{"id":"https://openalex.org/W3204924011","doi":"https://doi.org/10.1109/tpami.2023.3290012","title":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","display_name":"Counterfactual Samples Synthesizing and Training for Robust Visual Question Answering","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W3204924011","doi":"https://doi.org/10.1109/tpami.2023.3290012","mag":"3204924011","pmid":"https://pubmed.ncbi.nlm.nih.gov/37368813"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3290012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3290012","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100336360","display_name":"Long Chen","orcid":"https://orcid.org/0000-0001-6148-9709"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Long Chen","raw_affiliation_strings":["Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR"],"raw_orcid":"https://orcid.org/0000-0001-6148-9709","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Kowloon, Hong Kong SAR","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030295721","display_name":"Yuhang Zheng","orcid":"https://orcid.org/0000-0001-9628-1940"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang Zheng","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0001-9628-1940","affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5028589167","display_name":"Yulei Niu","orcid":"https://orcid.org/0000-0001-6332-3382"},"institutions":[{"id":"https://openalex.org/I78577930","display_name":"Columbia University","ror":"https://ror.org/00hj8s172","country_code":"US","type":"education","lineage":["https://openalex.org/I78577930"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yulei Niu","raw_affiliation_strings":["Department of Electrical Engineering, Columbia University, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0001-6332-3382","affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Columbia University, New York, NY, USA","institution_ids":["https://openalex.org/I78577930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042324027","display_name":"Hanwang Zhang","orcid":"https://orcid.org/0000-0001-7374-8739"},"institutions":[{"id":"https://openalex.org/I172675005","display_name":"Nanyang Technological University","ror":"https://ror.org/02e7b5302","country_code":"SG","type":"education","lineage":["https://openalex.org/I172675005"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Hanwang Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, Nanyang Technological University, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-7374-8739","affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Nanyang Technological University, Singapore","institution_ids":["https://openalex.org/I172675005"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101485989","display_name":"Jun Xiao","orcid":"https://orcid.org/0000-0002-6142-9914"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Xiao","raw_affiliation_strings":["College of Computer Science, Zhejiang University, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science, Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":4,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":4.0418,"has_fulltext":false,"cited_by_count":39,"citation_normalized_percentile":{"value":0.95329556,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":100},"biblio":{"volume":"45","issue":"11","first_page":"1","last_page":"16"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":1.0,"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":1.0,"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":0.9980999827384949,"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/T10028","display_name":"Topic Modeling","score":0.9947999715805054,"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/counterfactual-thinking","display_name":"Counterfactual thinking","score":0.9417175054550171},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7169567346572876},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6568461656570435},{"id":"https://openalex.org/keywords/question-answering","display_name":"Question answering","score":0.6114820837974548},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5988041758537292},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.555147647857666},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5082120895385742},{"id":"https://openalex.org/keywords/training-set","display_name":"Training set","score":0.5004937648773193},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.49618273973464966},{"id":"https://openalex.org/keywords/eye-tracking","display_name":"Eye