{"id":"https://openalex.org/W4387939438","doi":"https://doi.org/10.1007/s11263-023-01904-9","title":"Language-Aware Soft Prompting: Text-to-Text Optimization for Few- and Zero-Shot Adaptation of V &L Models","display_name":"Language-Aware Soft Prompting: Text-to-Text Optimization for Few- and Zero-Shot Adaptation of V &L Models","publication_year":2023,"publication_date":"2023-10-25","ids":{"openalex":"https://openalex.org/W4387939438","doi":"https://doi.org/10.1007/s11263-023-01904-9"},"language":"en","primary_location":{"id":"doi:10.1007/s11263-023-01904-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01904-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01904-9.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","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/s11263-023-01904-9.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5072822225","display_name":"Adrian Bulat","orcid":"https://orcid.org/0000-0002-3185-4979"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Adrian Bulat","raw_affiliation_strings":["Samsung AI Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Samsung AI Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024224610","display_name":"Georgios Tzimiropoulos","orcid":"https://orcid.org/0000-0002-1803-5338"},"institutions":[{"id":"https://openalex.org/I166337079","display_name":"Queen Mary University of London","ror":"https://ror.org/026zzn846","country_code":"GB","type":"education","lineage":["https://openalex.org/I124357947","https://openalex.org/I166337079"]},{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Georgios Tzimiropoulos","raw_affiliation_strings":["Queen Mary University of London, London, UK","Samsung AI Cambridge, Cambridge, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Queen Mary University of London, London, UK","institution_ids":["https://openalex.org/I166337079"]},{"raw_affiliation_string":"Samsung AI Cambridge, Cambridge, UK","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5024224610"],"corresponding_institution_ids":["https://openalex.org/I166337079","https://openalex.org/I4210117523"],"apc_list":{"value":2890,"currency":"EUR","value_usd":3690},"apc_paid":{"value":2890,"currency":"EUR","value_usd":3690},"fwci":1.3019,"has_fulltext":true,"cited_by_count":8,"citation_normalized_percentile":{"value":0.84525451,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":99},"biblio":{"volume":"132","issue":"4","first_page":"1108","last_page":"1125"},"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":0.9998000264167786,"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":0.9998000264167786,"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":0.9973999857902527,"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":0.9954000115394592,"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/overfitting","display_name":"Overfitting","score":0.9103943705558777},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.767263650894165},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6383438110351562},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.519836962223053},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5164132714271545},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5030121207237244},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5002212524414062},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.48975300788879395},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.453734815120697},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.330727219581604},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.1839887499809265},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.11268141865730286}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9103943705558777},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.767263650894165},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6383438110351562},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.519836962223053},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5164132714271545},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5030121207237244},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5002212524414062},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.48975300788879395},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.453734815120697},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.330727219581604},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.1839887499809265},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.11268141865730286},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1007/s11263-023-01904-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01904-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01904-9.