{"id":"https://openalex.org/W4414359385","doi":"https://doi.org/10.24963/ijcai.2025/755","title":"Empowering Vision Transformers with Multi-Scale Causal Intervention for Long-Tailed Image Classification","display_name":"Empowering Vision Transformers with Multi-Scale Causal Intervention for Long-Tailed Image Classification","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414359385","doi":"https://doi.org/10.24963/ijcai.2025/755"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/755","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","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":null,"display_name":"Xiaoshuo Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoshuo Yan","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115600314","display_name":"Zhaochuan Li","orcid":"https://orcid.org/0009-0004-6660-0831"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhaochuan Li","raw_affiliation_strings":["Inspur,China","School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur,China","institution_ids":["https://openalex.org/I4210144143"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100629169","display_name":"Lei Meng","orcid":"https://orcid.org/0000-0002-0273-5946"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lei Meng","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035416388","display_name":"Zhuang Qi","orcid":"https://orcid.org/0000-0001-6730-8075"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhuang Qi","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100750540","display_name":"Wei Wu","orcid":"https://orcid.org/0000-0002-7406-7916"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Wu","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100674833","display_name":"Zixuan Li","orcid":"https://orcid.org/0000-0002-7119-2113"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]},{"id":"https://openalex.org/I4210144143","display_name":"Inspur (China)","ror":"https://ror.org/0474p4r72","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210144143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zixuan Li","raw_affiliation_strings":["Inspur,China","School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Inspur,China","institution_ids":["https://openalex.org/I4210144143"]},{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080015931","display_name":"Xiangxu Meng","orcid":"https://orcid.org/0000-0001-9842-4044"},"institutions":[{"id":"https://openalex.org/I154099455","display_name":"Shandong University","ror":"https://ror.org/0207yh398","country_code":"CN","type":"education","lineage":["https://openalex.org/I154099455"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangxu Meng","raw_affiliation_strings":["School of Software, Shandong University, Jinan, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Software, Shandong University, Jinan, China","institution_ids":["https://openalex.org/I154099455"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"6785","last_page":"6793"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.8587999939918518,"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/T10320","display_name":"Neural Networks and Applications","score":0.8587999939918518,"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/spurious-relationship","display_name":"Spurious relationship","score":0.6814000010490417},{"id":"https://openalex.org/keywords/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.6394000053405762},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.46480000019073486},{"id":"https://openalex.org/keywords/causal-model","display_name":"Causal model","score":0.4415999948978424},{"id":"https://openalex.org/keywords/boosting","display_name":"Boosting (machine learning)","score":0.4415000081062317},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.41760000586509705},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.3991999924182892},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.39890000224113464},{"id":"https://openalex.org/keywords/causal-inference","display_name":"Causal inference","score":0.3912000060081482},{"id":"https://openalex.org/keywords/visual-reasoning","display_name":"Visual reasoning","score":0.3912000060081482}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.6814000010490417},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6672000288963318},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6509000062942505},{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.6394000053405762},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6384999752044678},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.46480000019073486},{"id":"https://openalex.org/C11671645","wikidata":"https://www.wikidata.org/wiki/Q5054567","display_name":"Causal