{"id":"https://openalex.org/W4389523744","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.629","title":"APoLLo : Unified Adapter and Prompt Learning for Vision Language Models","display_name":"APoLLo : Unified Adapter and Prompt Learning for Vision Language Models","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4389523744","doi":"https://doi.org/10.18653/v1/2023.emnlp-main.629"},"language":"en","primary_location":{"id":"doi:10.18653/v1/2023.emnlp-main.629","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.629","pdf_url":"https://aclanthology.org/2023.emnlp-main.629.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://aclanthology.org/2023.emnlp-main.629.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101778650","display_name":"Sanjoy Chowdhury","orcid":"https://orcid.org/0000-0003-4256-4720"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sanjoy Chowdhury","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101977185","display_name":"Sayan Nag","orcid":"https://orcid.org/0000-0001-5652-125X"},"institutions":[{"id":"https://openalex.org/I185261750","display_name":"University of Toronto","ror":"https://ror.org/03dbr7087","country_code":"CA","type":"education","lineage":["https://openalex.org/I185261750"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Sayan Nag","raw_affiliation_strings":["University of Toronto"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Toronto","institution_ids":["https://openalex.org/I185261750"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5004194238","display_name":"Dinesh Manocha","orcid":"https://orcid.org/0000-0001-7047-9801"},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Dinesh Manocha","raw_affiliation_strings":["University of Maryland, College Park"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland, College Park","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.0852,"has_fulltext":true,"cited_by_count":18,"citation_normalized_percentile":{"value":0.917657,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"10173","last_page":"10187"},"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":0.9962999820709229,"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/T10028","display_name":"Topic Modeling","score":0.992900013923645,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8186718225479126},{"id":"https://openalex.org/keywords/adapter","display_name":"Adapter (computing)","score":0.6892479658126831},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5924952626228333},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5819377899169922},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.5583437085151672},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.4800727963447571},{"id":"https://openalex.org/keywords/modalities","display_name":"Modalities","score":0.45667123794555664},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.36858969926834106},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.13543885946273804}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8186718225479126},{"id":"https://openalex.org/C177284502","wikidata":"https://www.wikidata.org/wiki/Q1005390","display_name":"Adapter (computing)","level":2,"score":0.6892479658126831},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5924952626228333},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5819377899169922},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5583437085151672},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.4800727963447571},{"id":"https://openalex.org/C2779903281","wikidata":"https://www.wikidata.org/wiki/Q6888026","display_name":"Modalities","level":2,"score":0.45667123794555664},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36858969926834106},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.13543885946273804},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","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/C36289849","wikidata":"https://www.wikidata.org/wiki/Q34749","display_name":"Social science","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.18653/v1/2023.emnlp-main.629","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.629","pdf_url":"https://aclanthology.org/2023.emnlp-main.629.