{"id":"https://openalex.org/W7117291385","doi":"https://doi.org/10.1109/access.2025.3648968","title":"Small-Object Detection at the Edge: A Pareto-Efficient Benchmark of Lightweight YOLO Models on UAV and Overhead Datasets","display_name":"Small-Object Detection at the Edge: A Pareto-Efficient Benchmark of Lightweight YOLO Models on UAV and Overhead Datasets","publication_year":2025,"publication_date":"2025-12-26","ids":{"openalex":"https://openalex.org/W7117291385","doi":"https://doi.org/10.1109/access.2025.3648968"},"language":null,"primary_location":{"id":"doi:10.1109/access.2025.3648968","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3648968","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3648968","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000394079","display_name":"Bijay Shakya","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Bijay Shakya","raw_affiliation_strings":["Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"],"affiliations":[{"raw_affiliation_string":"Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027631672","display_name":"O. El-Gayar","orcid":null},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Omar El-Gayar","raw_affiliation_strings":["College of Business and Information Systems, Dakota State University, Madison, SD, USA"],"affiliations":[{"raw_affiliation_string":"College of Business and Information Systems, Dakota State University, Madison, SD, USA","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031601362","display_name":"Jihene Kaabi","orcid":"https://orcid.org/0000-0002-9677-9607"},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jihene Kaabi","raw_affiliation_strings":["Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"],"affiliations":[{"raw_affiliation_string":"Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA","institution_ids":["https://openalex.org/I125467818"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013312714","display_name":"Khandaker Mamun Ahmed","orcid":"https://orcid.org/0000-0002-4713-188X"},"institutions":[{"id":"https://openalex.org/I125467818","display_name":"Dakota State University","ror":"https://ror.org/016yv6y68","country_code":"US","type":"education","lineage":["https://openalex.org/I125467818"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Khandaker Mamun Ahmed","raw_affiliation_strings":["Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA"],"affiliations":[{"raw_affiliation_string":"Beacom College of Computer and Cyber Sciences, Dakota State University, Madison, SD, USA","institution_ids":["https://openalex.org/I125467818"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5000394079"],"corresponding_institution_ids":["https://openalex.org/I125467818"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.64358608,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"528","last_page":"548"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9370999932289124,"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":0.9370999932289124,"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/T11133","display_name":"UAV Applications and Optimization","score":0.011699999682605267,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10273","display_name":"IoT and Edge/Fog Computing","score":0.010300000198185444,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/benchmark","display_name":"Benchmark (surveying)","score":0.739300012588501},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.7002000212669373},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6428999900817871},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6108999848365784},{"id":"https://openalex.org/keywords/energy-consumption","display_name":"Energy consumption","score":0.5942999720573425},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.5891000032424927},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5769000053405762},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4950999915599823},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.49059998989105225},{"id":"https://openalex.org/keywords/testbed","display_name":"Testbed","score":0.478300005197525}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8314999938011169},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.739300012588501},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.7002000212669373},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6428999900817871},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6108999848365784},{"id":"https://openalex.org/C2780165032","wikidata":"https://www.wikidata.org/wiki/Q16869822","display_name":"Energy consumption","level":2,"score":0.5942999720573425},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.5891000032424927},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5769000053405762},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4950999915599823},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.49059998989105225},{"id":"https://openalex.org/C31395832","wikidata":"https://www.wikidata.org/wiki/Q1318674","display_name":"Testbed","level":2,"score":0.478300005197525},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611999988555908},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4345000088214874},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.42669999599456787},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.4092999994754791},{"id":"https://openalex.org/C186370098","wikidata":"https://www.wikidata.org/wiki/Q442787","display_name":"Energy (signal processing)","level":2,"score":0.39959999918937683},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3986000120639801},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.38830000162124634},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.38260000944137573},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3781000077724457},{"id":"https://openalex.org/C2778049539","wikidata":"https://www.wikidata.org/wiki/Q17002908","display_name":"Bayesian