{"id":"https://openalex.org/W3201233295","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534287","title":"Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space","display_name":"Exploring Biases and Prejudice of Facial Synthesis via Semantic Latent Space","publication_year":2021,"publication_date":"2021-07-18","ids":{"openalex":"https://openalex.org/W3201233295","doi":"https://doi.org/10.1109/ijcnn52387.2021.9534287","mag":"3201233295"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn52387.2021.9534287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","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/A5063135412","display_name":"Xuyang Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Xuyang Shen","raw_affiliation_strings":["Research School of Computer Science, The Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063366658","display_name":"Jo Plested","orcid":null},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jo Plested","raw_affiliation_strings":["Research School of Computer Science, The Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032320901","display_name":"Sabrina Caldwell","orcid":"https://orcid.org/0000-0003-0605-3149"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Sabrina Caldwell","raw_affiliation_strings":["Research School of Computer Science, The Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030379402","display_name":"Tom Gedeon","orcid":"https://orcid.org/0000-0001-8356-4909"},"institutions":[{"id":"https://openalex.org/I118347636","display_name":"Australian National University","ror":"https://ror.org/019wvm592","country_code":"AU","type":"education","lineage":["https://openalex.org/I118347636"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Tom Gedeon","raw_affiliation_strings":["Research School of Computer Science, The Australian National University, Canberra, Australia"],"affiliations":[{"raw_affiliation_string":"Research School of Computer Science, The Australian National University, Canberra, Australia","institution_ids":["https://openalex.org/I118347636"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5063135412"],"corresponding_institution_ids":["https://openalex.org/I118347636"],"apc_list":null,"apc_paid":null,"fwci":0.1921,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.49357843,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"2","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":0.9998000264167786,"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":0.9998000264167786,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9994999766349792,"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/T12650","display_name":"Aesthetic Perception and Analysis","score":0.9675999879837036,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6880225539207458},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5711829662322998},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5546897649765015},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5164499282836914},{"id":"https://openalex.org/keywords/prejudice","display_name":"Prejudice (legal term)","score":0.515412449836731},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5105496644973755},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5063503980636597},{"id":"https://openalex.org/keywords/generator","display_name":"Generator (circuit theory)","score":0.4755532443523407},{"id":"https://openalex.org/keywords/cognitive-psychology","display_name":"Cognitive psychology","score":0.32901710271835327},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.2257961630821228},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.14048448204994202}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6880225539207458},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5711829662322998},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5546897649765015},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5164499282836914},{"id":"https://openalex.org/C107062074","wikidata":"https://www.wikidata.org/wiki/Q109701697","display_name":"Prejudice (legal term)","level":2,"score":0.515412449836731},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5105496644973755},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5063503980636597},{"id":"https://openalex.org/C2780992000","wikidata":"https://www.wikidata.org/wiki/Q17016113","display_name":"Generator (circuit theory)","level":3,"score":0.4755532443523407},{"id":"https://openalex.org/C180747234","wikidata":"https://www.wikidata.org/wiki/Q23373","display_name":"Cognitive