{"id":"https://openalex.org/W7127084009","doi":"https://doi.org/10.48550/arxiv.2601.22830","title":"A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF Conditions","display_name":"A Comparative Evaluation of Large Vision-Language Models for 2D Object Detection under SOTIF Conditions","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7127084009","doi":"https://doi.org/10.48550/arxiv.2601.22830"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.22830","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.22830","pdf_url":"https://arxiv.org/pdf/2601.22830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.22830","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5124782616","display_name":"Ji Zhou","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Zhou, Ji","raw_affiliation_strings":["Institute of Automotive Engineering , Graz University of Technology , 8010 Graz , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automotive Engineering , Graz University of Technology , 8010 Graz , Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124762015","display_name":"Yilin Ding","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Ding, Yilin","raw_affiliation_strings":["Institute of Automotive Engineering , Graz University of Technology , 8010 Graz , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automotive Engineering , Graz University of Technology , 8010 Graz , Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124826111","display_name":"Yongqi Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Zhao, Yongqi","raw_affiliation_strings":["Institute of Automotive Engineering , Graz University of Technology , 8010 Graz , Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automotive Engineering , Graz University of Technology , 8010 Graz , Austria","institution_ids":["https://openalex.org/I4092182"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124763196","display_name":"Jiachen Xu","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164339","display_name":"Oldham Council","ror":"https://ror.org/05cxzzq07","country_code":"GB","type":"government","lineage":["https://openalex.org/I4210164339"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Xu, Jiachen","raw_affiliation_strings":["Independent Researcher , 200000 Shanghai , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Independent Researcher , 200000 Shanghai , China","institution_ids":["https://openalex.org/I4210164339"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5138721554","display_name":"Dong Bi","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4092182","display_name":"Graz University of Technology","ror":"https://ror.org/00d7xrm67","country_code":"AT","type":"education","lineage":["https://openalex.org/I4092182"]},{"id":"https://openalex.org/I4210126203","display_name":"Hubei University of Automotive Technology","ror":"https://ror.org/039m95m06","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210126203"]}],"countries":["AT","CN"],"is_corresponding":false,"raw_author_name":"Bi, Dong","raw_affiliation_strings":["Institute of Automotive Engineering , Graz University of Technology , 8010 Graz , Austria","School of Intelligent Connected Vehicle , Hubei University of Automotive Technology , 442002 Shiyan , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automotive Engineering , Graz University of Technology , 8010 Graz , Austria","institution_ids":["https://openalex.org/I4092182"]},{"raw_affiliation_string":"School of Intelligent Connected Vehicle , Hubei University of Automotive Technology , 442002 Shiyan , China","institution_ids":["https://openalex.org/I4210126203"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5121602337","display_name":"Johannes Betz","orcid":"https://orcid.org/0000-0001-9197-2849","observed_orcids":["https://orcid.org/0000-0001-9197-2849"]},"institutions":[{"id":"https://openalex.org/I62916508","display_name":"Technical University of Munich","ror":"https://ror.org/02kkvpp62","country_code":"DE","type":"education","lineage":["https://openalex.org/I62916508"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Betz, Johannes","raw_affiliation_strings":["Professorship of Autonomous Vehicle Systems , Technical University of Munich , 85748 Garching , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Professorship of Autonomous Vehicle Systems , Technical University of Munich , 85748 Garching , Germany","institution_ids":["https://openalex.org/I62916508"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5084393303","display_name":"Arno Eichberger","orcid":"https://orcid.org/0000-0001-8246-8085","observed_orcids":["https://orcid.org/0000-0001-8246-8085"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Eichberger, Arno","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9326000213623047,"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":0.9326000213623047,"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":0.03759999945759773,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.007000000216066837,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/large-vision-language-models","display_name":"large vision-language models","score":0.9259999990463257},{"id":"https://openalex.org/keywords/2d-object-detection","display_name":"2D object detection","score":0.9319999814033508},{"id":"https://openalex.org/keywords/safety-of-the-intended-functionality","display_name":"safety of the intended functionality","score":0.8889999985694885},{"id":"https://openalex.org/keywords/autonomous-driving","display_name":"autonomous