{"id":"https://openalex.org/W3038544204","doi":"https://doi.org/10.48550/arxiv.2007.03293","title":"Single Shot MC Dropout Approximation","display_name":"Single Shot MC Dropout Approximation","publication_year":2020,"publication_date":"2020-07-07","ids":{"openalex":"https://openalex.org/W3038544204","doi":"https://doi.org/10.48550/arxiv.2007.03293","mag":"3038544204"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2007.03293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.03293","pdf_url":"https://arxiv.org/pdf/2007.03293","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/2007.03293","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5040544036","display_name":"Kai Brach","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I202697423","display_name":"University of Zurich","ror":"https://ror.org/02crff812","country_code":"CH","type":"education","lineage":["https://openalex.org/I202697423"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Brach, Kai","raw_affiliation_strings":[", and EBPI , University of Zurich , Switzerland","Elektrobit Automotive GmbH , Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":", and EBPI , University of Zurich , Switzerland","institution_ids":["https://openalex.org/I202697423"]},{"raw_affiliation_string":"Elektrobit Automotive GmbH , Germany","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053625034","display_name":"Beate Sick","orcid":"https://orcid.org/0000-0002-7264-1515","observed_orcids":["https://orcid.org/0000-0002-7264-1515"]},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Sick, Beate","raw_affiliation_strings":["IDP , Zurich University of Applied Sciences , Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IDP , Zurich University of Applied Sciences , Switzerland","institution_ids":["https://openalex.org/I858936495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078032390","display_name":"Oliver D\u00fcrr","orcid":"https://orcid.org/0000-0003-2271-8630","observed_orcids":["https://orcid.org/0000-0003-2271-8630"]},"institutions":[{"id":"https://openalex.org/I858936495","display_name":"ZHAW Zurich University of Applied Sciences","ror":"https://ror.org/05pmsvm27","country_code":"CH","type":"education","lineage":["https://openalex.org/I858936495"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"D\u00fcrr, Oliver","raw_affiliation_strings":["Z\u00fcrich University of Applied Sciences ZHAW"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Z\u00fcrich University of Applied Sciences ZHAW","institution_ids":["https://openalex.org/I858936495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":25,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.6929000020027161,"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/T12814","display_name":"Gaussian Processes and Bayesian Inference","score":0.6929000020027161,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.2551000118255615,"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":0.01590000092983246,"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/monte-carlo-dropout","display_name":"Monte Carlo dropout","score":0.8420000076293945},{"id":"https://openalex.org/keywords/bayesian-neural-networks","display_name":"Bayesian neural networks","score":0.8090000152587891},{"id":"https://openalex.org/keywords/uncertainty-estimation","display_name":"uncertainty estimation","score":0.7850000262260437},{"id":"https://openalex.org/keywords/approximate-analytical-solutions","display_name":"approximate analytical solutions","score":0.38499999046325684},{"id":"https://openalex.org/keywords/variance-estimation","display_name":"variance estimation","score":0.4580000042915344},{"id":"https://openalex.org/keywords/fully-connected-networks","display_name":"fully connected networks","score":0.6039999723434448},{"id":"https://openalex.org/keywords/real-time-deployment","display_name":"real-time deployment","score":0.6309999823570251}],"concepts":[{"id":"https://openalex.org/C2776145597","wikidata":"https://www.wikidata.org/wiki/Q25339462","display_name":"Dropout (neural networks)","level":2,"score":0.7689067125320435},{"id":"https://openalex.org/C2778344882","wikidata":"https://www.wikidata.org/wiki/Q278938","display_name":"Shot (pellet)","level":2,"score":0.6999022364616394},{"id":"https://openalex.org/C3019835501","wikidata":"https://www.wikidata.org/wiki/Q1310130","display_name":"Single