{"id":"https://openalex.org/W7131095274","doi":"https://doi.org/10.1109/iccvw69036.2025.00086","title":"Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection","display_name":"Uncertainty-Aware Likelihood Ratio Estimation for Pixel-Wise Out-of-Distribution Detection","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W7131095274","doi":"https://doi.org/10.1109/iccvw69036.2025.00086"},"language":null,"primary_location":{"id":"doi:10.1109/iccvw69036.2025.00086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","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/A5071833534","display_name":"Marc H\u00f6lle","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Marc H\u00f6lle","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg,Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg,Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Walter Kellermann","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Walter Kellermann","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg,Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg,Germany","institution_ids":["https://openalex.org/I181369854"]}]},{"author_position":"last","author":{"id":null,"display_name":"Vasileios Belagiannis","orcid":null},"institutions":[{"id":"https://openalex.org/I181369854","display_name":"Friedrich-Alexander-Universit\u00e4t Erlangen-N\u00fcrnberg","ror":"https://ror.org/00f7hpc57","country_code":"DE","type":"education","lineage":["https://openalex.org/I181369854"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Vasileios Belagiannis","raw_affiliation_strings":["Friedrich-Alexander-Universität Erlangen-Nürnberg,Germany"],"affiliations":[{"raw_affiliation_string":"Friedrich-Alexander-Universität Erlangen-Nürnberg,Germany","institution_ids":["https://openalex.org/I181369854"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5071833534"],"corresponding_institution_ids":["https://openalex.org/I181369854"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.86571336,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"783","last_page":"793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.26600000262260437,"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"}},"topics":[{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.26600000262260437,"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/T12153","display_name":"Advanced Optical Sensing Technologies","score":0.07609999924898148,"subfield":{"id":"https://openalex.org/subfields/3105","display_name":"Instrumentation"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.056299999356269836,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6726999878883362},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6622999906539917},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4993000030517578},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.45419999957084656},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4471000134944916},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.42879998683929443},{"id":"https://openalex.org/keywords/imperfect","display_name":"Imperfect","score":0.4171999990940094},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4108999967575073},{"id":"https://openalex.org/keywords/point","display_name":"Point (geometry)","score":0.4011000096797943}],"concepts":[{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6726999878883362},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6622999906539917},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5636000037193298},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5012000203132629},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4993000030517578},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.45419999957084656},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4471000134944916},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.42879998683929443},{"id":"https://openalex.org/C2780310539","wikidata":"https://www.wikidata.org/wiki/Q12547192","display_name":"Imperfect","level":2,"score":0.4171999990940094},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.4133000075817108},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4108999967575073},{"id":"https://openalex.org/C28719098","wikidata":"https://www.wikidata.org/wiki/Q44946","display_name":"Point (geometry)","level":2,"score":0.4011000096797943},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3869999945163727},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.3862999975681305},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.3801000118255615},{"id":"https://openalex.org/C49781872","wikidata":"https://www.wikidata.org/wiki/Q1045555","display_name":"Maximum likelihood","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C44648626","wikidata":"https://www.wikidata.org/wiki/Q1049848","display_name":"Percentage point","level":2,"score":0.33980000019073486},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.335099995136261},{"id":"https://openalex.org/C9483764","wikidata":"https://www.wikidata.org/wiki/Q585740","display_name":"Likelihood-ratio