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},{"id":"pmh:oai:qmro.qmul.ac.uk:123456789/92248","is_oa":true,"landing_page_url":"https://qmro.qmul.ac.uk/xmlui/handle/123456789/92248","pdf_url":"https://qmro.qmul.ac.uk/xmlui/bitstream/123456789/92248/2/Tzimiropoulos%20Language-Aware%20Soft%202023%20Published.pdf","source":{"id":"https://openalex.org/S4306400530","display_name":"Queen Mary Research Online (Queen Mary University of London)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I166337079","host_organization_name":"Queen Mary University of London","host_organization_lineage":["https://openalex.org/I166337079"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1007/s11263-023-01904-9","is_oa":true,"landing_page_url":"https://doi.org/10.1007/s11263-023-01904-9","pdf_url":"https://link.springer.com/content/pdf/10.1007/s11263-023-01904-9.pdf","source":{"id":"https://openalex.org/S25538012","display_name":"International Journal of Computer Vision","issn_l":"0920-5691","issn":["0920-5691","1573-1405"],"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","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Computer Vision","raw_type":"journal-article"},"sustainable_development_goals":[{"score":0.5799999833106995,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4387939438.pdf"},"referenced_works_count":42,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1977295328","https://openalex.org/W2017814585","https://openalex.org/W2047643928","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2155904486","https://openalex.org/W2533598788","https://openalex.org/W2596142952","https://openalex.org/W2618530766","https://openalex.org/W2889965839","https://openalex.org/W2947707615","https://openalex.org/W2952476201","https://openalex.org/W2963804252","https://openalex.org/W2964194231","https://openalex.org/W2970119729","https://openalex.org/W2999905431","https://openalex.org/W3005680577","https://openalex.org/W3034302825","https://openalex.org/W3036224891","https://openalex.org/W3037492894","https://openalex.org/W3126337491","https://openalex.org/W3135367836","https://openalex.org/W3153427360","https://openalex.org/W3170826592","https://openalex.org/W3172642864","https://openalex.org/W3174770825","https://openalex.org/W3175558129","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W4205991051","https://openalex.org/W4229453513","https://openalex.org/W4312310776","https://openalex.org/W4319163914","https://openalex.org/W4385570016","https://openalex.org/W4390873714","https://openalex.org/W6739901393","https://openalex.org/W6756040250","https://openalex.org/W6767599400","https://openalex.org/W6776867236","https://openalex.org/W6778883912","https://openalex.org/W6779928312"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W2922073769","https://openalex.org/W4378510483","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4221142204","https://openalex.org/W3098003361"],"abstract_inverted_index":{"Abstract":[0],"Soft":[1,84],"prompt":[2,154],"learning":[3,87,155],"has":[4],"emerged":[5],"as":[6],"a":[7,16,20,81,92,139,149,162,215],"promising":[8],"direction":[9],"for":[10,187,203,229,257,272],"adapting":[11],"V":[12],"&L":[13],"models":[14],"to":[15,104,110,138,165,177,209],"downstream":[17,231],"task":[18],"using":[19],"few":[21],"training":[22,30],"examples.":[23],"However,":[24],"current":[25],"methods":[26,50],"significantly":[27,244],"overfit":[28],"the":[29,43,54,69,98,101,118,122,196,199,204,207,230,258,261],"data":[31,61],"suffering":[32],"from":[33,42],"large":[34],"accuracy":[35,262],"degradation":[36],"when":[37],"tested":[38],"on":[39,235,249,263],"unseen":[40],"classes":[41,182,265],"same":[44],"domain.":[45],"In":[46],"addition,":[47],"all":[48,226,246],"prior":[49,247],"operate":[51],"exclusively":[52],"under":[53],"assumption":[55],"that":[56,96,172,240,283],"both":[57],"vision":[58],"and":[59,156,158,252,255,270],"language":[60],"is":[62,134,174],"present.":[63],"To":[64,74,116],"this":[65],"end,":[66],"we":[67,79,124,147,170,213,238,281],"make":[68],"following":[70],"5":[71],"contributions:":[72],"(1)":[73],"alleviate":[75],"base":[76],"class":[77,185],"overfitting,":[78],"propose":[80,126,161],"novel":[82,216,264],"Language-Aware":[83],"Prompting":[85],"(LASP)":[86],"method":[88],"by":[89,153,267],"means":[90],"of":[91,100,121,132,142,198,219,275],"text-to-text":[93],"cross-entropy":[94],"loss":[95],"maximizes":[97],"probability":[99],"learned":[102,200],"prompts":[103,133,269],"be":[105,297],"correctly":[106],"classified":[107],"with":[108,136],"respect":[109,137],"pre-defined":[111],"hand-crafted":[112,268],"textual":[113,143],"prompts.":[114,144,201],"(2)":[115],"increase":[117],"representation":[119],"capacity":[120],"prompts,":[123],"also":[125],"grouped":[127],"LASP":[128,173,220],"where":[129,221],"each":[130],"group":[131],"optimized":[135],"separate":[140],"subset":[141],"(3)":[145],"Moreover,":[146],"identify":[148],"visual-language":[150],"misalignment":[151],"introduced":[152],"LASP,":[157],"more":[159],"importantly,":[160],"re-calibration":[163],"mechanism":[164],"address":[166],"it.":[167],"(4)":[168],"Importantly,":[169],"show":[171,239,282],"inherently":[175],"amenable":[176],"including,":[178],"during":[179],"training,":[180],"virtual":[181],",":[183],"i.e.":[184],"names":[186],"which":[188],"no":[189,222],"visual":[190,223],"samples":[191,224],"are":[192,227],"available,":[193],"further":[194],"increasing":[195],"robustness":[197],"Expanding":[202],"first":[205,259],"time":[206],"setting":[208],"language-only":[210],"adaptation,":[211],"(5)":[212],"present":[214],"zero-shot":[217,285],"variant":[218,286],"at":[225],"available":[228],"task.":[232],"Through":[233],"evaluations":[234],"11":[236,276],"datasets,":[237],"our":[241,284],"approach":[242],"(a)":[243],"outperforms":[245],"works":[248],"soft":[250],"prompting,":[251],"(b)":[253],"matches":[254],"surpasses,":[256],"time,":[260],"obtained":[266],"CLIP":[271,289],"8":[273],"out":[274],"test":[277],"datasets.":[278],"Finally,":[279],"(c)":[280],"improves":[287],"upon":[288],"without":[290],"requiring":[291],"any":[292],"extra":[293],"data.":[294],"Code":[295],"will":[296],"made":[298],"available.":[299]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3}],"updated_date":"2026-06-13T06:13:01.061226","created_date":"2025-10-10T00:00:00"}