driving","score":0.7580000162124634},{"id":"https://openalex.org/keywords/environmental-perception","display_name":"environmental perception","score":0.7590000033378601},{"id":"https://openalex.org/keywords/visual-degradation","display_name":"visual deterioration","score":0.9049999713897705},{"id":"https://openalex.org/keywords/yolov5","display_name":"YOLOv5","score":0.9200000166893005},{"id":"https://openalex.org/keywords/gemini-3","display_name":"Gemini 3","score":0.6840000152587891}],"concepts":[{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7093999981880188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507999897003174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6384999752044678},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6215999722480774},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5558000206947327},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5288000106811523},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5267999768257141},{"id":"https://openalex.org/C81669768","wikidata":"https://www.wikidata.org/wiki/Q2359161","display_name":"Precision and recall","level":2,"score":0.45910000801086426},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.392300009727478},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34599998593330383},{"id":"https://openalex.org/C178253425","wikidata":"https://www.wikidata.org/wiki/Q162668","display_name":"Visual perception","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C100660578","wikidata":"https://www.wikidata.org/wiki/Q18733","display_name":"Recall","level":2,"score":0.32249999046325684},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.31690001487731934},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3133000135421753},{"id":"https://openalex.org/C3017944768","wikidata":"https://www.wikidata.org/wiki/Q1450463","display_name":"Poison control","level":2,"score":0.3005000054836273},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2915000021457672},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.29030001163482666},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2797999978065491},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2718000113964081}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.22830","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.22830","pdf_url":"https://arxiv.org/pdf/2601.22830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"doi:10.48550/arxiv.2601.22830","doi":"https://doi.org/10.48550/arxiv.2601.22830","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.22830","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.22830","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/abs/2601.22830","pdf_url":"https://arxiv.org/pdf/2601.22830","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127084009.pdf","grobid_xml":"https://content.openalex.org/works/W7127084009.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4417515405","https://openalex.org/W7111016626","https://openalex.org/W7162443602","https://openalex.org/W4413000198","https://openalex.org/W4416238263","https://openalex.org/W4412791139","https://openalex.org/W4415157581","https://openalex.org/W7108201988","https://openalex.org/W7139951665","https://openalex.org/W7164627852"],"abstract_inverted_index":{"Reliable":[0],"environmental":[1,78],"perception":[2,25],"remains":[3],"one":[4],"of":[5,12,16,61,140,149],"the":[6,17,66,88,92,107,137,147],"main":[7],"obstacles":[8],"for":[9,48,73,131],"safe":[10],"operation":[11],"automated":[13,157],"vehicles.":[14],"Safety":[15],"Intended":[18],"Functionality":[19],"(SOTIF)":[20],"concerns":[21],"safety":[22,153],"risks":[23],"from":[24],"insufficiencies,":[26],"particularly":[27],"under":[28,118],"adverse":[29],"conditions":[30],"where":[31],"conventional":[32],"detectors":[33,124],"often":[34],"falter.":[35],"While":[36],"Large":[37],"Vision-Language":[38],"Models":[39],"(LVLMs)":[40],"demonstrate":[41],"promising":[42],"semantic":[43,141],"reasoning,":[44],"their":[45],"quantitative":[46],"effectiveness":[47],"safety-critical":[49],"2D":[50],"object":[51],"detection":[52],"is":[53,81],"underexplored.":[54],"This":[55],"paper":[56],"presents":[57],"a":[58,69,98],"systematic":[59],"evaluation":[60],"ten":[62],"representative":[63],"LVLMs":[64,102,150],"using":[65],"PeSOTIF":[67],"dataset,":[68],"benchmark":[70],"specifically":[71],"curated":[72],"long-tail":[74],"traffic":[75],"scenarios":[76],"and":[77,91,114],"degradations.":[79],"Performance":[80],"quantitatively":[82],"compared":[83],"against":[84],"two":[85],"specialized":[86,123],"detectors:":[87],"anchor-based":[89],"YOLOv5":[90,108],"transformer-based":[93],"RT-DETRv4.":[94],"Experimental":[95],"results":[96],"reveal":[97],"critical":[99],"trade-off:":[100],"top-performing":[101],"(e.g.,":[103],"Gemini":[104],"3)":[105],"surpass":[106],"in":[109,128,155],"recall":[110],"by":[111],"over":[112],"25%":[113],"closely":[115],"match":[116],"RT-DETRv4":[117],"natural":[119],"visual":[120],"degradation,":[121],"while":[122],"retain":[125],"an":[126],"advantage":[127],"geometric":[129,144],"precision":[130],"handcrafted":[132],"perturbations.":[133],"These":[134],"findings":[135],"highlight":[136],"complementary":[138],"strengths":[139],"reasoning":[142],"versus":[143],"regression,":[145],"supporting":[146],"use":[148],"as":[151],"high-level":[152],"validators":[154],"SOTIF-oriented":[156],"driving":[158],"systems.":[159]},"counts_by_year":[],"updated_date":"2026-10-28T10:33:24.094632","created_date":"2026-02-03T00:00:00"}