{"id":"https://openalex.org/W4303088367","doi":"https://doi.org/10.21428/594757db.85f0799f","title":"Adaptive Confidence Calibration","display_name":"Adaptive Confidence Calibration","publication_year":2022,"publication_date":"2022-05-27","ids":{"openalex":"https://openalex.org/W4303088367","doi":"https://doi.org/10.21428/594757db.85f0799f"},"language":"en","primary_location":{"id":"doi:10.21428/594757db.85f0799f","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.85f0799f","pdf_url":"https://caiac.pubpub.org/pub/camnr5ix/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://caiac.pubpub.org/pub/camnr5ix/download/pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5065182288","display_name":"Jonathan Pearce","orcid":"https://orcid.org/0000-0003-1515-8815"},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":true,"raw_author_name":"Jonathan Pearce","raw_affiliation_strings":["McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5109496264","display_name":"David Meger","orcid":null},"institutions":[{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"David Meger","raw_affiliation_strings":["McGill University, Montreal, Canada"],"affiliations":[{"raw_affiliation_string":"McGill University, Montreal, Canada","institution_ids":["https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5065182288"],"corresponding_institution_ids":["https://openalex.org/I5023651"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.10377213,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9919999837875366,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9919999837875366,"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/T10876","display_name":"Fault Detection and Control Systems","score":0.9606000185012817,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9589999914169312,"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/computer-science","display_name":"Computer science","score":0.711953341960907},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.711750328540802},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5155908465385437},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5129146575927734},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5118757486343384},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44495052099227905},{"id":"https://openalex.org/keywords/measure","display_name":"Measure (data warehouse)","score":0.4423424303531647},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.28956061601638794},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.20370754599571228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.711953341960907},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.711750328540802},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5155908465385437},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5129146575927734},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5118757486343384},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44495052099227905},{"id":"https://openalex.org/C2780009758","wikidata":"https://www.wikidata.org/wiki/Q6804172","display_name":"Measure (data warehouse)","level":2,"score":0.4423424303531647},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.28956061601638794},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.20370754599571228},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.21428/594757db.85f0799f","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.85f0799f","pdf_url":"https://caiac.pubpub.org/pub/camnr5ix/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.21428/594757db.85f0799f","is_oa":true,"landing_page_url":"https://doi.org/10.21428/594757db.85f0799f","pdf_url":"https://caiac.pubpub.org/pub/camnr5ix/download/pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Canadian Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4303088367.pdf","grobid_xml":"https://content.openalex.org/works/W4303088367.grobid-xml"},"referenced_works_count":46,"referenced_works":["https://openalex.org/W1573197951","https://openalex.org/W1599263113","https://openalex.org/W1686810756","https://openalex.org/W2095705004","https://openalex.org/W2098824882","https://openalex.org/W2139137304","https://openalex.org/W2183341477","https://openalex.org/W2194775991","https://openalex.org/W2254249950","https://openalex.org/W2404901863","https://openalex.org/W2462906003","