optimization","level":2,"score":0.35989999771118164},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.3555000126361847},{"id":"https://openalex.org/C117797892","wikidata":"https://www.wikidata.org/wiki/Q286363","display_name":"Shadow (psychology)","level":2,"score":0.3538999855518341},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.34860000014305115},{"id":"https://openalex.org/C137635306","wikidata":"https://www.wikidata.org/wiki/Q182667","display_name":"Pareto principle","level":2,"score":0.3467000126838684},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.33719998598098755},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.32710000872612},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3050999939441681},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.30000001192092896},{"id":"https://openalex.org/C93996380","wikidata":"https://www.wikidata.org/wiki/Q44127","display_name":"Server","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.2906999886035919},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2870999872684479},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25529998540878296},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2025.3648968","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3648968","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3648968","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3648968","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.8482789993286133,"display_name":"Affordable and clean energy","id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W3019909811","https://openalex.org/W3042916480","https://openalex.org/W3046289513","https://openalex.org/W3122050197","https://openalex.org/W3122799380","https://openalex.org/W3124432240","https://openalex.org/W3208645658","https://openalex.org/W3213063024","https://openalex.org/W3214897310","https://openalex.org/W3215941943","https://openalex.org/W4229453634","https://openalex.org/W4297676427","https://openalex.org/W4309900042","https://openalex.org/W4322503836","https://openalex.org/W4382137697","https://openalex.org/W4382568144","https://openalex.org/W4385555853","https://openalex.org/W4385839827","https://openalex.org/W4386868384","https://openalex.org/W4386963036","https://openalex.org/W4392811632","https://openalex.org/W4396216689","https://openalex.org/W4396860960","https://openalex.org/W4398756379","https://openalex.org/W4401485877","https://openalex.org/W4403770406","https://openalex.org/W4409796263","https://openalex.org/W4410774956"],"related_works":[],"abstract_inverted_index":{"Small-object":[0],"detection":[1,229],"plays":[2],"a":[3,47,66,89],"critical":[4],"role":[5],"in":[6,161,206],"real-time":[7],"aerial,":[8],"Unmanned":[9],"Aerial":[10],"Vehicle":[11],"(UAV),":[12],"and":[13,26,34,82,92,100,111,121,136,147,156,163,185,209,224],"satellite":[14],"vision":[15,235],"systems,":[16],"as":[17,19],"well":[18],"many":[20],"other":[21],"domains,":[22],"where":[23],"hardware":[24],"constraints":[25],"deployment":[27],"environments":[28],"demand":[29],"high":[30],"accuracy,":[31],"low":[32],"latency,":[33,132],"energy":[35,137],"efficiency.":[36],"Although":[37],"numerous":[38],"lightweight":[39,73],"object":[40],"detectors":[41,215],"have":[42],"been":[43],"proposed,":[44],"there":[45],"exists":[46],"lack":[48],"of":[49,70,203,227],"rigorous,":[50],"cross-platform":[51],"benchmarks":[52],"that":[53,145,190],"evaluate":[54],"these":[55],"models":[56],"under":[57],"consistent":[58],"conditions":[59],"for":[60,213,231],"small-object-focused":[61],"applications.":[62],"This":[63],"paper":[64],"presents":[65],"comprehensive":[67],"comparative":[68],"evaluation":[69,126],"eight":[71],"recent":[72],"You":[74],"Look":[75],"Only":[76],"Once":[77],"(YOLO)-based":[78],"models,":[79],"including":[80],"YOLOX-Nano":[81],"YOLOv6\u2013v12":[83],"variants.":[84],"Models":[85],"are":[86],"trained":[87],"using":[88,119],"unified":[90],"pipeline":[91],"evaluated":[93],"on":[94,105,182,217],"three":[95],"representative":[96],"datasets:":[97],"VisDrone2019,":[98],"DOTA-v1.5,":[99],"xView.":[101],"Performance":[102],"is":[103],"assessed":[104],"both":[106],"cloud":[107],"GPUs":[108],"(NVIDIA":[109],"A100)":[110],"an":[112],"edge":[113,207],"AI":[114,208],"platform":[115],"(Jetson":[116],"Orin":[117],"Nano),":[118],"PyTorch":[120],"TensorRT":[122,165],"(FP16)":[123],"runtimes.":[124],"The":[125,198,220],"metrics":[127],"include":[128],"mAP@0.5,":[129],"mAP@0.5:0.95,":[130],"F1-score,":[131],"FPS,":[133],"memory":[134],"footprint,":[135],"consumption":[138],"(via":[139],"VDD_IN":[140],"telemetry).":[141],"Experimental":[142],"results":[143],"demonstrate":[144],"YOLOv8-Nano":[146],"YOLOv9-Tiny":[148],"achieve":[149],"leading":[150],"accuracy":[151],"across":[152,195],"datasets,":[153],"while":[154],"YOLOv6-Nano":[155],"YOLOv10-Nano":[157],"offer":[158],"favorable":[159],"trade-offs":[160],"speed":[162],"memory.":[164],"optimization":[166],"yields":[167],"3\u00d7\u20135\u00d7":[168],"speedup":[169],"over":[170],"PyTorch.":[171],"Energy":[172],"draw":[173],"ranges":[174],"from":[175],"7.6":[176],"W":[177],"to":[178],"10.4":[179],"W,":[180],"depending":[181],"the":[183,201],"model":[184,193],"configuration.":[186],"Pareto":[187],"frontiers":[188],"reveal":[189],"no":[191],"single":[192],"dominates":[194],"all":[196],"objectives.":[197],"study":[199],"highlights":[200],"importance":[202],"multi-objective":[204],"benchmarking":[205],"provides":[210],"practical":[211],"guidance":[212],"selecting":[214],"based":[216],"deployment-specific":[218],"constraints.":[219],"findings":[221],"support":[222],"theory-driven":[223],"application-oriented":[225],"advancement":[226],"efficient":[228],"architectures":[230],"real-time,":[232],"resource-aware":[233],"computer":[234],"systems.":[236]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-12-26T00:00:00"}