{"id":"https://openalex.org/W3141609294","doi":"https://doi.org/10.1109/wacv51458.2022.00257","title":"An Investigation of Critical Issues in Bias Mitigation Techniques","display_name":"An Investigation of Critical Issues in Bias Mitigation Techniques","publication_year":2022,"publication_date":"2022-01-01","ids":{"openalex":"https://openalex.org/W3141609294","doi":"https://doi.org/10.1109/wacv51458.2022.00257","mag":"3141609294"},"language":"en","primary_location":{"id":"doi:10.1109/wacv51458.2022.00257","doi":"https://doi.org/10.1109/wacv51458.2022.00257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv51458.2022.00257","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","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/A5031427851","display_name":"Robik Shrestha","orcid":"https://orcid.org/0000-0002-0945-3458","observed_orcids":["https://orcid.org/0000-0002-0945-3458"]},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Robik Shrestha","raw_affiliation_strings":["Rochester Institute of Technology"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047193437","display_name":"Kushal Kafle","orcid":"https://orcid.org/0000-0002-0847-7861","observed_orcids":["https://orcid.org/0000-0002-0847-7861"]},"institutions":[{"id":"https://openalex.org/I1306409833","display_name":"Adobe Systems (United States)","ror":"https://ror.org/059tvcg64","country_code":"US","type":"company","lineage":["https://openalex.org/I1306409833"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kushal Kafle","raw_affiliation_strings":["Adobe Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Adobe Research","institution_ids":["https://openalex.org/I1306409833"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046979072","display_name":"Christopher Kanan","orcid":"https://orcid.org/0000-0002-6412-995X","observed_orcids":["https://orcid.org/0000-0002-6412-995X"]},"institutions":[{"id":"https://openalex.org/I155173764","display_name":"Rochester Institute of Technology","ror":"https://ror.org/00v4yb702","country_code":"US","type":"education","lineage":["https://openalex.org/I155173764"]},{"id":"https://openalex.org/I4405261073","display_name":"Cornell Tech","ror":"https://ror.org/04qscbg47","country_code":"US","type":"education","lineage":["https://openalex.org/I205783295","https://openalex.org/I4405261073"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Kanan","raw_affiliation_strings":["Rochester Institute of Technology","Cornell Tech","Paige"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Rochester Institute of Technology","institution_ids":["https://openalex.org/I155173764"]},{"raw_affiliation_string":"Cornell Tech","institution_ids":["https://openalex.org/I4405261073"]},{"raw_affiliation_string":"Paige","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":5.2172,"has_fulltext":false,"cited_by_count":22,"citation_normalized_percentile":{"value":0.94858203,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":88,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2512","last_page":"2523"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9560999870300293,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","score":0.9560999870300293,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.00570000009611249,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.00419999985024333,"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/bias-mitigation","display_name":"bias mitigation","score":0.9039999842643738},{"id":"https://openalex.org/keywords/algorithmic-fairness","display_name":"algorithmic fairness","score":0.8870000243186951},{"id":"https://openalex.org/keywords/deep-learning","display_name":"deep learning","score":0.4690000116825104},{"id":"https://openalex.org/keywords/evaluation-protocol","display_name":"evaluation protocol","score":0.6449999809265137},{"id":"https://openalex.org/keywords/hidden-biases","display_name":"hidden biases","score":0.6990000009536743},{"id":"https://openalex.org/keywords/visual-question-answering","display_name":"visual question answering","score":0.8330000042915344},{"id":"https://openalex.org/keywords/benchmark-dataset","display_name":"benchmark dataset","score":0.6129999756813049},{"id":"https://openalex.org/keywords/minority-groups","display_name":"minority groups","score":0.38100001215934753}],"concepts":[{"id":"https://openalex.org/C190502265","wikidata":"https://www.wikidata.org/wiki/Q17069496","display_name":"MNIST database","level":3,"score":0.8599249124526978},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.8242922425270081},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7717684507369995},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7119954228401184},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.6711359620094299},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6480329632759094},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6058380007743835},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703887939453125},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4600162208080292},{"id":"https://openalex.org/C40423286","wikidata":"https://www.wikidata.org/wiki/Q284172","display_name":"Selection bias","level":2,"score":0.45140326023101807},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.4264489412307739},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.4145597219467163},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.2805691957473755},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.11565688252449036},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C142724271","wikidata":"https://www.wikidata.org/wiki/Q7208","display_name":"Pathology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv51458.2022.00257","doi":"https://doi.org/10.1109/wacv51458.2022.00257","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv51458.2022.00257","pdf_url":null,"source":{"id":"https://openalex.org/S4393918690","display_name":"IEEE Winter Conference on Applications of Computer