{"id":"https://openalex.org/W7124978411","doi":"https://doi.org/10.1109/cbmi66578.2025.11339339","title":"Explanatory Interactive Machine Learning for Bias Mitigation in Visual Gender Classification","display_name":"Explanatory Interactive Machine Learning for Bias Mitigation in Visual Gender Classification","publication_year":2025,"publication_date":"2025-10-22","ids":{"openalex":"https://openalex.org/W7124978411","doi":"https://doi.org/10.1109/cbmi66578.2025.11339339"},"language":null,"primary_location":{"id":"doi:10.1109/cbmi66578.2025.11339339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2602.13286","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5123404263","display_name":"Nathanya Queby Satriani","orcid":null},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Nathanya Queby Satriani","raw_affiliation_strings":["Johannes Kepler University Linz Linz,Austria"],"affiliations":[{"raw_affiliation_string":"Johannes Kepler University Linz Linz,Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5123445714","display_name":"Djordje Slijep\u010devi\u0107","orcid":null},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Djordje Slijep\u010devi\u0107","raw_affiliation_strings":["Institute of Creative Media Technologies St. Pölten University of Applied Sciences,St. Pölten,Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Creative Media Technologies St. Pölten University of Applied Sciences,St. Pölten,Austria","institution_ids":["https://openalex.org/I4210087747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091259315","display_name":"Markus Schedl","orcid":"https://orcid.org/0000-0003-1706-3406"},"institutions":[{"id":"https://openalex.org/I121883995","display_name":"Johannes Kepler University of Linz","ror":"https://ror.org/052r2xn60","country_code":"AT","type":"education","lineage":["https://openalex.org/I121883995"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Markus Schedl","raw_affiliation_strings":["Institute of Computational Perception LIT AI Lab Johannes Kepler University Linz,Linz,Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Computational Perception LIT AI Lab Johannes Kepler University Linz,Linz,Austria","institution_ids":["https://openalex.org/I121883995"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060926433","display_name":"Matthias Zeppelzauer","orcid":"https://orcid.org/0000-0003-0413-4746"},"institutions":[{"id":"https://openalex.org/I4210087747","display_name":"Creative Technologies (United States)","ror":"https://ror.org/001qkb777","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087747"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthias Zeppelzauer","raw_affiliation_strings":["Institute of Creative Media Technologies St. Pölten University of Applied Sciences,St. Pölten,Austria"],"affiliations":[{"raw_affiliation_string":"Institute of Creative Media Technologies St. Pölten University of Applied Sciences,St. Pölten,Austria","institution_ids":["https://openalex.org/I4210087747"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5123404263"],"corresponding_institution_ids":["https://openalex.org/I121883995"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.83521432,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9265000224113464,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9265000224113464,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.01679999940097332,"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/T10883","display_name":"Ethics and Social Impacts of AI","score":0.010599999688565731,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6884999871253967},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.6330999732017517},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.5370000004768372},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.508899986743927},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4553000032901764},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.45509999990463257},{"id":"https://openalex.org/keywords/logistic-regression","display_name":"Logistic regression","score":0.3549000024795532}],"concepts":[{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.718500018119812},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6884999871253967},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6718999743461609},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6467999815940857},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.6330999732017517},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.5370000004768372},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.508899986743927},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4553000032901764},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.45509999990463257},{"id":"https://openalex.org/C151956035","wikidata":"https://www.wikidata.org/wiki/Q1132755","display_name":"Logistic