{"id":"https://openalex.org/W4385966003","doi":"https://doi.org/10.1145/3581783.3612317","title":"Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features","display_name":"Benign Shortcut for Debiasing: Fair Visual Recognition via Intervention with Shortcut Features","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4385966003","doi":"https://doi.org/10.1145/3581783.3612317"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3612317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.08482","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100388041","display_name":"Yi Zhang","orcid":"https://orcid.org/0000-0001-6586-1037"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yi Zhang","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6586-1037","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023834030","display_name":"Jitao Sang","orcid":"https://orcid.org/0000-0002-0699-3205"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jitao Sang","raw_affiliation_strings":["Beijing Jiaotong University & Peng Cheng Lab, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-0699-3205","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University & Peng Cheng Lab, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5018357502","display_name":"Junyang Wang","orcid":"https://orcid.org/0000-0002-3204-6607"},"institutions":[{"id":"https://openalex.org/I21193070","display_name":"Beijing Jiaotong University","ror":"https://ror.org/01yj56c84","country_code":"CN","type":"education","lineage":["https://openalex.org/I21193070"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junyang Wang","raw_affiliation_strings":["Beijing Jiaotong University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3204-6607","affiliations":[{"raw_affiliation_string":"Beijing Jiaotong University, Beijing, China","institution_ids":["https://openalex.org/I21193070"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102021514","display_name":"Dongmei Jiang","orcid":"https://orcid.org/0000-0002-6238-8499"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Jiang","raw_affiliation_strings":["Peng Cheng Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-8499","affiliations":[{"raw_affiliation_string":"Peng Cheng Lab, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073082132","display_name":"Yaowei Wang","orcid":"https://orcid.org/0000-0002-6110-4036"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaowei Wang","raw_affiliation_strings":["Peng Cheng Lab, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6110-4036","affiliations":[{"raw_affiliation_string":"Peng Cheng Lab, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5100388041"],"corresponding_institution_ids":["https://openalex.org/I21193070"],"apc_list":null,"apc_paid":null,"fwci":2.2696,"has_fulltext":true,"cited_by_count":9,"citation_normalized_percentile":{"value":0.90514801,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"8860","last_page":"8868"},"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":0.9961000084877014,"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":0.9961000084877014,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9700999855995178,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9596999883651733,"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/debiasing","display_name":"Debiasing","score":0.998879075050354},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7809851765632629},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6751547455787659},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6681676506996155},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5531967282295227},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.552074670791626},{"id":"https://openalex.org/keywords/leverage","display_name":"Leverage (statistics)","score":0.5206436514854431},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.44409385323524475},{"id":"https://openalex.org/keywords/multi-task-learning","display_name":"Multi-task learning","score":0.4177919626235962},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.16813331842422485},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.15168830752372742}],"concepts":[{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.998879075050354},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7809851765632629},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6751547455787659},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6681676506996155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5531967282295227},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.552074670791626},{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.5206436514854431},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.44409385323524475},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.4177919626235962},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.16813331842422485},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.15168830752372742},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","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},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3581783.3612317","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3612317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.08482","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.08482","pdf_url":"https://arxiv.org/pdf/2308.08482","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.08482","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.08482","pdf_url":"https://arxiv.org/pdf/2308.08482","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"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":"text"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/5","score":0.5699999928474426,"display_name":"Gender