{"id":"https://openalex.org/W7128733848","doi":"https://doi.org/10.48550/arxiv.2602.11004","title":"Enhancing Predictability of Multi-Tenant DNN Inference for Autonomous Vehicles' Perception","display_name":"Enhancing Predictability of Multi-Tenant DNN Inference for Autonomous Vehicles' Perception","publication_year":2026,"publication_date":"2026-02-11","ids":{"openalex":"https://openalex.org/W7128733848","doi":"https://doi.org/10.48550/arxiv.2602.11004"},"language":null,"primary_location":{"id":"pmh:doi:10.48550/arxiv.2602.11004","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":null,"any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5039156669","display_name":"Liangkai Liu","orcid":"https://orcid.org/0000-0002-6149-9859"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Liangkai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Shin, Kang G.","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shin, Kang G.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125770781","display_name":"Jinkyu Lee","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lee, Jinkyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125770090","display_name":"Chengmo Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Chengmo","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5125747193","display_name":"Weisong Shi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shi, Weisong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.5443000197410583,"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":0.5443000197410583,"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/T11099","display_name":"Autonomous Vehicle Technology and Safety","score":0.16179999709129333,"subfield":{"id":"https://openalex.org/subfields/2203","display_name":"Automotive 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":0.1574999988079071,"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/inference","display_name":"Inference","score":0.6786999702453613},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6593000292778015},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.6004999876022339},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5437999963760376},{"id":"https://openalex.org/keywords/predictability","display_name":"Predictability","score":0.5034000277519226},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4372999966144562},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.3776000142097473},{"id":"https://openalex.org/keywords/region-of-interest","display_name":"Region of interest","score":0.34360000491142273}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7577999830245972},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6786999702453613},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6779999732971191},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6593000292778015},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.6004999876022339},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5437999963760376},{"id":"https://openalex.org/C197640229","wikidata":"https://www.wikidata.org/wiki/Q2534066","display_name":"Predictability","level":2,"score":0.5034000277519226},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.45590001344680786},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4372999966144562},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.3776000142097473},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37209999561309814},{"id":"https://openalex.org/C19609008","wikidata":"https://www.wikidata.org/wiki/Q2138203","display_name":"Region of interest","level":2,"score":0.34360000491142273},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33059999346733093},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.31529998779296875},{"id":"https://openalex.org/C65909025","wikidata":"https://www.wikidata.org/wiki/Q1945033","display_name":"Monocular","level":2,"score":0.3075000047683716},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.30730000138282776},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30169999599456787},{"id":"https://openalex.org/C3261483","wikidata":"https://www.wikidata.org/wiki/Q119565","display_name":"Frame rate","level":2,"score":0.29120001196861267},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.27639999985694885},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.2637999951839447},{"id":"https://openalex.org/C116834253","wikidata":"https://www.wikidata.org/wiki/Q2039217","display_name":"Identification (biology)","level":2,"score":0.260699987411499}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:doi:10.48550/arxiv.2602.11004","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},{"id":"doi:10.48550/arxiv.2602.11004","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2602.11004","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":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:doi:10.48550/arxiv.2602.11004","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"public-domain","license_id":"https://openalex.org/licenses/public-domain","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Autonomous":[0],"vehicles":[1],"(AVs)":[2],"rely":[3],"on":[4,57,120,170],"sensors":[5],"and":[6,16,44,74,112,127,143,147,167,176,195,206,233,239,267,277],"deep":[7],"neural":[8],"networks":[9],"(DNNs)":[10],"to":[11,36,63,94,141,163,185,246,259,282],"perceive":[12],"their":[13],"surrounding":[14,135],"environment":[15],"make":[17],"maneuver":[18],"decisions":[19],"in":[20,28,149,228],"real":[21],"time.":[22],"However,":[23,137],"achieving":[24],"real-time":[25],"DNN":[26,60,70,210],"inference":[27,61],"the":[29,37,41,45,59,69,89,99,133,171,191,201,219,237,240,252,262,278,285],"AV's":[30,46,134],"perception":[31,66,220,249],"pipeline":[32,232],"is":[33,118,139,244],"challenging":[34,140],"due":[35],"large":[38],"gap":[39],"between":[40],"computation":[42],"requirement":[43],"limited":[47],"resources.":[48],"Most,":[49],"if":[50],"not":[51],"all,":[52],"of":[53,91,102,114,173,203,221,254],"existing":[54],"studies":[55],"focus":[56],"optimizing":[58],"time":[62],"achieve":[64],"faster":[65],"by":[67,107,257,265,270,275,280],"compressing":[68],"model":[71],"with":[72,84,132,208,236],"pruning":[73],"quantization.":[75],"In":[76],"contrast,":[77],"we":[78,213],"present":[79],"a":[80,182,215],"Predictable":[81],"Perception":[82],"system":[83],"DNNs":[85,106,151],"(PP-DNN)":[86],"that":[87,124],"reduce":[88],"amount":[90],"image":[92],"data":[93],"be":[95],"processed":[96],"while":[97],"maintaining":[98],"same":[100],"level":[101],"accuracy":[103],"for":[104,129,152,218],"multi-tenant":[105,150],"dynamically":[108],"selecting":[109],"critical":[110,125,145,165,193,204],"frames":[111,126,146,166,175,194,205,256],"regions":[113],"interest":[115],"(ROIs).":[116],"PP-DNN":[117,158,179,227,243],"based":[119,169],"our":[121],"key":[122],"insight":[123],"ROIs":[128,148,168,207],"AVs":[130],"vary":[131],"environment.":[136],"it":[138,235],"identify":[142,164],"use":[144],"predictable":[153],"inference.":[154],"Given":[155],"image-frame":[156],"streams,":[157],"leverages":[159,181],"an":[160,229],"ROI":[161,198],"generator":[162],"similarities":[172],"consecutive":[174],"traffic":[177],"scenarios.":[178],"then":[180],"FLOPs":[183],"predictor":[184,217],"predict":[186],"multiply-accumulate":[187],"operations":[188],"(MACs)":[189],"from":[190],"dynamic":[192],"ROIs.":[196],"The":[197],"scheduler":[199],"coordinates":[200],"processing":[202],"multiple":[209],"models.":[211],"Finally,":[212],"design":[214],"detection":[216,273],"non-critical":[222],"frames.":[223],"We":[224],"have":[225],"implemented":[226],"ROS-based":[230],"AV":[231],"evaluated":[234],"BDD100K":[238],"nuScenes":[241],"dataset.":[242],"observed":[245],"significantly":[247],"enhance":[248],"predictability,":[250],"increasing":[251],"number":[253],"fusion":[255,263],"up":[258,281],"7.3x,":[260],"reducing":[261],"delay":[264],">2.6x":[266],"fusion-delay":[268],"variations":[269],">2.3x,":[271],"improving":[272],"completeness":[274],"75.4%":[276],"cost-effectiveness":[279],"98%":[283],"over":[284],"baseline.":[286]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-02-13T00:00:00"}