{"id":"https://openalex.org/W4226057767","doi":"https://doi.org/10.1109/fg52635.2021.9667053","title":"Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition","display_name":"Information-Theoretic Bias Assessment Of Learned Representations Of Pretrained Face Recognition","publication_year":2021,"publication_date":"2021-12-15","ids":{"openalex":"https://openalex.org/W4226057767","doi":"https://doi.org/10.1109/fg52635.2021.9667053"},"language":"en","primary_location":{"id":"doi:10.1109/fg52635.2021.9667053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg52635.2021.9667053","pdf_url":null,"source":{"id":"https://openalex.org/S4363608446","display_name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","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/A5103016895","display_name":"Jiazhi Li","orcid":"https://orcid.org/0000-0003-3938-7989"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Jiazhi Li","raw_affiliation_strings":["University of Southern California, Information Sciences Institute, Marina del Rey, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Information Sciences Institute, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028776484","display_name":"Wael AbdAlmageed","orcid":"https://orcid.org/0000-0002-8320-8530"},"institutions":[{"id":"https://openalex.org/I1174212","display_name":"University of Southern California","ror":"https://ror.org/03taz7m60","country_code":"US","type":"education","lineage":["https://openalex.org/I1174212"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wael Abd-Almageed","raw_affiliation_strings":["University of Southern California, Information Sciences Institute, Marina del Rey, CA, USA"],"affiliations":[{"raw_affiliation_string":"University of Southern California, Information Sciences Institute, Marina del Rey, CA, USA","institution_ids":["https://openalex.org/I1174212"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5103016895"],"corresponding_institution_ids":["https://openalex.org/I1174212"],"apc_list":null,"apc_paid":null,"fwci":0.196,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.61074309,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"7","issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.9995999932289124,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9569000005722046,"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/T10057","display_name":"Face and Expression Recognition","score":0.9545000195503235,"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/metric","display_name":"Metric (unit)","score":0.8669372200965881},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8148449063301086},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6987659931182861},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6494776606559753},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6484578251838684},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.6009060144424438},{"id":"https://openalex.org/keywords/facial-recognition-system","display_name":"Facial recognition system","score":0.599936842918396},{"id":"https://openalex.org/keywords/variation","display_name":"Variation (astronomy)","score":0.5988168120384216},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5272751450538635},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4245030879974365},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3915788531303406},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.06481555104255676}],"concepts":[{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.8669372200965881},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8148449063301086},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6987659931182861},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6494776606559753},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6484578251838684},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.6009060144424438},{"id":"https://openalex.org/C31510193","wikidata":"https://www.wikidata.org/wiki/Q1192553","display_name":"Facial recognition system","level":3,"score":0.599936842918396},{"id":"https://openalex.org/C2778334786","wikidata":"https://www.wikidata.org/wiki/Q1586270","display_name":"Variation (astronomy)","level":2,"score":0.5988168120384216},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5272751450538635},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4245030879974365},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3915788531303406},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.06481555104255676},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"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/C44870925","wikidata":"https://www.wikidata.org/wiki/Q37547","display_name":"Astrophysics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/fg52635.2021.9667053","is_oa":false,"landing_page_url":"https://doi.org/10.1109/fg52635.2021.9667053","pdf_url":null,"source":{"id":"https://openalex.org/S4363608446","display_name":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"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":"2021 