tracking","score":0.4260879158973694},{"id":"https://openalex.org/keywords/test-set","display_name":"Test set","score":0.41348177194595337},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09515094757080078}],"concepts":[{"id":"https://openalex.org/C108650721","wikidata":"https://www.wikidata.org/wiki/Q1783253","display_name":"Counterfactual thinking","level":2,"score":0.9417175054550171},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7169567346572876},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6568461656570435},{"id":"https://openalex.org/C44291984","wikidata":"https://www.wikidata.org/wiki/Q1074173","display_name":"Question answering","level":2,"score":0.6114820837974548},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5988041758537292},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.555147647857666},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5082120895385742},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.5004937648773193},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.49618273973464966},{"id":"https://openalex.org/C56461940","wikidata":"https://www.wikidata.org/wiki/Q970687","display_name":"Eye tracking","level":2,"score":0.4260879158973694},{"id":"https://openalex.org/C169903167","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Test set","level":2,"score":0.41348177194595337},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09515094757080078},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/tpami.2023.3290012","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3290012","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:37368813","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/37368813","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-128918","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-128918","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"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":"Article"},{"id":"pmh:oai:dr.ntu.edu.sg:10356/171830","is_oa":false,"landing_page_url":"https://hdl.handle.net/10356/171830","pdf_url":null,"source":{"id":"https://openalex.org/S4306402609","display_name":"DR-NTU (Nanyang Technological University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I172675005","host_organization_name":"Nanyang Technological University","host_organization_lineage":["https://openalex.org/I172675005"],"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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.41999998688697815,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1933349210","https://openalex.org/W2099471712","https://openalex.org/W2250539671","https://openalex.org/W2471094925","https://openalex.org/W2560730294","https://openalex.org/W2561715562","https://openalex.org/W2613718673","https://openalex.org/W2745461083","https://openalex.org/W2759653627","https://openalex.org/W2842511635","https://openalex.org/W2887978863","https://openalex.org/W2889326796","https://openalex.org/W2916723116","https://openalex.org/W2934842096","https://openalex.org/W2950761309","https://openalex.org/W2955124656","https://openalex.org/W2962685807","https://openalex.org/W2962858109","https://openalex.org/W2963140463","https://openalex.org/W2963260436","https://openalex.org/W2963383024","https://openalex.org/W2963518342","https://openalex.org/W2963521239","https://openalex.org/W2963630207","https://openalex.org/W2963644680","https://openalex.org/W2963798744","https://openalex.org/W2963890019","https://openalex.org/W2963954913","https://openalex.org/W2963955422","https://openalex.org/W2964044490","https://openalex.org/W2964118342","https://openalex.org/W2964305556","https://openalex.org/W2965628639","https://openalex.org/W2966683369","https://openalex.org/W2970019270","https://openalex.org/W2970231061","https://openalex.org/W2970548373","https://openalex.org/W2973151436","https://openalex.org/W2983256121","https://openalex.org/W2985056390","https://openalex.org/W2987123286","https://openalex.org/W2995460200","https://openalex.org/W3007641164","https://openalex.org/W3026376263","https://openalex.org/W3034287395","https://openalex.org/W3034727271","https://openalex.org/W3034978746","https://openalex.org/W3035145964","https://openalex.org/W3035512383","https://openalex.org/W3035517717","https://openalex.org/W3035524453","https://openalex.org/W3090449556","https://openalex.org/W3091588028","https://openalex.org/W3099884329","https://openalex.org/W3100160322","https://openalex.org/W3100345210","https://openalex.org/W3104