{"id":"https://openalex.org/W7138234828","doi":"https://doi.org/10.1609/aaai.v40i13.38051","title":"Explicit Modeling of Causal Factors and Confounders for Image Classification","display_name":"Explicit Modeling of Causal Factors and Confounders for Image Classification","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138234828","doi":"https://doi.org/10.1609/aaai.v40i13.38051"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i13.38051","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38051","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i13.38051","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129690921","display_name":"Wei Wu","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Wei Wu","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129713953","display_name":"Lei Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lei Meng","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129750184","display_name":"Zhuang Qi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhuang Qi","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129679675","display_name":"Zixuan Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100402814","display_name":"Yongjie Zhang","orcid":"https://orcid.org/0000-0002-2273-2339"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yachong Zhang","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019522111","display_name":"Xiaoshuo Yan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaoshuo Yan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5129685647","display_name":"Xiangxu Meng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5129690921"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.57419836,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"13","first_page":"10763","last_page":"10771"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3522999882698059,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.3522999882698059,"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":0.3109000027179718,"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":0.06469999998807907,"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/causal-inference","display_name":"Causal inference","score":0.6340000033378601},{"id":"https://openalex.org/keywords/spurious-relationship","display_name":"Spurious relationship","score":0.6146000027656555},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5530999898910522},{"id":"https://openalex.org/keywords/confounding","display_name":"Confounding","score":0.5475999712944031},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5131999850273132},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.48899999260902405},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.4765999913215637},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.4717999994754791}],"concepts":[{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.6340000033378601},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6147000193595886},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6146000027656555},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5530999898910522},{"id":"https://openalex.org/C77350462","wikidata":"https://www.wikidata.org/wiki/Q1125472","display_name":"Confounding","level":2,"score":0.5475999712944031},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.529699981212616},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5131999850273132},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.48899999260902405},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.4765999913215637},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.4717999994754791},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4569000005722046},{"id":"https://openalex.org/C64357122","wikidata":"https://www.wikidata.org/wiki/Q1149766","display_name":"Causality (physics)","level":2,"score":0.42730000615119934},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.375},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.35839998722076416},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.3515999913215637},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3149000108242035},{"id":"https://openalex.org/C2779458634","wikidata":"https://www.wikidata.org/wiki/Q24963715","display_name":"Debiasing","level":2,"score":0.3046000003814697},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.2985999882221222},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2962000072002411},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.2928999960422516},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.26969999074935913}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i13.38051","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38051","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i13.38051","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i13.38051","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.7734429836273193,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Causal":[0,81],"inference":[1],"has":[2],"emerged":[3],"as":[4],"a":[5,183],"promising":[6],"approach":[7,71],"for":[8,72,148],"identifying":[9],"decisive":[10],"semantic":[11,43,185],"factors":[12,58,75,124,127,140,204],"and":[13,76,104,117,125,157,166,202,214],"eliminating":[14],"spurious":[15],"correlations":[16],"in":[17,48,55,205,217],"visual":[18,102],"representation":[19,186],"learning.":[20],"However,":[21],"most":[22],"existing":[23],"methods":[24,213,216],"rely":[25],"on":[26,193],"latent,":[27],"data-driven":[28],"confounder":[29],"modeling,":[30],"normally":[31],"attributing":[32],"the":[33,99,133,153],"source":[34],"of":[35,88,115],"bias":[36],"to":[37,111,129,181],"background":[38],"information":[39],"while":[40],"neglecting":[41],"object-level":[42],"confusions":[44],"that":[45,187,197],"commonly":[46],"occur":[47],"complex":[49,206],"scenes.":[50],"This":[51,174],"limits":[52],"their":[53],"effectiveness":[54],"disentangling":[56],"causal":[57,74,116,123,139,179,201,211],"from":[59],"confounding":[60,118,126,203],"semantics.":[61,150],"To":[62],"address":[63],"this":[64],"challenge,":[65],"we":[66],"propose":[67],"an":[68],"explicit":[69],"modeling":[70],"both":[73],"confounders,":[77],"termed":[78],"Explicit":[79,154],"Modeling":[80,156],"Model":[82],"(EMCM).":[83],"The":[84,92],"proposed":[85],"framework":[86,175],"consists":[87],"three":[89],"key":[90],"components.":[91],"Features":[93,135],"Stability":[94],"Estimation":[95],"module":[96,137],"explicitly":[97],"models":[98],"relationship":[100],"between":[101],"semantics":[103],"class":[105],"labels":[106],"by":[107,171],"leveraging":[108],"clustering":[109],"patterns":[110],"perform":[112],"class-aware":[113],"separation":[114],"factors.":[119],"It":[120],"produces":[121],"class-specific":[122],"linked":[128],"ambiguous":[130],"categories.":[131],"Subsequently,":[132],"Discriminative":[134],"Enhancing":[136],"integrates":[138],"into":[141],"fused":[142],"patch":[143],"features":[144,170],"via":[145],"front-door":[146],"intervention":[147],"stable":[149],"In":[151],"parallel,":[152],"Confounder":[155],"Debiasing":[158],"Module":[159],"learns":[160],"confounders":[161],"under":[162],"clear":[163],"label":[164],"guidance":[165],"derives":[167],"debiased":[168],"context":[169],"TDE":[172],"modeling.":[173],"leverages":[176],"two":[177,194],"complementary":[178],"perspectives":[180],"construct":[182],"unified":[184],"facilitates":[188],"improved":[189],"generalization.":[190],"Extensive":[191],"experiments":[192],"datasets":[195],"demonstrate":[196],"EMCM":[198],"effectively":[199],"disentangles":[200],"scenarios,":[207],"consistently":[208],"outperforming":[209],"state-of-the-art":[210],"debiasing":[212],"text-guided":[215],"all":[218],"metrics.":[219]},"counts_by_year":[],"updated_date":"2026-03-18T06:31:55.123368","created_date":"2026-03-18T00:00:00"}