{"id":"https://openalex.org/W4385763969","doi":"https://doi.org/10.24963/ijcai.2023/659","title":"Addressing Weak Decision Boundaries in Image Classification by Leveraging Web Search and Generative Models","display_name":"Addressing Weak Decision Boundaries in Image Classification by Leveraging Web Search and Generative Models","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385763969","doi":"https://doi.org/10.24963/ijcai.2023/659"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/659","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/659","pdf_url":"https://www.ijcai.org/proceedings/2023/0659.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0659.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5092629422","display_name":"Preetam Prabhu Srikar Dammu","orcid":"https://orcid.org/0009-0007-2021-0354"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Preetam Prabhu Srikar Dammu","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103242391","display_name":"Yunhe Feng","orcid":"https://orcid.org/0000-0002-7599-2484"},"institutions":[{"id":"https://openalex.org/I123534392","display_name":"University of North Texas","ror":"https://ror.org/00v97ad02","country_code":"US","type":"education","lineage":["https://openalex.org/I123534392"]},{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yunhe Feng","raw_affiliation_strings":["University of North Texas, Denton, TX, USA","University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of North Texas, Denton, TX, USA","institution_ids":["https://openalex.org/I123534392"]},{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061319881","display_name":"Chirag Shah","orcid":"https://orcid.org/0000-0002-3797-4293"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Chirag Shah","raw_affiliation_strings":["University of Washington, Seattle, WA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Washington, Seattle, WA, USA","institution_ids":["https://openalex.org/I201448701"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.1632,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55091816,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"5941","last_page":"5949"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973999857902527,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9973999857902527,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9973000288009644,"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/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9951000213623047,"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/computer-science","display_name":"Computer science","score":0.7328745722770691},{"id":"https://openalex.org/keywords/generative-grammar","display_name":"Generative grammar","score":0.5903177857398987},{"id":"https://openalex.org/keywords/generative-model","display_name":"Generative model","score":0.5112409591674805},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.4921185374259949},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4645521342754364},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4238257110118866},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3718101978302002},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3514488935470581},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.3279833197593689},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32752713561058044}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7328745722770691},{"id":"https://openalex.org/C39890363","wikidata":"https://www.wikidata.org/wiki/Q36108","display_name":"Generative grammar","level":2,"score":0.5903177857398987},{"id":"https://openalex.org/C167966045","wikidata":"https://www.wikidata.org/wiki/Q5532625","display_name":"Generative model","level":3,"score":0.5112409591674805},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.4921185374259949},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4645521342754364},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4238257110118866},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3718101978302002},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3514488935470581},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3279833197593689},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32752713561058044}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.24963/ijcai.2023/659","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/659","pdf_url":"https://www.ijcai.org/proceedings/2023/0659.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2310.19986","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2310.19986","pdf_url":"https://arxiv.org/pdf/2310.19986","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/659","is_oa":true,"landing_page_url":"https://doi.org/10.24963/ijcai.2023/659","pdf_url":"https://www.ijcai.org/proceedings/2023/0659.