788521","https://openalex.org/W3174366544","https://openalex.org/W3175344799","https://openalex.org/W3177934633","https://openalex.org/W3199231060","https://openalex.org/W3202355045","https://openalex.org/W3202778561","https://openalex.org/W4214648142","https://openalex.org/W4297808394","https://openalex.org/W4312457137","https://openalex.org/W6752083267","https://openalex.org/W6754733129","https://openalex.org/W6763000187","https://openalex.org/W6764072591","https://openalex.org/W6764756247","https://openalex.org/W6767211374","https://openalex.org/W6768307605","https://openalex.org/W6769858568","https://openalex.org/W6774460212","https://openalex.org/W6776700526","https://openalex.org/W6777578573","https://openalex.org/W6804171142","https://openalex.org/W6844194202"],"related_works":["https://openalex.org/W4401571341","https://openalex.org/W1999699871","https://openalex.org/W4225124612","https://openalex.org/W2043806667","https://openalex.org/W4362604364","https://openalex.org/W2021633306","https://openalex.org/W2006801911","https://openalex.org/W2033669961","https://openalex.org/W2971899271","https://openalex.org/W1972167985"],"abstract_inverted_index":{"Today's":[0],"VQA":[1,32,45,78,126,187,202],"models":[2,127,188,203],"still":[3],"tend":[4],"to":[5,16,18,39,59,68,101,130,193,204],"capture":[6],"superficial":[7],"linguistic":[8,103],"correlations":[9],"in":[10,105,171,175],"the":[11,19,41,60,87,102,186,201,207,217,247],"training":[12,42,123],"set":[13,21],"and":[14,47,118,136,143,157,177,210,230,235,280],"fail":[15],"generalize":[17],"test":[20],"with":[22,71,124,189],"different":[23],"QA":[24],"distributions.":[25],"To":[26,107,215],"reduce":[27],"these":[28],"language":[29],"biases,":[30],"recent":[31],"works":[33],"introduce":[34],"an":[35,76,232],"auxiliary":[36],"question-only":[37],"model":[38,62,83,97,257],"regularize":[40],"of":[43,75,150,224,249,256],"targeted":[44],"model,":[46],"achieve":[48,268],"dominating":[49],"performance":[50,270],"on":[51,86,132,241,254,271],"diagnostic":[52],"benchmarks":[53,274],"for":[54,228],"out-of-distribution":[55,273],"testing.":[56],"However,":[57],"due":[58],"complex":[61],"design,":[63],"ensemble-based":[64],"methods":[65],"are":[66,128],"unable":[67],"equip":[69],"themselves":[70],"two":[72,151,222],"indispensable":[73],"characteristics":[74],"ideal":[77],"model:":[79],"1)":[80],"Visual-explainable:":[81],"The":[82,96],"should":[84,98],"rely":[85],"right":[88],"visual":[89],"regions":[90],"when":[91],"making":[92],"decisions.":[93],"2)":[94],"Question-sensitive:":[95],"be":[99],"sensitive":[100],"variations":[104],"questions.":[106],"this":[108],"end,":[109],"we":[110,220,267],"propose":[111,221],"a":[112],"novel":[113],"model-agnostic":[114],"Counterfactual":[115,153,158],"Samples":[116,154,159],"Synthesizing":[117,155],"Training":[119,160],"(CSST)":[120],"strategy.":[121],"After":[122],"CSST,":[125],"forced":[129],"focus":[131],"all":[133,272],"critical":[134,169],"objects":[135,170],"words,":[137],"which":[138],"significantly":[139],"improves":[140],"both":[141,190],"visual-explainable":[142],"question-sensitive":[144],"abilities.":[145],"Specifically,":[146],"CSST":[147],"is":[148],"composed":[149],"parts:":[152],"(CSS)":[156],"(CST).":[161],"CSS":[162],"generates":[163],"counterfactual":[164,213],"samples":[165,192,209],"by":[166,252],"carefully":[167],"masking":[168],"images":[172],"or":[173],"words":[174],"questions":[176],"assigning":[178],"pseudo":[179],"ground-truth":[180,196],"answers.":[181],"CST":[182,218],"not":[183],"only":[184],"trains":[185],"complementary":[191],"predict":[194],"respective":[195],"answers,":[197],"but":[198],"also":[199],"urges":[200],"further":[205],"distinguish":[206],"original":[208],"superficially":[211],"similar":[212],"ones.":[214],"facilitate":[216],"training,":[219],"variants":[223],"supervised":[225],"contrastive":[226],"loss":[227],"VQA,":[229],"design":[231],"effective":[233],"positive":[234],"negative":[236],"sample":[237],"selection":[238],"mechanism":[239],"based":[240],"CSS.":[242],"Extensive":[243],"experiments":[244],"have":[245],"shown":[246],"effectiveness":[248],"CSST.":[250],"Particularly,":[251],"building":[253],"top":[255],"LMH+SAR":[258],"(Clark":[259],"et":[260,264],"al.":[261,265],"2019),":[262],"(Si":[263],"2021),":[266],"record-breaking":[269],"(e.g.,":[275],"VQA-CP":[276,278],"v2,":[277],"v1,":[279],"GQA-OOD).":[281]},"counts_by_year":[{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":21},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}