test","level":2,"score":0.33219999074935913},{"id":"https://openalex.org/C87007009","wikidata":"https://www.wikidata.org/wiki/Q210832","display_name":"Statistical hypothesis testing","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.3122999966144562},{"id":"https://openalex.org/C41426520","wikidata":"https://www.wikidata.org/wiki/Q1192065","display_name":"Point estimation","level":2,"score":0.3052999973297119},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29789999127388},{"id":"https://openalex.org/C96250715","wikidata":"https://www.wikidata.org/wiki/Q965330","display_name":"Estimation","level":2,"score":0.29339998960494995},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.2770000100135803},{"id":"https://openalex.org/C182081679","wikidata":"https://www.wikidata.org/wiki/Q1275153","display_name":"Expectation\u2013maximization algorithm","level":3,"score":0.26989999413490295},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.26840001344680786},{"id":"https://openalex.org/C40969351","wikidata":"https://www.wikidata.org/wiki/Q3516228","display_name":"Word error rate","level":2,"score":0.26489999890327454},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.25760000944137573},{"id":"https://openalex.org/C57830394","wikidata":"https://www.wikidata.org/wiki/Q278079","display_name":"Posterior probability","level":3,"score":0.25690001249313354}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iccvw69036.2025.00086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccvw69036.2025.00086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W91088564","https://openalex.org/W2119880843","https://openalex.org/W2340897893","https://openalex.org/W2490662969","https://openalex.org/W2737258237","https://openalex.org/W2781228439","https://openalex.org/W2933610837","https://openalex.org/W2963149653","https://openalex.org/W2963944506","https://openalex.org/W2963995504","https://openalex.org/W2964059111","https://openalex.org/W2981786146","https://openalex.org/W3112906266","https://openalex.org/W3114997473","https://openalex.org/W3176640650","https://openalex.org/W4225896280","https://openalex.org/W4312601785","https://openalex.org/W4319300250","https://openalex.org/W4319300301","https://openalex.org/W4319301119","https://openalex.org/W4385805000","https://openalex.org/W4390190026","https://openalex.org/W4390190806","https://openalex.org/W4390872487","https://openalex.org/W4390872523","https://openalex.org/W4390873310","https://openalex.org/W4390873436","https://openalex.org/W4391843787","https://openalex.org/W4391952441","https://openalex.org/W4393153466","https://openalex.org/W4401415356","https://openalex.org/W4402716212","https://openalex.org/W4404536278","https://openalex.org/W4404672390","https://openalex.org/W4407450971","https://openalex.org/W4409263500","https://openalex.org/W4411929998"],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,79],"models":[2],"trained":[3],"on":[4,125],"known":[5,71],"object":[6,36],"classes":[7,37],"often":[8,39],"fail":[9],"in":[10,31,114],"real-world":[11],"autonomous":[12],"driving":[13],"scenarios":[14],"by":[15,111],"confidently":[16],"misclassifying":[17],"unknown":[18,26,43,73],"objects.":[19,44],"While":[20],"pixel-wise":[21],"out-of-distribution":[22],"detection":[23],"can":[24,119],"identify":[25],"objects,":[27],"existing":[28],"methods":[29],"struggle":[30],"complex":[32],"scenes":[33],"where":[34],"rare":[35,101],"are":[38],"confused":[40],"with":[41],"truly":[42],"We":[45,108],"introduce":[46],"an":[47,60],"uncertainty-aware":[48],"likelihood":[49,65],"ratio":[50,66],"estimation":[51],"method":[52,92,131],"that":[53,96,110],"addresses":[54],"these":[55],"limitations.":[56],"Our":[57],"approach":[58],"uses":[59],"evidential":[61],"classifier":[62],"within":[63],"a":[64,77],"test":[67],"to":[68],"distinguish":[69],"between":[70],"and":[72,104,148],"pixel":[74],"features":[75],"from":[76,99],"semantic":[78],"model,":[80],"while":[81,142],"explicitly":[82],"accounting":[83],"for":[84],"uncertainty.":[85],"Instead":[86],"of":[87],"producing":[88],"point":[89],"estimates,":[90],"our":[91,130],"outputs":[93],"probability":[94],"distributions":[95],"capture":[97],"uncertainty":[98,113],"both":[100],"training":[102],"examples":[103],"imperfect":[105],"synthetic":[106],"outliers.":[107],"show":[109],"incorporating":[112],"this":[115],"way,":[116],"outlier":[117],"exposure":[118],"be":[120],"leveraged":[121],"more":[122],"effectively.":[123],"Evaluated":[124],"five":[126],"standard":[127],"benchmark":[128],"datasets,":[129],"achieves":[132],"the":[133],"lowest":[134],"average":[135,145],"false":[136],"positive":[137],"rate":[138],"(2.5%)":[139],"among":[140],"state-of-the-art":[141],"maintaining":[143],"high":[144],"precision":[146],"(90.91%)":[147],"incurring":[149],"only":[150],"negligible":[151],"computational":[152],"overhead.":[153],"Code":[154],"is":[155],"available":[156],"at":[157],"https://github.com/glasbruch/ULRE.":[158]},"counts_by_year":[],"updated_date":"2026-03-25T23:56:10.502304","created_date":"2026-02-24T00:00:00"}