model","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.4415000081062317},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.41760000586509705},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.39890000224113464},{"id":"https://openalex.org/C158600405","wikidata":"https://www.wikidata.org/wiki/Q5054566","display_name":"Causal inference","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.36149999499320984},{"id":"https://openalex.org/C8642999","wikidata":"https://www.wikidata.org/wiki/Q4171168","display_name":"Hyperparameter","level":2,"score":0.3537999987602234},{"id":"https://openalex.org/C176181172","wikidata":"https://www.wikidata.org/wiki/Q3490301","display_name":"Nondeterministic algorithm","level":2,"score":0.35359999537467957},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.33799999952316284},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32179999351501465},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.31299999356269836},{"id":"https://openalex.org/C115086926","wikidata":"https://www.wikidata.org/wiki/Q17004651","display_name":"Causal reasoning","level":3,"score":0.31189998984336853},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C163504300","wikidata":"https://www.wikidata.org/wiki/Q2364925","display_name":"Causal structure","level":2,"score":0.29350000619888306},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.28279998898506165},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.27959999442100525},{"id":"https://openalex.org/C28006648","wikidata":"https://www.wikidata.org/wiki/Q6934509","display_name":"Multi-task learning","level":3,"score":0.27889999747276306},{"id":"https://openalex.org/C161301231","wikidata":"https://www.wikidata.org/wiki/Q3478658","display_name":"Knowledge representation and reasoning","level":2,"score":0.2743000090122223},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C2781045450","wikidata":"https://www.wikidata.org/wiki/Q254569","display_name":"Backdoor","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.27090001106262207},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2621999979019165},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.26089999079704285},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/755","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/755","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"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],"inference":[1],"has":[2],"emerged":[3],"as":[4],"a":[5,102],"promising":[6],"approach":[7],"to":[8,34,74,84,107,141,148,179],"mitigate":[9],"long-tail":[10,196],"classification":[11],"by":[12,17,172,188,208],"handling":[13],"the":[14,23,51,118,127,136,157,166,181,185,200],"biases":[15,206],"introduced":[16,207],"class":[18],"imbalance.":[19],"However,":[20],"along":[21],"with":[22,90],"change":[24],"of":[25,53,168],"advanced":[26],"backbone":[27],"models":[28,40,56],"from":[29,144],"Convolutional":[30],"Neural":[31],"Networks":[32],"(CNNs)":[33],"Visual":[35],"Transformers":[36],"(ViT),":[37],"existing":[38,54,213],"causal":[39,55,72,104,110,114,120,154],"may":[41],"not":[42],"achieve":[43],"an":[44],"expected":[45],"performance":[46],"gain.":[47],"This":[48],"paper":[49,99],"investigates":[50],"influence":[52],"on":[57,194],"CNNs":[58],"and":[59,80,129,138],"ViT":[60],"variants,":[61],"highlighting":[62],"that":[63,199],"ViT's":[64],"global":[65],"feature":[66,139],"representation":[67,121],"makes":[68],"it":[69,125,164],"hard":[70],"for":[71],"methods":[73],"model":[75,143],"associations":[76,111,183],"between":[77],"fine-grained":[78,109,153],"features":[79],"predictions,":[81],"which":[82,151,211],"leads":[83],"difficulties":[85],"in":[86,117,184],"classifying":[87],"tail":[88],"classes":[89],"similar":[91],"visual":[92],"appearance.":[93],"To":[94],"address":[95],"these":[96],"issues,":[97],"this":[98],"proposes":[100],"TSCNet,":[101],"two-stage":[103],"modeling":[105],"method":[106],"discover":[108],"through":[112],"multi-scale":[113],"interventions.":[115],"Specifically,":[116],"hierarchical":[119],"learning":[122],"stage":[123,162],"(HCRL),":[124],"decouples":[126],"background":[128],"objects,":[130],"applying":[131],"backdoor":[132],"interventions":[133],"at":[134],"both":[135],"patch":[137],"level":[140],"prevent":[142],"using":[145],"class-irrelevant":[146],"areas":[147],"infer":[149],"labels":[150],"enhances":[152],"representation.":[155],"In":[156],"counterfactual":[158,175],"logits'":[159],"bias":[160],"calibration":[161],"(CLBC),":[163],"refines":[165],"optimization":[167],"model's":[169],"decision":[170],"boundary":[171],"adaptive":[173],"constructing":[174],"balanced":[176],"data":[177,189,209],"distribution":[178],"remove":[180],"spurious":[182],"logits":[186],"caused":[187],"distribution.":[190],"Extensive":[191],"experiments":[192],"conducted":[193],"various":[195],"benchmarks":[197],"demonstrate":[198],"proposed":[201],"TSCNet":[202],"can":[203],"eliminate":[204],"multiple":[205],"imbalance,":[210],"outperforms":[212],"methods.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}