{"id":"https://openalex.org/W3036633009","doi":"https://doi.org/10.48550/arxiv.2006.11584","title":"Calibration of Model Uncertainty for Dropout Variational Inference","display_name":"Calibration of Model Uncertainty for Dropout Variational Inference","publication_year":2020,"publication_date":"2020-06-20","ids":{"openalex":"https://openalex.org/W3036633009","doi":"https://doi.org/10.48550/arxiv.2006.11584","mag":"3036633009"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2006.11584","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.11584","pdf_url":"https://arxiv.org/pdf/2006.11584","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.11584","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5071989904","display_name":"Max-Heinrich Laves","orcid":"https://orcid.org/0000-0003-0156-7247","observed_orcids":["https://orcid.org/0000-0003-0156-7247"]},"institutions":[{"id":"https://openalex.org/I114112103","display_name":"Leibniz University Hannover","ror":"https://ror.org/0304hq317","country_code":"DE","type":"education","lineage":["https://openalex.org/I114112103"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Laves, Max-Heinrich","raw_affiliation_strings":["Leibniz University of Hanover,"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Leibniz University of Hanover,","institution_ids":["https://openalex.org/I114112103"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068385096","display_name":"Sontje Ihler","orcid":"https://orcid.org/0000-0002-7495-3141","observed_orcids":["https://orcid.org/0000-0002-7495-3141"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ihler, Sontje","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030912644","display_name":"Karl-Philipp Kortmann","orcid":"https://orcid.org/0000-0002-0472-3316","observed_orcids":["https://orcid.org/0000-0002-0472-3316"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kortmann, Karl-Philipp","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028164919","display_name":"Tobias Ortmaier","orcid":"https://orcid.org/0000-0003-1644-3685","observed_orcids":["https://orcid.org/0000-0003-1644-3685"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ortmaier, Tobias","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":27,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9189000129699707,"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":0.9189000129699707,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.05400000140070915,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.008700000122189522,"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/uncertainty-calibration","display_name":"uncertainty calibration","score":0.8040000200271606},{"id":"https://openalex.org/keywords/monte-carlo-dropout","display_name":"Monte Carlo dropout","score":0.8119999766349792},{"id":"https://openalex.org/keywords/variational-bayesian-inference","display_name":"variational inference","score":0.9390000104904175},{"id":"https://openalex.org/keywords/out-of-distribution-detection","display_name":"out-of-distribution detection","score":0.8259999752044678},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.7089999914169312},{"id":"https://openalex.org/keywords/cifar-10","display_name":"CIFAR-10","score":0.6840000152587891},{"id":"https://openalex.org/keywords/cifar-100","display_name":"CIFAR-100","score":0.968999981880188},{"id":"https://openalex.org/keywords/svhn","display_name":"SVHN","score":0.9739999771118164}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7112981081008911},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.6721047163009644},{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.6684545278549194},{"id":"https://openalex.org/C19499675","wikidata":"https://www.wikidata.org/wiki/Q232207","display_name":"Monte Carlo method","level":2,"score":0.6328611373901367},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.5976906418800354},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.5766031742095947},{"id":"https://openalex.org/C160234255","wikidata":"https://www.wikidata.org/wiki/Q812535","display_name":"Bayesian inference","level":3,"score":0.5631921291351318},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5601339936256409},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.5252848863601685},{"id":"https://openalex.org/C32230216","wikidata":"https://www.wikidata.org/wiki/Q7882499","display_name":"Uncertainty quantification","level":2,"score":0.49430155754089355},{"id":"https://openalex.org/C107673813","wikidata":"https://www.wikidata.org/wiki/Q812534","display_name":"Bayesian probability","level":2,"score":0.46506813168525696},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3392530083656311},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3132324516773224},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.284213662147522},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2317354381084442},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.20956996083259583},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.07133734226226807},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2006.11584","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.11584","pdf_url":"https://arxiv.org/pdf/2006.11584","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.2006.11584","doi":"https://doi.org/10.48550/arxiv.2006.11584","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.11584","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:2006.11584","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.11584","pdf_url":"https://arxiv.org/pdf/2006.11584","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":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3036633009.pdf","grobid_xml":"https://content.openalex.org/works/W3036633009.grobid-xml"},"referenced_works_count":34,"referenced_works":["https://openalex.org/W35527955","https://openalex.org/W582134693","https://openalex.org/W1618905105","https://openalex.org/W1663973292","https://openalex.org/W1826234144","https://openalex.org/W1959608418","https://openalex.org/W2012942264","https://openalex.org/W2095705004","https://openalex.org/W2098824882","https://openalex.org/W2119112357","https://openalex.org/W2164411961","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2254249950","https://openalex.org/W2335728318","https://openalex.org/W2547875792","https://openalex.org/W2548228487","https://openalex.org/W2560321925","https://openalex.org/W2581377246","https://openalex.org/W2592505114","https://openalex.org/W2597787948","https://openalex.org/W2600383743","https://openalex.org/W2626967530","https://openalex.org/W2787825417","https://openalex.org/W2810469995","https://openalex.org/W2867167548","https://openalex.org/W2912168444","https://openalex.org/W2917792182","https://openalex.org/W2950300355","https://openalex.org/W2951266961","https://openalex.org/W2963446712","https://openalex.org/W2969338701","https://openalex.org/W3037590790","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W2976356773","https://openalex.org/W7164462493","https://openalex.org/W3201739046","https://openalex.org/W2605055943","https://openalex.org/W4382680941","https://openalex.org/W4414105366","https://openalex.org/W4293583914","https://openalex.org/W2953172087","https://openalex.org/W2894335577","https://openalex.org/W4414784918"],"abstract_inverted_index":{"The":[0,46],"model":[1,31],"uncertainty":[2,34,74],"obtained":[3],"by":[4,69],"variational":[5,27],"Bayesian":[6],"inference":[7,28],"with":[8],"Monte":[9],"Carlo":[10],"dropout":[11,26],"is":[12,38,50],"prone":[13],"to":[14,25,29,43],"miscalibration.":[15,45],"In":[16],"this":[17],"paper,":[18],"different":[19],"logit":[20,64],"scaling":[21,65],"methods":[22],"are":[23],"extended":[24],"recalibrate":[30],"uncertainty.":[32],"Expected":[33],"calibration":[35],"error":[36],"(UCE)":[37],"presented":[39],"as":[40],"a":[41],"metric":[42],"measure":[44],"effectiveness":[47],"of":[48,71,78,84],"recalibration":[49],"evaluated":[51],"on":[52],"CIFAR-10/100":[53],"and":[54,81],"SVHN":[55],"for":[56],"recent":[57],"CNN":[58],"architectures.":[59],"Experimental":[60],"results":[61],"show":[62],"that":[63],"considerably":[66],"reduce":[67],"miscalibration":[68],"means":[70],"UCE.":[72],"Well-calibrated":[73],"enables":[75],"reliable":[76],"rejection":[77],"uncertain":[79],"predictions":[80],"robust":[82],"detection":[83],"out-of-distribution":[85],"data.":[86]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":6},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":5},{"year":2021,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-06-25T00:00:00"}