{"id":"https://openalex.org/W4407217526","doi":"https://doi.org/10.1007/s10994-025-06742-z","title":"Alignclip: navigating the misalignments for robust vision-language generalization","display_name":"Alignclip: navigating the misalignments for robust vision-language generalization","publication_year":2025,"publication_date":"2025-02-06","ids":{"openalex":"https://openalex.org/W4407217526","doi":"https://doi.org/10.1007/s10994-025-06742-z"},"language":"en","primary_location":{"id":"doi:10.1007/s10994-025-06742-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06742-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06742-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06742-z.pdf","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5086112796","display_name":"Zhongyi Han","orcid":"https://orcid.org/0000-0003-2851-193X"},"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"]},{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["AE","SA"],"is_corresponding":true,"raw_author_name":"Zhongyi Han","raw_affiliation_strings":["CEMSE, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CEMSE, King Abdullah University of Science and Technology, Thuwal, Saudi Arabia","institution_ids":["https://openalex.org/I71920554"]},{"raw_affiliation_string":"Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5012997528","display_name":"Gongxu Luo","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":false,"raw_author_name":"Gongxu Luo","raw_affiliation_strings":["Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111078774","display_name":"Hao Sun","orcid":"https://orcid.org/0009-0000-5327-6594"},"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":"Hao Sun","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/A5100697598","display_name":"Yaqian Li","orcid":"https://orcid.org/0000-0003-1032-9910"},"institutions":[{"id":"https://openalex.org/I4210129149","display_name":"Postmaster Psychologie Opleidingen","ror":"https://ror.org/03naar428","country_code":"NL","type":"education","lineage":["https://openalex.org/I4210129149"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yaqian Li","raw_affiliation_strings":["OPPO Research Institute, OPPO, Shanghai, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"OPPO Research Institute, OPPO, Shanghai, China","institution_ids":["https://openalex.org/I4210129149"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047240103","display_name":"Bo Han","orcid":"https://orcid.org/0000-0002-6338-0958"},"institutions":[{"id":"https://openalex.org/I141568987","display_name":"Hong Kong Baptist University","ror":"https://ror.org/0145fw131","country_code":"HK","type":"education","lineage":["https://openalex.org/I141568987"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Bo Han","raw_affiliation_strings":["Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Hong Kong Baptist University, Kowloon Tong, Hong Kong","institution_ids":["https://openalex.org/I141568987"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102023771","display_name":"Mingming Gong","orcid":"https://orcid.org/0000-0001-7147-5589"},"institutions":[{"id":"https://openalex.org/I165779595","display_name":"The University of Melbourne","ror":"https://ror.org/01ej9dk98","country_code":"AU","type":"education","lineage":["https://openalex.org/I165779595"]},{"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","AU"],"is_corresponding":false,"raw_author_name":"Mingming Gong","raw_affiliation_strings":["Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","School of Mathematics and Statistics, The University of Melbourne, Melbourne, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"School of Mathematics and Statistics, The University of Melbourne, Melbourne, Australia","institution_ids":["https://openalex.org/I165779595"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100342380","display_name":"Kun Zhang","orcid":"https://orcid.org/0000-0003-2140-2546"},"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"]},{"id":"https://openalex.org/I74973139","display_name":"Carnegie Mellon University","ror":"https://ror.org/05x2bcf33","country_code":"US","type":"education","lineage":["https://openalex.org/I74973139"]}],"countries":["AE","US"],"is_corresponding":false,"raw_author_name":"Kun Zhang","raw_affiliation_strings":["Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","Department of Philosophy, Carnegie Mellon University, Pittsburgh, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Department of Philosophy, Carnegie Mellon University, Pittsburgh, USA","institution_ids":["https://openalex.org/I74973139"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065250332","display_name":"Tongliang Liu","orcid":"https://orcid.org/0000-0002-9640-6472"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]},{"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","AU"],"is_corresponding":true,"raw_author_name":"Tongliang Liu","raw_affiliation_strings":["Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","School of Computer Science, The University of Sydney, Sydney, Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Machine Learning, Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, United Arab Emirates","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"School of Computer Science, The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":7,"institutions_distinct_count":8,"corresponding_author_ids":["https://openalex.org/A5065250332","https://openalex.org/A5086112796"],"corresponding_institution_ids":["https://openalex.org/I129604602","https://openalex.org/I4210113480","https://openalex.org/I71920554"],"apc_list":{"value":2990,"currency":"USD","value_usd":2990},"apc_paid":{"value":2990,"currency":"USD","value_usd":2990},"fwci":3.8206,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.93479932,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"114","issue":"3","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9991999864578247,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.7861087322235107},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5841708779335022},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5780336856842041},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4744775593280792},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3492550253868103},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2644822895526886},{"id":"https://openalex.org/keywords/mathematical-analysis","display_name":"Mathematical