{"id":"https://openalex.org/W4414990195","doi":"https://doi.org/10.1109/iccv51701.2025.00160","title":"DiMPLE - Disentangled Multi-Modal Prompt Learning: Enhancing Out-of-Distribution Alignment with Invariant and Spurious Feature Separation","display_name":"DiMPLE - Disentangled Multi-Modal Prompt Learning: Enhancing Out-of-Distribution Alignment with Invariant and Spurious Feature Separation","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414990195","doi":"https://doi.org/10.1109/iccv51701.2025.00160"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.00160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2506.21237","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5015650372","display_name":"Umaima Rahman","orcid":null},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":true,"raw_author_name":"Umaima Rahman","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088282276","display_name":"Mohammad Yaqub","orcid":"https://orcid.org/0000-0001-6896-1105"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Mohammad Yaqub","raw_affiliation_strings":["Mohamed Bin Zayed University of Artificial Intelligence"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Mohamed Bin Zayed University of Artificial Intelligence","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078933997","display_name":"Dwarikanath Mahapatra","orcid":"https://orcid.org/0000-0001-9749-7858"},"institutions":[{"id":"https://openalex.org/I176601375","display_name":"Khalifa University of Science and Technology","ror":"https://ror.org/05hffr360","country_code":"AE","type":"education","lineage":["https://openalex.org/I176601375"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Dwarikanath Mahapatra","raw_affiliation_strings":["Khalifa University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Khalifa University","institution_ids":["https://openalex.org/I176601375"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5015650372"],"corresponding_institution_ids":["https://openalex.org/I4210113480"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13775318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1634","last_page":"1643"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9379000067710876,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9379000067710876,"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":0.9527999758720398},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.6775000095367432},{"id":"https://openalex.org/keywords/dimple","display_name":"Dimple","score":0.6668999791145325},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6274999976158142},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5400000214576721},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4221999943256378}],"concepts":[{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.9527999758720398},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.6775000095367432},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6675000190734863},{"id":"https://openalex.org/C152327431","wikidata":"https://www.wikidata.org/wiki/Q521200","display_name":"Dimple","level":2,"score":0.6668999791145325},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6274999976158142},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5400000214576721},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5049999952316284},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4821000099182129},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4221999943256378},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.41830000281333923},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.40470001101493835},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4043000042438507},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3939000070095062},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3458000123500824},{"id":"https://openalex.org/C152139883","wikidata":"https://www.wikidata.org/wiki/Q252973","display_name":"Mutual information","level":2,"score":0.3037000000476837}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.00160","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.00160","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2506.21237","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21237","pdf_url":"https://arxiv.org/pdf/2506.21237","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},{"id":"doi:10.48550/arxiv.2506.21237","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2506.21237","pdf_url":null,"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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2506.21237","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2506.21237","pdf_url":"https://arxiv.org/pdf/2506.21237","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"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"},"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":{"We":[0],"introduce":[1],"DiMPLe":[2,42,93],"(Disentangled":[3],"Multi-Modal":[4],"Prompt":[5],"Learning),":[6],"a":[7],"novel":[8,57,119],"approach":[9],"to":[10,56,61,98],"disentangle":[11],"invariant":[12,75,88],"and":[13,18,46,59,76,83,106,116],"spurious":[14,77,80],"features":[15,44],"across":[16,47,102],"vision":[17],"language":[19],"modalities":[20,48],"in":[21,26,112,118],"multi-modal":[22],"learning.":[23],"Spurious":[24],"correlations":[25],"visual":[27],"data":[28],"often":[29],"hinder":[30],"out-of-distribution":[31],"(OOD)":[32],"performance.":[33],"Unlike":[34],"prior":[35],"methods":[36],"focusing":[37],"solely":[38],"on":[39,87],"image":[40],"features,":[41,78],"disentangles":[43],"within":[45],"while":[49],"maintaining":[50],"consistent":[51],"alignment,":[52],"enabling":[53],"better":[54],"generalization":[55],"classes":[58],"robustness":[60],"distribution":[62],"shifts.":[63],"Our":[64],"method":[65],"combines":[66],"three":[67],"key":[68],"objectives:":[69],"(1)":[70],"mutual":[71],"information":[72],"minimization":[73],"between":[74],"(2)":[79],"feature":[81],"regularization,":[82],"(3)":[84],"contrastive":[85],"learning":[86],"features.":[89],"Extensive":[90],"experiments":[91],"demonstrate":[92],"demonstrates":[94],"superior":[95],"performance":[96],"compared":[97],"CoOp-OOD,":[99],"when":[100],"averaged":[101],"11":[103],"diverse":[104],"datasets,":[105],"achieves":[107],"absolute":[108],"gains":[109],"of":[110],"15.27":[111],"base":[113],"class":[114,120],"accuracy":[115],"44.31":[117],"accuracy.":[121]},"counts_by_year":[],"updated_date":"2026-05-06T06:03:25.996018","created_date":"2025-10-09T00:00:00"}