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.18653/v1/2023.emnlp-main.629","is_oa":true,"landing_page_url":"https://doi.org/10.18653/v1/2023.emnlp-main.629","pdf_url":"https://aclanthology.org/2023.emnlp-main.629.pdf","source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4","score":0.6700000166893005}],"awards":[{"id":"https://openalex.org/G4344294614","display_name":null,"funder_award_id":"W911NF2110026","funder_id":"https://openalex.org/F4320338281","funder_display_name":"Army Research Office"}],"funders":[{"id":"https://openalex.org/F4320338281","display_name":"Army Research Office","ror":"https://ror.org/05epdh915"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4389523744.pdf","grobid_xml":"https://content.openalex.org/works/W4389523744.grobid-xml"},"referenced_works_count":70,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W24089286","https://openalex.org/W1846799578","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/W2896457183","https://openalex.org/W2947707615","https://openalex.org/W2953937638","https://openalex.org/W2955425717","https://openalex.org/W2962707369","https://openalex.org/W2962945654","https://openalex.org/W2963211188","https://openalex.org/W2964303773","https://openalex.org/W2965373594","https://openalex.org/W2971296908","https://openalex.org/W3005680577","https://openalex.org/W3037492894","https://openalex.org/W3094502228","https://openalex.org/W3126337491","https://openalex.org/W3128513979","https://openalex.org/W3134652006","https://openalex.org/W3138516171","https://openalex.org/W3166396011","https://openalex.org/W3174770825","https://openalex.org/W3177096435","https://openalex.org/W3198377975","https://openalex.org/W3205270560","https://openalex.org/W3213647938","https://openalex.org/W3215626407","https://openalex.org/W4205991051","https://openalex.org/W4224545477","https://openalex.org/W4226182655","https://openalex.org/W4229453513","https://openalex.org/W4280496682","https://openalex.org/W4281838252","https://openalex.org/W4281987380","https://openalex.org/W4284961860","https://openalex.org/W4288089799","https://openalex.org/W4292779060","https://openalex.org/W4296151208","https://openalex.org/W4310557340","https://openalex.org/W4311642023","https://openalex.org/W4312310776","https://openalex.org/W4312424618","https://openalex.org/W4312446817","https://openalex.org/W4312784228","https://openalex.org/W4312884055","https://openalex.org/W4312933868","https://openalex.org/W4313068342","https://openalex.org/W4321337794","https://openalex.org/W4322718191","https://openalex.org/W4362655426","https://openalex.org/W4366330698","https://openalex.org/W4366458249","https://openalex.org/W4368321032","https://openalex.org/W4378473852","https://openalex.org/W4385571139","https://openalex.org/W4385801086","https://openalex.org/W4386065353","https://openalex.org/W4386065763","https://openalex.org/W4386065836","https://openalex.org/W4386071547","https://openalex.org/W4386071687","https://openalex.org/W4386076084","https://openalex.org/W4386790226","https://openalex.org/W4389519448"],"related_works":["https://openalex.org/W4362597605","https://openalex.org/W1574414179","https://openalex.org/W4297676672","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4281702477","https://openalex.org/W2490526372","https://openalex.org/W4376166922","https://openalex.org/W4378510483","https://openalex.org/W4221142204"],"abstract_inverted_index":{"The":[0],"choice":[1],"of":[2,13,48],"input":[3],"text":[4],"prompt":[5],"plays":[6],"a":[7,25,56,119],"critical":[8],"role":[9],"in":[10,55,65,94],"the":[11,45,74,77,84],"performance":[12],"Vision-Language":[14,36],"Pretrained":[15],"(VLP)":[16],"models":[17,50],"such":[18],"as":[19],"CLIP.":[20],"We":[21,59,80],"present":[22],"APoLLo":[23,117],",":[24],"unified":[26],"multi-modal":[27],"approach":[28],"that":[29],"combines":[30],"Adapter":[31],"and":[32,69,111],"Prompt":[33],"learning":[34],"for":[35,131],"models.":[37],"Our":[38,97],"method":[39,98],"is":[40,99],"designed":[41],"to":[42,72,91,106,123],"substantially":[43],"improve":[44],"generalization":[46,105],"capabilities":[47],"VLP":[49],"when":[51],"they":[52],"are":[53],"fine-tuned":[54],"few-shot":[57],"setting.":[58],"introduce":[60],"trainable":[61],"cross-attention-based":[62],"adapter":[63],"layers":[64],"conjunction":[66],"with":[67],"vision":[68],"language":[70],"encoders":[71],"strengthen":[73],"alignment":[75],"between":[76,83],"two":[78],"modalities.":[79],"enforce":[81],"consistency":[82],"respective":[85],"encoder":[86],"branches":[87],"(receiving":[88],"augmented":[89],"inputs)":[90],"prevent":[92],"overfitting":[93],"downstream":[95],"tasks.":[96],"evaluated":[100],"on":[101,128],"three":[102],"representative":[103],"tasks:":[104],"novel":[107,129],"classes,":[108],"cross-dataset":[109],"evaluation,":[110],"unseen":[112],"domain":[113],"shifts.":[114],"In":[115],"practice,":[116],"achieves":[118],"relative":[120],"gain":[121],"up":[122],"6.03%":[124],"over":[125],"MaPLe":[126],"(SOTA)":[127],"classes":[130],"10":[132],"diverse":[133],"image":[134],"recognition":[135],"datasets.":[136]},"counts_by_year":[{"year":2026,"cited_by_count":3},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":2}],"updated_date":"2026-08-18T07:49:30.821534","created_date":"2025-10-10T00:00:00"}