equality"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385966003.pdf"},"referenced_works_count":55,"referenced_works":["https://openalex.org/W167016754","https://openalex.org/W1514535095","https://openalex.org/W1686810756","https://openalex.org/W1834627138","https://openalex.org/W1956343362","https://openalex.org/W1967742189","https://openalex.org/W1977295328","https://openalex.org/W1979769549","https://openalex.org/W2014352947","https://openalex.org/W2148385623","https://openalex.org/W2194775991","https://openalex.org/W2530395818","https://openalex.org/W2592232824","https://openalex.org/W2751465153","https://openalex.org/W2909334458","https://openalex.org/W2912808728","https://openalex.org/W2937229771","https://openalex.org/W2945295328","https://openalex.org/W2950095160","https://openalex.org/W2952676795","https://openalex.org/W2962681511","https://openalex.org/W2963116854","https://openalex.org/W2963350032","https://openalex.org/W2982232682","https://openalex.org/W2989701728","https://openalex.org/W2990751682","https://openalex.org/W2999905431","https://openalex.org/W3007373432","https://openalex.org/W3016970897","https://openalex.org/W3034700241","https://openalex.org/W3035037113","https://openalex.org/W3035103424","https://openalex.org/W3035651653","https://openalex.org/W3087788237","https://openalex.org/W3088715381","https://openalex.org/W3098253476","https://openalex.org/W3103934428","https://openalex.org/W3104149808","https://openalex.org/W3104182862","https://openalex.org/W3123103757","https://openalex.org/W3170037207","https://openalex.org/W3175547470","https://openalex.org/W3177313640","https://openalex.org/W3177888841","https://openalex.org/W3204544513","https://openalex.org/W4224992224","https://openalex.org/W4256361765","https://openalex.org/W4283376200","https://openalex.org/W4283831096","https://openalex.org/W4287115658","https://openalex.org/W4287198317","https://openalex.org/W4312566264","https://openalex.org/W4312678124","https://openalex.org/W6604305821","https://openalex.org/W6798345263"],"related_works":["https://openalex.org/W4362554880","https://openalex.org/W4281684980","https://openalex.org/W4386875279","https://openalex.org/W2171721708","https://openalex.org/W4390963114","https://openalex.org/W3214527415","https://openalex.org/W4287887864","https://openalex.org/W1495104519","https://openalex.org/W4225584739","https://openalex.org/W4388144300"],"abstract_inverted_index":{"Machine":[0],"learning":[1,63,79,127,194],"models":[2,48],"often":[3],"learn":[4],"to":[5,77,101,121,134,142,155,160,169,211],"make":[6],"predictions":[7],"that":[8,72,85],"rely":[9],"on":[10,64,161,178],"sensitive":[11],"social":[12,45,60],"attributes":[13,46,61,130],"like":[14],"gender":[15],"and":[16,31,58,137,177,215,227],"race,":[17],"which":[18],"poses":[19],"significant":[20,217],"fairness":[21],"risks,":[22],"especially":[23],"in":[24,47,108,167,224],"societal":[25],"applications,":[26],"such":[27],"as":[28],"hiring,":[29],"banking,":[30],"criminal":[32],"justice.":[33],"Existing":[34],"work":[35],"tackles":[36],"this":[37,115],"issue":[38],"by":[39,185],"minimizing":[40],"the":[41,52,65,78,92,103,124,170,174,179,188,193,196,202,220],"employed":[42],"information":[43],"about":[44],"for":[49,112],"debiasing.":[50,70],"However,":[51],"high":[53],"correlation":[54],"between":[55],"target":[56,66,87,109,125,171,197],"task":[57,67,88,110,172,198],"these":[59],"makes":[62],"incompatible":[68],"with":[69],"Given":[71],"model":[73],"bias":[74,81,106,129,132,165,205],"arises":[75],"due":[76],"of":[80,105,128,151,195,204],"features":[82,100,133,145,159,166],"(i.e.,":[83],"gender)":[84],"help":[86],"optimization,":[89],"we":[90,97,117],"explore":[91],"following":[93],"research":[94],"question:":[95],"Can":[96],"leverage":[98],"shortcut":[99,135,144,158],"replace":[102,164],"role":[104],"feature":[107],"optimization":[111],"debiasing?":[113],"To":[114],"end,":[116],"propose":[118],"Shortcut":[119,152,209],"Debiasing,":[120],"first":[122],"transfer":[123],"task's":[126],"from":[131],"features,":[136],"then":[138],"employ":[139],"causal":[140],"intervention":[141,186],"eliminate":[143],"during":[146,173,187],"inference.":[147],"The":[148],"key":[149],"idea":[150],"Debiasing":[153,210],"is":[154],"design":[156],"controllable":[157],"one":[162],"hand":[163,181],"contributing":[168],"training":[175],"stage,":[176],"other":[180],"be":[182],"easily":[183],"removed":[184],"inference":[189],"stage.":[190],"This":[191],"guarantees":[192],"does":[199],"not":[200],"hinder":[201],"elimination":[203],"features.":[206],"We":[207],"apply":[208],"several":[212],"benchmark":[213],"datasets,":[214],"achieve":[216],"improvements":[218],"over":[219],"state-of-the-art":[221],"debiasing":[222],"methods":[223],"both":[225],"accuracy":[226],"fairness.":[228]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2023-08-18T00:00:00"}