shot","level":2,"score":0.5345059633255005},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.385753333568573},{"id":"https://openalex.org/C149782125","wikidata":"https://www.wikidata.org/wiki/Q160039","display_name":"Econometrics","level":1,"score":0.36168789863586426},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3022211194038391},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.24839907884597778},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.19782057404518127},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.19210055470466614},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.18632006645202637},{"id":"https://openalex.org/C191897082","wikidata":"https://www.wikidata.org/wiki/Q11467","display_name":"Metallurgy","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"pmh:oai:arXiv.org:2007.03293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.03293","pdf_url":"https://arxiv.org/pdf/2007.03293","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":"pmh:oai:elib.uni-konstanz.de-htwg:2657","doi":null,"is_oa":true,"landing_page_url":"https://opus.htwg-konstanz.de/frontdoor/index/index/docId/2657","pdf_url":"https://opus.htwg-konstanz.de/frontdoor/index/index/docId/2657","source":{"id":"https://openalex.org/S4306400170","display_name":"URN-Resolver at the German National Library (German National Library)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I2802635041","host_organization_name":"Technische Informationsbibliothek (TIB)","host_organization_lineage":["https://openalex.org/I2802635041"],"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":"conferenceobject"},{"id":"doi:10.48550/arxiv.2007.03293","doi":"https://doi.org/10.48550/arxiv.2007.03293","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2007.03293","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:2007.03293","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.03293","pdf_url":"https://arxiv.org/pdf/2007.03293","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":[{"id":"https://openalex.org/G404480018","display_name":null,"funder_award_id":"01IS19083A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3038544204.pdf","grobid_xml":"https://content.openalex.org/works/W3038544204.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W582134693","https://openalex.org/W1979073566","https://openalex.org/W2010629420","https://openalex.org/W2095705004","https://openalex.org/W2111051539","https://openalex.org/W2111959010","https://openalex.org/W2180290696","https://openalex.org/W2342840547","https://openalex.org/W2560321925","https://openalex.org/W2600383743","https://openalex.org/W2740379828","https://openalex.org/W2767194911","https://openalex.org/W2797862905","https://openalex.org/W2798811024","https://openalex.org/W2888977849","https://openalex.org/W2921523090","https://openalex.org/W2963167203","https://openalex.org/W2963613699","https://openalex.org/W2965563166","https://openalex.org/W2972716140","https://openalex.org/W2981207549","https://openalex.org/W3037939899","https://openalex.org/W4241644338"],"related_works":["https://openalex.org/W4386185411","https://openalex.org/W582134693","https://openalex.org/W2953374819","https://openalex.org/W3200973167","https://openalex.org/W7162315644","https://openalex.org/W7116069671","https://openalex.org/W4415623275","https://openalex.org/W2907176385","https://openalex.org/W7010490688","https://openalex.org/W2589209256"],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"(DNNs)":[3],"are":[4,24,55],"known":[5],"for":[6,94,158],"their":[7,37],"high":[8],"prediction":[9],"performance,":[10],"especially":[11],"in":[12,97],"perceptual":[13],"tasks":[14],"such":[15,44],"as":[16,45],"object":[17],"recognition":[18],"or":[19],"autonomous":[20],"driving.":[21],"Still,":[22],"DNNs":[23,42],"prone":[25],"to":[26,91],"yield":[27],"unreliable":[28],"predictions":[29],"when":[30],"encountering":[31],"completely":[32],"new":[33],"situations":[34],"without":[35,82],"indicating":[36],"uncertainty.":[38],"Bayesian":[39],"variants":[40],"of":[41,80,108,143,161],"(BDNNs),":[43],"MC":[46,73,110,132,152],"dropout":[47,74,111,133],"BDNNs,":[48],"do":[49],"provide":[50],"uncertainty":[51,141],"measures.":[52],"However,":[53],"BDNNs":[54,81],"slow":[56],"during":[57],"test":[58],"time":[59],"because":[60],"they":[61],"rely":[62],"on":[63,117],"a":[64,70,86,98,122],"sampling":[65],"approach.":[66],"Here":[67],"we":[68],"present":[69],"single":[71,130],"shot":[72,131],"approximation":[75,134],"that":[76,128,147],"preserves":[77],"the":[78,102,106,109,136,140,144],"advantages":[79],"being":[83,155],"slower":[84],"than":[85],"DNN.":[87],"Our":[88],"approach":[89,116],"is":[90,148],"analytically":[92],"approximate":[93],"each":[95],"layer":[96],"fully":[99],"connected":[100],"network":[101],"expected":[103],"value":[104],"and":[105,121,139],"variance":[107],"signal.":[112],"We":[113,126],"evaluate":[114],"our":[115,129],"different":[118],"benchmark":[119],"datasets":[120],"simulated":[123],"toy":[124],"example.":[125],"demonstrate":[127],"resembles":[135],"point":[137],"estimate":[138,142],"predictive":[145],"distribution":[146],"achieved":[149],"with":[150],"an":[151],"approach,":[153],"while":[154],"fast":[156],"enough":[157],"real-time":[159],"deployments":[160],"BDNNs.":[162]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":10},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":5}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-07-10T00:00:00"}