{"id":"https://openalex.org/W4388189152","doi":"https://doi.org/10.1145/3581783.3611911","title":"Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification","display_name":"Distilling Vision-Language Foundation Models: A Data-Free Approach via Prompt Diversification","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4388189152","doi":"https://doi.org/10.1145/3581783.3611911"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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/A5074343584","display_name":"Yunyi Xuan","orcid":"https://orcid.org/0009-0000-6365-5475"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yunyi Xuan","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100686044","display_name":"Weijie Chen","orcid":"https://orcid.org/0000-0001-5508-473X"},"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":"Weijie Chen","raw_affiliation_strings":["Zhejiang University & Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University & Hikvision Research Institute, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056516274","display_name":"Shicai Yang","orcid":"https://orcid.org/0000-0002-9260-1334"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shicai Yang","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636142","display_name":"Di Xie","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Di Xie","raw_affiliation_strings":["Hikvision Research Institute, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Hikvision Research Institute, Hangzhou, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010577514","display_name":"Luojun Lin","orcid":"https://orcid.org/0000-0002-1141-2487"},"institutions":[{"id":"https://openalex.org/I80947539","display_name":"Fuzhou University","ror":"https://ror.org/011xvna82","country_code":"CN","type":"education","lineage":["https://openalex.org/I80947539"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Luojun Lin","raw_affiliation_strings":["Fuzhou University, Fuzhou, China"],"affiliations":[{"raw_affiliation_string":"Fuzhou University, Fuzhou, China","institution_ids":["https://openalex.org/I80947539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5008666077","display_name":"Yueting Zhuang","orcid":"https://orcid.org/0000-0001-9017-2508"},"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":"Yueting Zhuang","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5074343584"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.4814,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.65932629,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"4928","last_page":"4938"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9995999932289124,"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":0.9995999932289124,"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":0.9994000196456909,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9979000091552734,"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":0.7933304309844971},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.6866910457611084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6004606485366821},{"id":"https://openalex.org/keywords/diversification","display_name":"Diversification (marketing strategy)","score":0.4639316201210022},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.46110305190086365},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.45816570520401},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.42758649587631226}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7933304309844971},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.6866910457611084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6004606485366821},{"id":"https://openalex.org/C180916674","wikidata":"https://www.wikidata.org/wiki/Q3711935","display_name":"Diversification (marketing strategy)","level":2,"score":0.4639316201210022},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46110305190086365},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.45816570520401},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.42758649587631226},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611911","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611911","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 31st ACM International Conference on Multimedia","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":17,"referenced_works":["https://openalex.org/W4149471","https://openalex.org/W1821462560","https://openalex.org/W2110764733","https://openalex.org/W2115733720","https://openalex.org/W2167366427","https://openalex.org/W2194775991","https://openalex.org/W2763549966","https://openalex.org/W2885018852","https://openalex.org/W2982619380","https://openalex.org/W2982802130","https://openalex.org/W3128934284","https://openalex.org/W3191459272","https://openalex.org/W4226426325","https://openalex.org/W6600715346","https://openalex.org/W6601630192","https://openalex.org/W6601977772","https://openalex.org/W6638523607"],"related_works":["https://openalex.org/W4389391504","https://openalex.org/W3162204513","https://openalex.org/W4301410663","https://openalex.org/W4312472185","https://openalex.org/W2382761395","https://openalex.org/W2358904772","https://openalex.org/W2897048536","https://openalex.org/W2480512091","https://openalex.org/W2741848782","https://openalex.org/W2371138613"],"abstract_inverted_index":{"Data-Free":[0],"Knowledge":[1],"Distillation":[2],"(DFKD)":[3],"has":[4],"shown":[5],"great":[6],"potential":[7],"in":[8,39,52,120,140],"creating":[9],"a":[10,86],"compact":[11],"student":[12,87],"model":[13,88],"while":[14],"alleviating":[15],"the":[16,66,77,98,103,113,168,171,177],"dependency":[17],"on":[18,163],"real":[19],"training":[20],"data":[21],"by":[22,126],"synthesizing":[23,121],"surrogate":[24,123],"data.":[25],"However,":[26],"prior":[27],"arts":[28],"are":[29,138],"seldom":[30],"discussed":[31],"under":[32],"distribution":[33],"shifts,":[34],"which":[35],"may":[36],"be":[37],"vulnerable":[38],"real-world":[40],"applications.":[41],"Recent":[42],"Vision-Language":[43,71],"Foundation":[44,72],"Models,":[45],"e.g.,":[46],"CLIP,":[47],"have":[48],"demonstrated":[49],"remarkable":[50],"performance":[51],"zero-shot":[53],"out-of-distribution":[54,99,164],"generalization,":[55],"yet":[56],"consuming":[57],"heavy":[58],"computation":[59],"resources.":[60],"In":[61,107],"this":[62,117],"paper,":[63],"we":[64,143],"discuss":[65],"extension":[67],"of":[68,116,170],"DFKD":[69],"to":[70,76,84,109,150],"Models":[73],"without":[74],"access":[75],"billion-level":[78],"image-text":[79],"datasets.":[80],"The":[81],"objective":[82],"is":[83],"customize":[85],"for":[89],"distribution-agnostic":[90],"downstream":[91],"tasks":[92],"with":[93,154,174],"given":[94],"category":[95,132],"concepts,":[96],"inheriting":[97],"generalization":[100,111,165],"capability":[101],"from":[102],"pre-trained":[104],"foundation":[105],"models.":[106],"order":[108],"avoid":[110],"degradation,":[112],"primary":[114],"challenge":[115],"task":[118],"lies":[119],"diverse":[122,155],"images":[124],"driven":[125],"text":[127,141],"prompts.":[128],"Since":[129],"not":[130],"only":[131],"concepts":[133],"but":[134],"also":[135],"style":[136],"information":[137],"encoded":[139],"prompts,":[142],"propose":[144],"three":[145],"novel":[146],"Prompt":[147],"Diversification":[148],"methods":[149],"encourage":[151],"image":[152],"synthesis":[153],"styles,":[156],"namely":[157],"Mix-Prompt,":[158],"Random-Prompt,":[159],"and":[160],"Contrastive-Prompt.":[161],"Experiments":[162],"datasets":[166],"demonstrate":[167],"effectiveness":[169],"proposed":[172],"methods,":[173],"Contrastive-Prompt":[175],"performing":[176],"best.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-10T00:00:00"}