analysis","score":0.048847049474716187}],"concepts":[{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.7861087322235107},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5841708779335022},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5780336856842041},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4744775593280792},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3492550253868103},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2644822895526886},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.048847049474716187}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1007/s10994-025-06742-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06742-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06742-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1007/s10994-025-06742-z","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s10994-025-06742-z","pdf_url":"https://link.springer.com/content/pdf/10.1007/s10994-025-06742-z.pdf","source":{"id":"https://openalex.org/S62148650","display_name":"Machine Learning","issn_l":"0885-6125","issn":["0885-6125","1573-0565"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"journal"},"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Machine Learning","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10","score":0.41999998688697815}],"awards":[],"funders":[{"id":"https://openalex.org/F4320322320","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4407217526.pdf","grobid_xml":"https://content.openalex.org/works/W4407217526.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W652269744","https://openalex.org/W1882958252","https://openalex.org/W2108598243","https://openalex.org/W2145215286","https://openalex.org/W2155858138","https://openalex.org/W2531327146","https://openalex.org/W2767414122","https://openalex.org/W2894728917","https://openalex.org/W2964288524","https://openalex.org/W3037492894","https://openalex.org/W3040002795","https://openalex.org/W3094502228","https://openalex.org/W3102842772","https://openalex.org/W3135367836","https://openalex.org/W3135588948","https://openalex.org/W3169976301","https://openalex.org/W3180303049","https://openalex.org/W3194427711","https://openalex.org/W3198377975","https://openalex.org/W3198675127","https://openalex.org/W4221151247","https://openalex.org/W4221167530","https://openalex.org/W4226182655","https://openalex.org/W4229453513","https://openalex.org/W4285787895","https://openalex.org/W4296151208","https://openalex.org/W4306729030","https://openalex.org/W4307079025","https://openalex.org/W4312252361","https://openalex.org/W4312310776","https://openalex.org/W4312420092","https://openalex.org/W4312910992","https://openalex.org/W4312972638","https://openalex.org/W4362597616","https://openalex.org/W4386071547","https://openalex.org/W4390872773","https://openalex.org/W4402727764","https://openalex.org/W6678360021","https://openalex.org/W6678470764","https://openalex.org/W6739901393","https://openalex.org/W6757817989","https://openalex.org/W6780233385","https://openalex.org/W6799707133","https://openalex.org/W6849786500"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"In":[0],"the":[1,18,58,71,99,147],"realm":[2],"of":[3,20,101,130,149],"Vision-Language":[4],"Pretraining":[5],"models,":[6],"achieving":[7],"robust":[8],"and":[9,52,132,138,151],"adaptive":[10],"representations":[11,150],"is":[12],"a":[13,113,128],"cornerstone":[14],"for":[15,75],"successfully":[16],"handling":[17],"unpredictability":[19],"real-world":[21,77],"scenarios.":[22],"This":[23],"paper":[24],"delves":[25],"into":[26],"two":[27],"pivotal":[28],"misalignment":[29],"challenges":[30],"inherent":[31],"to":[32,42,61,97,120],"Contrastive":[33],"Language-Image":[34],"Pre-training":[35],"(CLIP)":[36],"models:":[37],"attention":[38,93,102,105],"misalignment,":[39,55],"which":[40],"leads":[41],"an":[43,86],"overemphasis":[44],"on":[45,66,127],"background":[46],"elements":[47],"rather":[48],"than":[49],"salient":[50],"objects,":[51],"predictive":[53],"category":[54],"characterized":[56],"by":[57,91],"model\u2019s":[59],"struggle":[60],"discern":[62],"between":[63],"classes":[64],"based":[65],"similarity.":[67],"These":[68],"misalignments":[69],"undermine":[70],"representational":[72],"stability":[73,148],"essential":[74],"dynamic,":[76],"applications.":[78],"To":[79],"address":[80],"these":[81],"challenges,":[82],"we":[83,141],"propose":[84],"AlignCLIP,":[85],"advanced":[87],"fine-tuning":[88],"methodology":[89],"distinguished":[90],"its":[92],"alignment":[94],"loss,":[95],"designed":[96],"calibrate":[98],"distribution":[100,136],"across":[103],"multi-head":[104],"layers.":[106],"Furthermore,":[107],"AlignCLIP":[108,144],"introduces":[109],"semantic":[110],"label":[111],"smoothing,":[112],"technique":[114],"that":[115,143],"leverages":[116],"textual":[117],"class":[118],"similarities":[119],"refine":[121],"prediction":[122],"hierarchies.":[123],"Through":[124],"comprehensive":[125],"experimentation":[126],"variety":[129],"datasets":[131],"in":[133],"scenarios":[134],"involving":[135],"shifts":[137],"unseen":[139],"classes,":[140],"demonstrate":[142],"significantly":[145],"enhances":[146],"shows":[152],"superior":[153],"generalization":[154],"capabilities.":[155]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-07-23T08:03:31.855105","created_date":"2025-10-10T00:00:00"}