regression","level":2,"score":0.3549000024795532},{"id":"https://openalex.org/C45804977","wikidata":"https://www.wikidata.org/wiki/Q7239673","display_name":"Predictive modelling","level":2,"score":0.3495999872684479},{"id":"https://openalex.org/C140331021","wikidata":"https://www.wikidata.org/wiki/Q1868104","display_name":"Logit","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C34388435","wikidata":"https://www.wikidata.org/wiki/Q2267362","display_name":"Bounded function","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C2983427547","wikidata":"https://www.wikidata.org/wiki/Q93200","display_name":"Gender bias","level":2,"score":0.2687000036239624},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.2531999945640564},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.2526000142097473},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cbmi66578.2025.11339339","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cbmi66578.2025.11339339","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2602.13286","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.13286","pdf_url":"https://arxiv.org/pdf/2602.13286","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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:doi:10.48550/arxiv.2602.13286","is_oa":true,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4406922384","display_name":"Open MIND","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":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2602.13286","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2602.13286","pdf_url":"https://arxiv.org/pdf/2602.13286","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.4739147126674652},{"id":"https://metadata.un.org/sdg/5","display_name":"Gender equality","score":0.44334477186203003}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W1501005121","https://openalex.org/W2031489346","https://openalex.org/W2794079986","https://openalex.org/W2891503716","https://openalex.org/W2962772482","https://openalex.org/W2995523160","https://openalex.org/W3181414820","https://openalex.org/W4294740730","https://openalex.org/W4309619902","https://openalex.org/W4313650676","https://openalex.org/W4321598326","https://openalex.org/W4391753543","https://openalex.org/W4402321740"],"related_works":[],"abstract_inverted_index":{"Explanatory":[0],"interactive":[1],"learning":[2,12,47],"(XIL)":[3],"enables":[4],"users":[5],"to":[6,24,31,49,62,133,168,184,196],"guide":[7],"model":[8,147],"training":[9],"in":[10,55,59,128,171],"machine":[11],"(ML)":[13],"by":[14,102,181],"providing":[15],"feedback":[16],"on":[17,26,135],"the":[18,32,35,43,82,123,151,163,175],"model's":[19],"explanations,":[20],"thereby":[21],"helping":[22],"it":[23],"focus":[25,134],"features":[27],"that":[28,93],"are":[29,99],"relevant":[30,136],"prediction":[33],"from":[34],"user's":[36],"perspective.":[37],"In":[38],"this":[39,46],"study,":[40],"we":[41],"explore":[42],"capability":[44],"of":[45,125,165],"paradigm":[48],"mitigate":[50],"bias":[51,148],"and":[52,79,115,144,156,178],"spurious":[53],"correlations":[54],"visual":[56],"classifiers,":[57],"specifically":[58],"scenarios":[60],"prone":[61],"data":[63],"bias,":[64],"such":[65],"as":[66,86,88],"gender":[67,172],"classification.":[68],"We":[69],"investigate":[70],"two":[71],"methodologically":[72],"different":[73],"state-of-the-art":[74],"XIL":[75,166,182],"strategies,":[76],"i.e.,":[77],"CAIPI":[78,141],"Right":[80,83],"for":[81],"Reasons":[84],"(RRR),":[85],"well":[87],"a":[89],"novel":[90],"hybrid":[91],"approach":[92],"combines":[94],"both":[95],"strategies.":[96],"The":[97],"results":[98,121],"evaluated":[100],"quan-titatively":[101],"comparing":[103],"segmentation":[104],"masks":[105],"with":[106,188],"explanations":[107],"generated":[108],"using":[109],"Gradient-weighted":[110],"Class":[111],"Activation":[112],"Mapping":[113],"(GradCAM)":[114],"Bounded":[116],"Logit":[117],"Attention":[118],"(BLA).":[119],"Experimental":[120],"demonstrate":[122],"effectiveness":[124],"these":[126],"methods":[127,167],"(i)":[129],"guiding":[130],"ML":[131],"models":[132],"image":[137],"features,":[138],"par-ticularly":[139],"when":[140],"is":[142],"used,":[143],"(ii)":[145],"reducing":[146],"(i.e.,":[149],"balancing":[150],"misclassification":[152],"rates":[153],"between":[154],"male":[155],"female":[157],"predictions).":[158],"Our":[159],"analysis":[160],"further":[161],"supports":[162],"potential":[164,195],"improve":[169,198],"fairness":[170,179],"classifiers.":[173],"Overall,":[174],"increased":[176],"transparency":[177],"obtained":[180],"leads":[183],"slight":[185],"performance":[186],"decreases":[187],"an":[189],"exception":[190],"being":[191],"CAIPI,":[192],"which":[193],"shows":[194],"even":[197],"classification":[199],"accuracy.":[200]},"counts_by_year":[],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2026-01-21T00:00:00"}