Vision","issn_l":"2472-6737","issn":["2472-6737"],"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":["norway-1"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.7390999794006348,"display_name":"Reduced inequalities"}],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1484551447","https://openalex.org/W1968355947","https://openalex.org/W1979902804","https://openalex.org/W2104933073","https://openalex.org/W2116064496","https://openalex.org/W2118978333","https://openalex.org/W2148143831","https://openalex.org/W2194775991","https://openalex.org/W2483215953","https://openalex.org/W2531499355","https://openalex.org/W2543774860","https://openalex.org/W2564590721","https://openalex.org/W2745461083","https://openalex.org/W2771951981","https://openalex.org/W2784397426","https://openalex.org/W2788557041","https://openalex.org/W2790376986","https://openalex.org/W2803187616","https://openalex.org/W2848033333","https://openalex.org/W2887788426","https://openalex.org/W2890647280","https://openalex.org/W2890952061","https://openalex.org/W2891021031","https://openalex.org/W2895243423","https://openalex.org/W2895281799","https://openalex.org/W2903371384","https://openalex.org/W2908791737","https://openalex.org/W2910707576","https://openalex.org/W2934463783","https://openalex.org/W2950018712","https://openalex.org/W2950104027","https://openalex.org/W2952111037","https://openalex.org/W2953494151","https://openalex.org/W2955124656","https://openalex.org/W2958447893","https://openalex.org/W2962685807","https://openalex.org/W2962787423","https://openalex.org/W2963350032","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2963742154","https://openalex.org/W2963759070","https://openalex.org/W2970019270","https://openalex.org/W2979327556","https://openalex.org/W2982358316","https://openalex.org/W2982461533","https://openalex.org/W2984256198","https://openalex.org/W2990397898","https://openalex.org/W2991497298","https://openalex.org/W2991579958","https://openalex.org/W2996388127","https://openalex.org/W3006389498","https://openalex.org/W3007592798","https://openalex.org/W3007641164","https://openalex.org/W3011101596","https://openalex.org/W3016066790","https://openalex.org/W3021336872","https://openalex.org/W3034564653","https://openalex.org/W3034943799","https://openalex.org/W3035037113","https://openalex.org/W3035398303","https://openalex.org/W3035561630","https://openalex.org/W3038239361","https://openalex.org/W3044009838","https://openalex.org/W3088349782","https://openalex.org/W3092928935","https://openalex.org/W3099180329","https://openalex.org/W3099536922","https://openalex.org/W3100924069","https://openalex.org/W3105260243","https://openalex.org/W3110511794","https://openalex.org/W3119689247","https://openalex.org/W3123374861","https://openalex.org/W4289542857","https://openalex.org/W4300408123","https://openalex.org/W4394639892"],"related_works":["https://openalex.org/W4287250505","https://openalex.org/W6962664954","https://openalex.org/W7204640149","https://openalex.org/W2957285709","https://openalex.org/W4312319992","https://openalex.org/W4220719590","https://openalex.org/W3176139276","https://openalex.org/W4390873414","https://openalex.org/W3035765133","https://openalex.org/W6944365522"],"abstract_inverted_index":{"A":[0],"critical":[1,104,180],"problem":[2],"in":[3,13],"deep":[4],"learning":[5],"is":[6,38,47,179],"that":[7,31,59,136,196],"systems":[8,54,68],"learn":[9],"inappropriate":[10],"biases,":[11,200],"resulting":[12],"their":[14],"inability":[15],"to":[16,25,33,61,71,78,100,141,156,159,166,203,205,214,228],"perform":[17],"well":[18],"on":[19,57,221],"minority":[20],"groups.":[21],"This":[22,46],"has":[23],"led":[24],"the":[26,79,116,167,185,215,226],"creation":[27],"of":[28,65,139,208,217,233],"multiple":[29,142,206],"algorithms":[30,114,197],"endeavor":[32],"mitigate":[34],"bias.":[35],"However,":[36],"it":[37],"not":[39,189],"clear":[40],"how":[41],"effective":[42],"these":[43],"methods":[44],"are.":[45],"because":[48,181],"study":[49,172],"protocols":[50],"differ":[51],"among":[52],"papers,":[53],"are":[55,75,201,211,243],"tested":[56],"datasets":[58],"fail":[60],"test":[62,80,168,186],"many":[63,183],"forms":[64,207],"bias,":[66,209],"and":[67,93,102,120,149,210,241],"have":[69],"access":[70],"hidden":[72,160,199],"knowledge":[73],"or":[74],"tuned":[76],"specifically":[77],"set.":[81,219],"To":[82],"address":[83],"this,":[84],"we":[85,171,224],"introduce":[86,129],"an":[87],"improved":[88],"evaluation":[89],"protocol,":[90],"sensible":[91],"metrics,":[92],"a":[94,130,150],"new":[95,131],"dataset,":[96],"which":[97,178],"enables":[98,137],"us":[99],"ask":[101],"answer":[103],"questions":[105],"about":[106],"bias":[107,143,235],"mitigation":[108,236],"algorithms.":[109],"We":[110,128,145,194],"evaluate":[111],"seven":[112],"state-of-the-art":[113],"using":[115],"same":[117],"network":[118],"architecture":[119],"hyperparameter":[121],"selection":[122],"policy":[123],"across":[124,174],"three":[125],"benchmark":[126,155],"datasets.":[127],"dataset":[132],"called":[133],"Biased":[134,147],"MNIST":[135,148],"assessment":[138,232],"robustness":[140,158,173],"sources.":[144],"use":[146],"visual":[151],"question":[152],"answering":[153],"(VQA)":[154],"assess":[157],"biases.":[161],"Rather":[162],"than":[163],"only":[164],"tuning":[165,176,218],"set":[169],"distribution,":[170],"different":[175],"distributions,":[177],"for":[182],"applications":[184],"distribution":[187],"may":[188],"be":[190],"known":[191],"during":[192],"development.":[193],"find":[195],"exploit":[198],"unable":[202],"scale":[204],"highly":[212],"sensitive":[213],"choice":[216],"Based":[220],"our":[222],"findings,":[223],"implore":[225],"community":[227],"adopt":[229],"more":[230],"rigorous":[231],"future":[234],"methods.":[237],"All":[238],"data,":[239],"code,":[240],"results":[242],"publicly":[244],"available1.":[245]},"counts_by_year":[{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":6},{"year":2023,"cited_by_count":6},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":1}],"updated_date":"2026-10-27T15:51:10.671819","created_date":"2021-04-13T00:00:00"}