{"id":"https://openalex.org/W4401857107","doi":"https://doi.org/10.1145/3637528.3671945","title":"Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model","display_name":"Efficient and Long-Tailed Generalization for Pre-trained Vision-Language Model","publication_year":2024,"publication_date":"2024-08-24","ids":{"openalex":"https://openalex.org/W4401857107","doi":"https://doi.org/10.1145/3637528.3671945"},"language":"en","primary_location":{"id":"doi:10.1145/3637528.3671945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","raw_type":"proceedings-article"},"type":"article","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":"https://openalex.org/A5059966571","display_name":"Jiang-Xin Shi","orcid":"https://orcid.org/0000-0002-0318-0911"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiang-Xin Shi","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100548114","display_name":"Chi Zhang","orcid":"https://orcid.org/0009-0005-1124-0493"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104582126","display_name":"Tong Wei","orcid":"https://orcid.org/0000-0002-2766-8209"},"institutions":[{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tong Wei","raw_affiliation_strings":["School of Computer Science and Engineering, Key Laboratory of Computer Network and Information, Integration of Ministry of Education, Southeast University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, Key Laboratory of Computer Network and Information, Integration of Ministry of Education, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100355152","display_name":"Yu-Feng Li","orcid":"https://orcid.org/0000-0002-7727-4304"},"institutions":[{"id":"https://openalex.org/I881766915","display_name":"Nanjing University","ror":"https://ror.org/01rxvg760","country_code":"CN","type":"education","lineage":["https://openalex.org/I881766915"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu-Feng Li","raw_affiliation_strings":["National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China"],"affiliations":[{"raw_affiliation_string":"National Key Laboratory for Novel Software Technology, School of Artificial Intelligence, Nanjing University, Nanjing, China","institution_ids":["https://openalex.org/I881766915"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059966571"],"corresponding_institution_ids":["https://openalex.org/I881766915"],"apc_list":null,"apc_paid":null,"fwci":0.7609,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.72137918,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"2663","last_page":"2673"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9980000257492065,"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":0.9973000288009644,"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/computer-science","display_name":"Computer science","score":0.7096522450447083},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6842623353004456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.596577525138855},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4415972828865051},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.34519970417022705},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1288152039051056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7096522450447083},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6842623353004456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.596577525138855},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4415972828865051},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34519970417022705},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1288152039051056},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3637528.3671945","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3637528.3671945","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","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":12,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2138011018","https://openalex.org/W2533598788","https://openalex.org/W2964194231","https://openalex.org/W3037492894","https://openalex.org/W3177096435","https://openalex.org/W4225922615","https://openalex.org/W4239072543","https://openalex.org/W4390873530"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","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":{"Pre-trained":[0],"vision-language":[1],"models":[2],"like":[3],"CLIP":[4,30,127],"have":[5,49],"shown":[6],"powerful":[7],"zero-shot":[8],"inference":[9],"ability":[10],"via":[11],"image-text":[12],"matching":[13],"and":[14,46,82,106,114,118,133,141],"prove":[15],"to":[16,31,79,100,138,158,175],"be":[17,59,87],"strong":[18],"few-shot":[19],"learners":[20],"in":[21,26],"various":[22],"downstream":[23,32],"tasks.":[24],"However,":[25],"real-world":[27],"scenarios,":[28],"adapting":[29],"tasks":[33,61],"may":[34,41],"encounter":[35],"the":[36,54,92,111,116,126,135,160,198,202],"following":[37],"challenges:":[38],"1)":[39],"data":[40,44],"exhibit":[42],"long-tailed":[43,83],"distributions":[45],"might":[47,58],"not":[48],"abundant":[50],"samples":[51,68],"for":[52,144,172,178],"all":[53],"classes;":[55],"2)":[56],"There":[57],"emerging":[60],"with":[62],"new":[63,119,173],"classes":[64,113,174],"that":[65],"contain":[66],"no":[67],"at":[69,212],"all.":[70],"To":[71,146],"overcome":[72],"them,":[73],"we":[74,95,124,153,168],"propose":[75,96,155],"a":[76,130],"novel":[77],"framework":[78],"achieve":[80],"efficient":[81,122],"generalization,":[84,167],"which":[85],"can":[86],"termed":[88],"as":[89,129],"Candle.":[90],"During":[91],"training":[93,182,199],"process,":[94],"compensating":[97],"logit-adjusted":[98],"loss":[99],"encourage":[101],"large":[102],"margins":[103],"of":[104,150,181,204],"prototypes":[105,143,171],"alleviate":[107],"imbalance":[108],"both":[109,163],"within":[110],"base":[112,117],"between":[115],"classes.":[120],"For":[121,165],"adaptation,":[123],"treat":[125],"model":[128],"black":[131],"box":[132],"leverage":[134],"extracted":[136],"features":[137,161],"obtain":[139],"visual":[140],"textual":[142],"prediction.":[145],"make":[147,176],"full":[148],"use":[149],"multi-modal":[151],"information,":[152],"also":[154],"cross-modal":[156],"attention":[157],"enrich":[159],"from":[162],"modalities.":[164],"effective":[166],"introduce":[169],"virtual":[170],"up":[177],"their":[179],"lack":[180],"images.":[183],"Candle":[184],"achieves":[185],"state-of-the-art":[186],"performance":[187],"over":[188],"extensive":[189],"experiments":[190],"on":[191],"11":[192],"diverse":[193],"datasets":[194],"while":[195],"substantially":[196],"reducing":[197],"time,":[200],"demonstrating":[201],"superiority":[203],"our":[205],"approach.":[206],"The":[207],"source":[208],"code":[209],"is":[210],"available":[211],"https://github.com/shijxcs/Candle.":[213]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}