16th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2021)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.6399999856948853,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":52,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W2031342017","https://openalex.org/W2034603029","https://openalex.org/W2100960835","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2114331649","https://openalex.org/W2145979309","https://openalex.org/W2194775991","https://openalex.org/W2530395818","https://openalex.org/W2592232824","https://openalex.org/W2738042021","https://openalex.org/W2788481061","https://openalex.org/W2797558164","https://openalex.org/W2803832867","https://openalex.org/W2871667416","https://openalex.org/W2890680318","https://openalex.org/W2895243423","https://openalex.org/W2912376035","https://openalex.org/W2936687512","https://openalex.org/W2941039078","https://openalex.org/W2957285709","https://openalex.org/W2962770929","https://openalex.org/W2962787423","https://openalex.org/W2963116854","https://openalex.org/W2963350032","https://openalex.org/W2963446520","https://openalex.org/W2964036823","https://openalex.org/W2969069666","https://openalex.org/W2982232682","https://openalex.org/W2982358316","https://openalex.org/W2990751682","https://openalex.org/W2994828068","https://openalex.org/W2998503299","https://openalex.org/W3034700241","https://openalex.org/W3035067471","https://openalex.org/W3035574324","https://openalex.org/W3097003645","https://openalex.org/W3113409159","https://openalex.org/W3120485916","https://openalex.org/W3120895209","https://openalex.org/W3175998650","https://openalex.org/W3185463067","https://openalex.org/W4243316134","https://openalex.org/W4289490880","https://openalex.org/W6728551298","https://openalex.org/W6738077463","https://openalex.org/W6748382702","https://openalex.org/W6752051073","https://openalex.org/W6754215057","https://openalex.org/W6754610156","https://openalex.org/W6761653978"],"related_works":["https://openalex.org/W2386430105","https://openalex.org/W2356521405","https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W1482441085","https://openalex.org/W2966858528","https://openalex.org/W2151687600","https://openalex.org/W4323323165","https://openalex.org/W4386066345","https://openalex.org/W2745033168"],"abstract_inverted_index":{"As":[0],"equality":[1],"issues":[2],"in":[3,137,149],"the":[4,83,132,161,168],"use":[5],"of":[6,13,56,65,91,134,163],"face":[7],"recognition":[8,68],"have":[9,18],"garnered":[10],"a":[11,96,127,143],"lot":[12],"attention":[14],"lately,":[15],"greater":[16],"efforts":[17],"been":[19],"made":[20],"to":[21,26,29,53,111],"debiased":[22,165],"deep":[23],"learning":[24],"models":[25,166],"improve":[27],"fairness":[28],"minorities.":[30],"However,":[31],"there":[32],"is":[33,108],"still":[34],"no":[35],"clear":[36,150],"definition":[37],"nor":[38],"sufficient":[39],"analysis":[40],"for":[41],"bias":[42,50,57,113],"assessment":[43,51],"metrics.":[44],"We":[45],"propose":[46],"an":[47],"information-theoretic,":[48],"independent":[49],"metric":[52,71,145],"identify":[54],"degree":[55],"against":[58],"protected":[59,92],"demographic":[60],"attributes":[61,93],"from":[62,73],"learned":[63],"representations":[64],"pretrained":[66],"facial":[67],"systems.":[69],"Our":[70],"differs":[72],"other":[74,157],"methods":[75],"that":[76,105,130],"rely":[77],"on":[78,117],"classification":[79],"accuracy":[80],"or":[81],"examine":[82],"differences":[84],"between":[85],"ground":[86],"truth":[87],"and":[88,103,152,159],"predicted":[89,94],"labels":[90],"using":[95],"shallow":[97],"network.":[98],"Also,":[99],"we":[100,125,141],"argue,":[101],"theoretically":[102],"experimentally,":[104],"logits-level":[106],"loss":[107],"not":[109],"adequate":[110],"explain":[112],"since":[114],"predictors":[115],"based":[116],"neural":[118],"networks":[119],"will":[120],"always":[121],"find":[122],"correlations.":[123],"Further,":[124],"present":[126],"synthetic":[128],"dataset":[129],"mitigates":[131],"issue":[133],"insufficient":[135],"samples":[136],"certain":[138],"cohorts.":[139],"Lastly,":[140],"establish":[142],"benchmark":[144],"by":[146],"presenting":[147],"advantages":[148],"discrimination":[151],"small":[153],"variation":[154],"comparing":[155],"with":[156,167],"metrics,":[158],"evaluate":[160],"performance":[162],"different":[164],"proposed":[169],"metric.":[170]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}