https://openalex.org/W2626967530","https://openalex.org/W2765407302","https://openalex.org/W2785917027","https://openalex.org/W2797862905","https://openalex.org/W2804697534","https://openalex.org/W2917792182","https://openalex.org/W2933254221","https://openalex.org/W2945125794","https://openalex.org/W2948194985","https://openalex.org/W2948210185","https://openalex.org/W2970121940","https://openalex.org/W2971118045","https://openalex.org/W2994481268","https://openalex.org/W3007260230","https://openalex.org/W3037142499","https://openalex.org/W3093141676","https://openalex.org/W3093783084","https://openalex.org/W3118608800","https://openalex.org/W3122110922","https://openalex.org/W3123454130","https://openalex.org/W3173196825","https://openalex.org/W4287828713","https://openalex.org/W4287865413","https://openalex.org/W4300088958","https://openalex.org/W4300568423","https://openalex.org/W4386564360","https://openalex.org/W6687483927","https://openalex.org/W6718836005","https://openalex.org/W6739651123","https://openalex.org/W6745136726","https://openalex.org/W6761586423","https://openalex.org/W6765646913","https://openalex.org/W6774433549","https://openalex.org/W6779738646","https://openalex.org/W6797388580"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4224009465","https://openalex.org/W2413300777","https://openalex.org/W4286629047","https://openalex.org/W4306321456","https://openalex.org/W4285260836","https://openalex.org/W3046775127","https://openalex.org/W3170094116","https://openalex.org/W4205958290"],"abstract_inverted_index":{"Confidence":[0],"calibration":[1,68,109,153,163,182,196,213,228,252],"is":[2,121,165],"a":[3,54,95,118,192,239],"quickly":[4],"growing":[5],"area":[6],"of":[7,137,161,230],"research":[8,253],"in":[9,103],"deep":[10],"learning,":[11],"including":[12],"computer":[13],"vision":[14],"applications.":[15,36],"New":[16],"model":[17,27,66,115,119,152,212,227,231],"architectures":[18],"and":[19,56,73,80,92,147,154,157,171,190,202,223,233],"loss":[20,179],"functions":[21],"are":[22,45,89,93,168],"being":[23],"introduced":[24],"to":[25,39,48,149,176,180,215],"improve":[26],"calibration,":[28,116],"an":[29,128],"important":[30],"topic":[31],"for":[32,64,108,194,249],"safety":[33],"critical":[34],"AI":[35],"In":[37],"order":[38],"evaluate":[40],"these":[41,76,105,138,217,242],"new":[42,59],"methods,":[43],"they":[44,167],"frequently":[46],"compared":[47,214],"simple":[49,81],"baselines,":[50],"which":[51],"serve":[52],"as":[53],"comparison":[55,240],"help":[57],"measure":[58],"methods\u00e2\u0080\u0099":[60],"effectiveness.":[61],"Popular":[62],"baselines":[63],"evaluating":[65],"confidence":[67,148,251],"include":[69],"label":[70],"smoothing,":[71],"mixup":[72],"dropout.":[74],"Despite":[75],"methods":[77,140,219,244],"frequent":[78],"use":[79],"implementations,":[82],"the":[83,101,134,177,200],"parameter":[84,135],"values":[85,107,222],"that":[86,120,131,166,208,245],"define":[87],"them":[88],"rarely":[90],"validated,":[91],"usually":[94],"default":[96,106,221],"value.":[97],"This":[98],"paper":[99],"demonstrates":[100],"danger":[102],"using":[104,216],"benchmarks":[110],"on":[111,144],"common":[112],"datasets;":[113],"poor":[114],"specifically,":[117],"purely":[122],"over-":[123,156],"or":[124],"underconfident.":[125],"We":[126],"present":[127],"adaptive":[129,185],"framework":[130,186],"can":[132,246],"adjust":[133],"value":[136],"baseline":[139,243],"during":[141],"training":[142,178],"based":[143],"validation":[145],"accuracy":[146],"maintain":[150],"good":[151,226],"balance":[155],"underconfidence.":[158],"A":[159],"disadvantage":[160],"binning-based":[162],"metrics":[164],"not":[169],"differentiable":[170],"therefore":[172],"cannot":[173],"be":[174,247],"added":[175],"penalize":[181],"error.":[183],"Our":[184],"solves":[187],"this":[188],"problem":[189],"provides":[191,238],"solution":[193],"optimizing":[195],"methods.":[197],"Experiments":[198],"with":[199,220],"CIFAR-10":[201],"CIFAR-100":[203],"image":[204],"classification":[205],"datasets":[206],"show":[207],"our":[209,236],"approach":[210],"improves":[211],"popular":[218],"we":[224],"achieve":[225],"regardless":[229],"architecture":[232],"dataset.":[234],"Further,":[235],"analysis":[237],"between":[241],"considered":[248],"future":[250]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}