{"id":"https://openalex.org/W4387969733","doi":"https://doi.org/10.1145/3581783.3611706","title":"VioLET: Vision-Language Efficient Tuning with Collaborative Multi-modal Gradients","display_name":"VioLET: Vision-Language Efficient Tuning with Collaborative Multi-modal Gradients","publication_year":2023,"publication_date":"2023-10-26","ids":{"openalex":"https://openalex.org/W4387969733","doi":"https://doi.org/10.1145/3581783.3611706"},"language":"en","primary_location":{"id":"doi:10.1145/3581783.3611706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611706","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":"conference-paper","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/A5049554440","display_name":"Yaoming Wang","orcid":"https://orcid.org/0000-0002-0026-4247"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaoming Wang","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-0026-4247","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114549708","display_name":"Yuchen Liu","orcid":"https://orcid.org/0000-0002-3096-448X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuchen Liu","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-3096-448X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100614075","display_name":"Xiaopeng Zhang","orcid":"https://orcid.org/0000-0003-1276-1424"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaopeng Zhang","raw_affiliation_strings":["Huawei Technologies Ltd, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1276-1424","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd, Shanghai, China","institution_ids":["https://openalex.org/I2250955327"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031347223","display_name":"J.N. Li","orcid":"https://orcid.org/0000-0002-9846-5951"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9846-5951","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101614377","display_name":"Bowen Shi","orcid":"https://orcid.org/0000-0002-9169-7055"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bowen Shi","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-9169-7055","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100675587","display_name":"Chenglin Li","orcid":"https://orcid.org/0000-0003-2888-594X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chenglin Li","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2888-594X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045342512","display_name":"Wenrui Dai","orcid":"https://orcid.org/0000-0003-2522-5778"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenrui Dai","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-2522-5778","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002494284","display_name":"Hongkai Xiong","orcid":"https://orcid.org/0000-0003-4552-0029"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hongkai Xiong","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-4552-0029","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111504451","display_name":"Qi Tian","orcid":"https://orcid.org/0000-0002-5165-4325"},"institutions":[{"id":"https://openalex.org/I2250955327","display_name":"Huawei Technologies (China)","ror":"https://ror.org/00cmhce21","country_code":"CN","type":"company","lineage":["https://openalex.org/I2250955327"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qi Tian","raw_affiliation_strings":["Huawei Technologies Ltd, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-5165-4325","affiliations":[{"raw_affiliation_string":"Huawei Technologies Ltd, Shenzhen, China","institution_ids":["https://openalex.org/I2250955327"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"4595","last_page":"4605"},"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":0.9997000098228455,"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":0.9997000098228455,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9919000267982483,"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":0.8185320496559143},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5940157175064087},{"id":"https://openalex.org/keywords/modal","display_name":"Modal","score":0.5920482873916626},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5481961965560913},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5406427383422852},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.4991905689239502},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4611395299434662},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.45075011253356934},{"id":"https://openalex.org/keywords/forgetting","display_name":"Forgetting","score":0.4371177852153778},{"id":"https://openalex.org/keywords/contrast","display_name":"Contrast (vision)","score":0.4105859398841858},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3513341248035431},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.10370686650276184},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.08999526500701904}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8185320496559143},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5940157175064087},{"id":"https://openalex.org/C71139939","wikidata":"https://www.wikidata.org/wiki/Q910194","display_name":"Modal","level":2,"score":0.5920482873916626},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5481961965560913},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5406427383422852},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.4991905689239502},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4611395299434662},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.45075011253356934},{"id":"https://openalex.org/C7149132","wikidata":"https://www.wikidata.org/wiki/Q1377840","display_name":"Forgetting","level":2,"score":0.4371177852153778},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.4105859398841858},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3513341248035431},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10370686650276184},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08999526500701904},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C188027245","wikidata":"https://www.wikidata.org/wiki/Q750446","display_name":"Polymer chemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3581783.3611706","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3581783.3611706","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":[{"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education","score":0.7699999809265137}],"awards":[{"id":"https://openalex.org/G3164072223","display_name":null,"funder_award_id":"62250055","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3438946646","display_name":null,"funder_award_id":"61932022","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4936292138","display_name":null,"funder_award_id":"T2122024","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G510744082","display_name":null,"funder_award_id":"61831018","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5326461368","display_name":null,"funder_award_id":"61971285","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6094063813","display_name":null,"funder_award_id":"62125109","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6393920532","display_name":null,"funder_award_id":"61972256","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7123918047","display_name":null,"funder_award_id":"62120106007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8700549466","display_name":null,"funder_award_id":"61931023","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2150856297","https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2963736817","https://openalex.org/W2964194231","https://openalex.org/W3037492894","https://openalex.org/W3106539628","https://openalex.org/W3166140588","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4286856918","https://openalex.org/W4287122891","https://openalex.org/W4312310776","https://openalex.org/W4386076003","https://openalex.org/W6771876938","https://openalex.org/W6804126242"],"related_works":["https://openalex.org/W4289718052","https://openalex.org/W2164121020","https://openalex.org/W2145559838","https://openalex.org/W2905319430","https://openalex.org/W3116498279","https://openalex.org/W4287549553","https://openalex.org/W4310285384","https://openalex.org/W3183027292","https://openalex.org/W4301143707","https://openalex.org/W2952745240"],"abstract_inverted_index":{"Parameter-Efficient":[0],"Tuning":[1],"(PET)":[2],"has":[3],"emerged":[4],"as":[5,154],"a":[6,78],"leading":[7],"advancement":[8],"in":[9,55],"both":[10,99],"Natural":[11],"Language":[12,85],"Processing":[13],"and":[14,46,62,111,145],"Computer":[15],"Vision,":[16],"enabling":[17],"efficient":[18],"accommodation":[19],"of":[20,51,98,121],"downstream":[21],"tasks":[22,149],"without":[23,108],"costly":[24],"fine-tuning.":[25],"However,":[26],"most":[27],"existing":[28,170],"PET":[29,80,171],"approaches":[30],"are":[31,140],"limited":[32],"to":[33,59,69,93,117],"uni-modal":[34],"tuning,":[35],"even":[36],"for":[37],"vision-language":[38],"models":[39,57],"like":[40],"CLIP.":[41],"We":[42],"investigate":[43],"this":[44,74],"limitation":[45],"demonstrate":[47],"that":[48,88],"simultaneous":[49],"tuning":[50],"the":[52,95,119,122,131,155],"two":[53,114],"modalities":[54],"such":[56],"leads":[58],"multi-modal":[60,91],"forgetting":[61],"catastrophic":[63],"performance":[64],"degradation,":[65],"particularly":[66],"when":[67],"generalizing":[68],"new":[70],"classes.":[71],"To":[72],"address":[73],"issue,":[75],"we":[76,102,129],"propose":[77],"novel":[79],"approach":[81],"called":[82],"VioLET":[83,157],"(Vision":[84],"Efficient":[86],"Tuning)":[87],"utilizes":[89],"collaborative":[90],"gradients":[92,120],"unlock":[94],"full":[96],"potential":[97],"modalities.":[100],"Specifically,":[101],"incorporate":[103],"an":[104,135],"additional":[105],"visual":[106,115],"encoder":[107],"learnable":[109],"parameters":[110,124],"use":[112],"these":[113],"encoders":[116],"compute":[118],"context":[123],"separately.":[125],"When":[126],"conflicts":[127],"arise,":[128],"replace":[130],"original":[132],"gradient":[133],"with":[134],"orthogonal":[136],"gradient.":[137],"Extensive":[138],"experiments":[139],"conducted":[141],"on":[142,163],"few-shot":[143],"recognition":[144],"unseen":[146],"class":[147],"generalization":[148],"using":[150],"ResNet-50":[151],"or":[152],"ViT/B-16":[153],"backbone.":[156],"consistently":[158],"outperforms":[159],"several":[160],"state-of-the-art":[161],"methods":[162],"11":[164],"datasets,":[165],"showcasing":[166],"its":[167],"superiority":[168],"over":[169],"approaches.":[172],"The":[173],"code":[174],"is":[175],"available":[176],"at":[177],"https://github.com/Wang-Yaoming/VioLET.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}