],"growth":[9],"of":[10,37,64,94,101,105,118,121],"interest":[11],"in":[12,68,91],"real-world":[13],"systems":[14,22],"based":[15],"on":[16,40],"deep":[17],"neural":[18],"networks":[19],"(DNNs).":[20],"These":[21],"typically":[23],"incorporate":[24],"multiple":[25,45,65,127,137],"DNNs":[26,76],"running":[27],"simultaneously.":[28],"this":[30],"paper":[31],"we":[32,114],"propose":[33],"novel":[35],"approach":[36,84],"multi-DNN":[38],"execution":[39,143],"single":[42,123],"GPU":[43],"using":[44,140,171],"CUDA":[46],"contexts":[47],"and":[48,73,132],"TensorRT,":[49],"state-of-the-art":[50],"DNN":[51,97,124,170],"inference":[52],"framework.":[53],"We":[54,80,145],"show":[55,81,146],"that":[56,82,147],"it":[57],"can":[58,85,160],"lead":[59],"to":[60,110,163],"more":[61,165],"efficient":[62],"scheduling":[63],"DNNs,":[66],"especially":[67],"case":[69],"when":[70],"lightweight":[72,96],"heavy":[75,107],"are":[77],"inferred":[78],"together.":[79],"our":[83],"provide":[86,161],"an":[87],"almost":[88],"7x":[89],"increase":[90],"throughput":[93,103,120,166],"at":[98,154],"cost":[100],"neglible":[102],"drop":[104],"DNN,":[108],"compared":[109],"baseline.":[112],"Moreover,":[113],"compare":[115],"two":[116],"ways":[117],"improving":[119],"by":[125,135],"processing":[126,136],"images":[128,138],"together:":[129],"standard":[130,149],"batching":[131,134,150,153,159],"implicit":[133,152,158],"simultaneously":[139],"several":[141],"TensorRT":[142],"contexts.":[144],"meanwhile":[148],"outperforms":[151],"larger":[155],"batch":[156,173],"sizes,":[157],"up":[162],"43%":[164],"for":[167],"smaller":[169,172],"size.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}