psychology","level":1,"score":0.32901710271835327},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2257961630821228},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.14048448204994202},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"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/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn52387.2021.9534287","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn52387.2021.9534287","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.44999998807907104,"display_name":"Gender equality","id":"https://metadata.un.org/sdg/5"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":42,"referenced_works":["https://openalex.org/W1916406603","https://openalex.org/W2137857332","https://openalex.org/W2142780847","https://openalex.org/W2567627528","https://openalex.org/W2770618123","https://openalex.org/W2788481061","https://openalex.org/W2795325993","https://openalex.org/W2891525068","https://openalex.org/W2912457762","https://openalex.org/W2928736629","https://openalex.org/W2960894964","https://openalex.org/W2962793481","https://openalex.org/W2963073614","https://openalex.org/W2963100452","https://openalex.org/W2963991565","https://openalex.org/W2964074081","https://openalex.org/W2964337551","https://openalex.org/W3014590323","https://openalex.org/W3023702633","https://openalex.org/W3047527121","https://openalex.org/W3089745382","https://openalex.org/W3095060934","https://openalex.org/W3095866053","https://openalex.org/W3109295923","https://openalex.org/W3109803668","https://openalex.org/W3127511859","https://openalex.org/W4285790115","https://openalex.org/W4288376480","https://openalex.org/W4302343661","https://openalex.org/W6729966448","https://openalex.org/W6731703475","https://openalex.org/W6746336887","https://openalex.org/W6748382702","https://openalex.org/W6749726075","https://openalex.org/W6756006421","https://openalex.org/W6758760113","https://openalex.org/W6761182108","https://openalex.org/W6767327189","https://openalex.org/W6773594038","https://openalex.org/W6781333953","https://openalex.org/W6781543076","https://openalex.org/W6781885499"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3005996785","https://openalex.org/W3014948380","https://openalex.org/W4386984417","https://openalex.org/W4210468674","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W4238433571"],"abstract_inverted_index":{"Deep":[0],"learning":[1],"(DL)":[2],"models":[3,155,170,173],"are":[4,141,156],"widely":[5],"used":[6],"to":[7,113,126,158,182,185,212],"provide":[8],"a":[9,87,213],"more":[10],"convenient":[11],"and":[12,33,55,78,136,195,205],"smarter":[13],"life.":[14],"However,":[15],"biased":[16,27,45,64,67,115,159],"algorithms":[17,28],"will":[18,29],"negatively":[19],"influence":[20],"us.":[21],"For":[22],"instance,":[23],"groups":[24],"targeted":[25],"by":[26],"feel":[30],"unfairly":[31],"treated":[32],"even":[34],"fearful":[35],"of":[36,39,52,69,76,103,131,144,164],"negative":[37],"consequences":[38],"these":[40,145],"biases.":[41],"This":[42],"work":[43],"targets":[44],"generative":[46],"models'":[47],"behaviors,":[48],"identifying":[49],"the":[50,53,74,82,93,99,108,162,165,200,209,222],"cause":[51],"biases":[54],"eliminating":[56],"them.":[57],"We":[58,176,207],"can":[59,85,171,202],"(as":[60],"expected)":[61],"conclude":[62,177],"that":[63,98,178,199,219],"data":[65,84],"causes":[66],"predictions":[68],"face":[70,153,168],"frontalization":[71,154,169],"models.":[72,146],"Varying":[73],"proportions":[75,105],"male":[77],"female":[79,118],"faces":[80,140],"in":[81,134,152,167],"training":[83,188],"have":[86],"substantial":[88],"effect":[89],"on":[90,92,117],"behavior":[91,116],"test":[94],"data:":[95],"we":[96],"found":[97],"seemingly":[100],"obvious":[101],"choice":[102],"50:50":[104],"was":[106,121],"not":[107],"best":[109,211],"for":[110],"this":[111],"dataset":[112],"reduce":[114],"faces,":[119],"which":[120],"71%":[122],"unbiased":[123,129,215],"as":[124],"compared":[125],"our":[127,196],"top":[128],"rate":[130],"84%.":[132],"Failure":[133],"generation":[135],"generating":[137],"incorrect":[138],"gender":[139],"two":[142],"behaviors":[143],"In":[147],"addition,":[148],"only":[149],"some":[150],"layers":[151],"vulnerable":[157],"datasets.":[160],"Optimizing":[161],"skip-connections":[163],"generator":[166],"make":[172],"less":[174],"biased.":[175],"it":[179],"is":[180,217],"likely":[181],"be":[183,203],"impossible":[184],"eliminate":[186],"all":[187],"bias":[189,201],"without":[190],"an":[191],"unlimited":[192],"size":[193],"dataset,":[194],"experiments":[197],"show":[198],"reduced":[204],"quantified.":[206],"believe":[208],"next":[210],"perfect":[214],"predictor":[216],"one":[218],"has":[220],"minimized":[221],"remaining":[223],"known":[224],"bias.":[225]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}