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.46000000834465027,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4385763969.pdf"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W1673923490","https://openalex.org/W1945616565","https://openalex.org/W2104167780","https://openalex.org/W2126326837","https://openalex.org/W2194775991","https://openalex.org/W2732026016","https://openalex.org/W2767106145","https://openalex.org/W2946455955","https://openalex.org/W2962787423","https://openalex.org/W2962858109","https://openalex.org/W2963349562","https://openalex.org/W2963857521","https://openalex.org/W2990751682","https://openalex.org/W2998702515","https://openalex.org/W3005040148","https://openalex.org/W3023702633","https://openalex.org/W3036567070","https://openalex.org/W3040002795","https://openalex.org/W3094502228","https://openalex.org/W3101298150","https://openalex.org/W3118536434","https://openalex.org/W3123103757","https://openalex.org/W3129576130","https://openalex.org/W3160274781","https://openalex.org/W3166112346","https://openalex.org/W3177096435","https://openalex.org/W3177397812","https://openalex.org/W3207710400","https://openalex.org/W4200191097","https://openalex.org/W4224281327","https://openalex.org/W4282960557","https://openalex.org/W4283803090","https://openalex.org/W4286907938","https://openalex.org/W4287126366","https://openalex.org/W4293846201","https://openalex.org/W4312933868","https://openalex.org/W4316669404"],"related_works":["https://openalex.org/W4365211920","https://openalex.org/W3014948380","https://openalex.org/W4380551139","https://openalex.org/W4317695495","https://openalex.org/W4287117424","https://openalex.org/W4387506531","https://openalex.org/W2087346071","https://openalex.org/W2967848559","https://openalex.org/W4299831724","https://openalex.org/W4283803360"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"technologies":[3],"are":[4,16],"known":[5],"to":[6,23,71,123,187,229],"be":[7],"riddled":[8],"with":[9],"ethical":[10],"and":[11,54,68,94,103,148,151,207,235],"operational":[12],"problems,":[13],"however,":[14],"we":[15,173,190,214],"witnessing":[17],"an":[18,51,59,85,208],"increasing":[19],"thrust":[20],"by":[21,204],"businesses":[22],"deploy":[24],"them":[25],"in":[26,50,100,106,179,195,221],"sensitive":[27],"applications.":[28],"One":[29],"major":[30],"issue":[31],"among":[32],"many":[33],"is":[34,98,121,202,227],"that":[35,61,96,109],"ML":[36],"models":[37,70],"do":[38],"not":[39],"perform":[40],"equally":[41],"well":[42,139],"for":[43,129,136,142],"underrepresented":[44],"groups.":[45],"This":[46],"puts":[47],"vulnerable":[48,111,219],"populations":[49,112,220],"even":[52],"disadvantaged":[53],"unfavorable":[55],"position.":[56],"We":[57,80],"propose":[58],"approach":[60],"leverages":[62],"the":[63,75,168,180,196,224],"power":[64],"of":[65,74,77,116,233],"web":[66],"search":[67,134],"generative":[69],"alleviate":[72,161],"some":[73],"shortcomings":[76],"discriminative":[78],"models.":[79],"demonstrate":[81],"our":[82,216],"method":[83,120,217],"on":[84,218],"image":[86],"classification":[87],"problem":[88],"using":[89],"ImageNet's":[90],"People":[91],"Subtree":[92],"subset,":[93],"show":[95,153],"it":[97,201],"effective":[99],"enhancing":[101],"robustness":[102],"mitigating":[104],"bias":[105,163],"certain":[107],"classes":[108],"represent":[110],"(e.g.,":[113],"female":[114],"doctor":[115],"color).":[117],"Our":[118],"new":[119],"able":[122],"(1)":[124],"identify":[125],"weak":[126],"decision":[127,198],"boundaries":[128],"such":[130],"classes;":[131],"(2)":[132],"construct":[133],"queries":[135],"Google":[137],"as":[138,140,200],"text":[141],"generating":[143],"images":[144],"through":[145],"DALL-E":[146],"2":[147],"Stable":[149],"Diffusion;":[150],"(3)":[152],"how":[154],"these":[155,188],"newly":[156],"captured":[157],"training":[158],"samples":[159],"could":[160],"population":[162],"issue.":[164],"While":[165],"still":[166],"improving":[167],"model's":[169,181],"overall":[170],"performance":[171],"considerably,":[172],"achieve":[174],"a":[175,192,230],"significant":[176],"reduction":[177],"(77.30%)":[178],"gender":[182],"accuracy":[183],"disparity.":[184],"In":[185],"addition":[186],"improvements,":[189],"observed":[191],"notable":[193],"enhancement":[194],"classifier's":[197],"boundary,":[199],"characterized":[203],"fewer":[205],"weakspots":[206],"increased":[209],"separation":[210],"between":[211],"classes.":[212],"Although":[213],"showcase":[215],"this":[222],"study,":[223],"proposed":[225],"technique":[226],"extendable":[228],"wide":[231],"range":[232],"problems":[234],"domains.":[236]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}