{"id":"https://openalex.org/W4403792169","doi":"https://doi.org/10.1145/3664647.3680983","title":"Enhancing Pre-trained ViTs for Downstream Task Adaptation: A Locality-Aware Prompt Learning Method","display_name":"Enhancing Pre-trained ViTs for Downstream Task Adaptation: A Locality-Aware Prompt Learning Method","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403792169","doi":"https://doi.org/10.1145/3664647.3680983"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680983","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd 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/A5077560552","display_name":"Shaokun Wang","orcid":"https://orcid.org/0000-0001-8945-1200"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Shaokun Wang","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056455411","display_name":"Yifan Yu","orcid":"https://orcid.org/0009-0002-5291-9003"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yifan Yu","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102819064","display_name":"Yuhang He","orcid":"https://orcid.org/0000-0002-6750-1403"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuhang He","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100687952","display_name":"Yihong Gong","orcid":"https://orcid.org/0000-0002-1793-5836"},"institutions":[{"id":"https://openalex.org/I87445476","display_name":"Xi'an Jiaotong University","ror":"https://ror.org/017zhmm22","country_code":"CN","type":"education","lineage":["https://openalex.org/I87445476"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yihong Gong","raw_affiliation_strings":["Xi'an Jiaotong University, Xi'an, China"],"affiliations":[{"raw_affiliation_string":"Xi'an Jiaotong University, Xi'an, China","institution_ids":["https://openalex.org/I87445476"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5077560552"],"corresponding_institution_ids":["https://openalex.org/I87445476"],"apc_list":null,"apc_paid":null,"fwci":0.2632,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55617698,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"797","last_page":"806"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9902999997138977,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9902999997138977,"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":0.9754999876022339,"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/T11122","display_name":"Online Learning and Analytics","score":0.9645000100135803,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/locality","display_name":"Locality","score":0.8455835580825806},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7628113031387329},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.7000319957733154},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6995072364807129},{"id":"https://openalex.org/keywords/downstream","display_name":"Downstream (manufacturing)","score":0.5797733664512634},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.37189239263534546},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08558350801467896},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.06978869438171387},{"id":"https://openalex.org/keywords/neuroscience","display_name":"Neuroscience","score":0.059152573347091675},{"id":"https://openalex.org/keywords/operations-management","display_name":"Operations management","score":0.05667924880981445}],"concepts":[{"id":"https://openalex.org/C2779808786","wikidata":"https://www.wikidata.org/wiki/Q6664603","display_name":"Locality","level":2,"score":0.8455835580825806},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7628113031387329},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.7000319957733154},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6995072364807129},{"id":"https://openalex.org/C2776207758","wikidata":"https://www.wikidata.org/wiki/Q5303302","display_name":"Downstream (manufacturing)","level":2,"score":0.5797733664512634},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37189239263534546},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08558350801467896},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.06978869438171387},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.059152573347091675},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.05667924880981445},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3664647.3680983","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680983","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/13","display_name":"Climate action"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W2022539494","https://openalex.org/W2963154697","https://openalex.org/W2981836045","https://openalex.org/W2990045899","https://openalex.org/W3121523901","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W3166986030","https://openalex.org/W3174770825","https://openalex.org/W3185341429","https://openalex.org/W3195830874","https://openalex.org/W3198377975","https://openalex.org/W3198525581","https://openalex.org/W3212076252","https://openalex.org/W4205991051","https://openalex.org/W4214493665","https://openalex.org/W4214709605","https://openalex.org/W4229453513","https://openalex.org/W4285247752","https://openalex.org/W4287022992","https://openalex.org/W4299997467","https://openalex.org/W4312238419","https://openalex.org/W4312310776","https://openalex.org/W4312480274","https://openalex.org/W4312599212","https://openalex.org/W4312651322","https://openalex.org/W4313175608","https://openalex.org/W4320167334","https://openalex.org/W4386071547","https://openalex.org/W4386071620","https://openalex.org/W4386075553","https://openalex.org/W4386075796","https://openalex.org/W4386501573","https://openalex.org/W4387968387","https://openalex.org/W4390873714","https://openalex.org/W6605052884","https://openalex.org/W6748883668","https://openalex.org/W6848935878"],"related_works":["https://openalex.org/W1583765404","https://openalex.org/W4214653257","https://openalex.org/W1556451512","https://openalex.org/W1555349535","https://openalex.org/W4234091740","https://openalex.org/W2055438207","https://openalex.org/W4213350282","https://openalex.org/W2521424917","https://openalex.org/W3040203686","https://openalex.org/W4381247876"],"abstract_inverted_index":{"Vision":[0],"Transformers":[1],"(ViTs)":[2],"excel":[3],"in":[4,16,106],"extracting":[5,18],"global":[6,217],"information":[7,19],"from":[8,156],"image":[9,126,141],"patches.":[10,142],"However,":[11],"their":[12,24],"inherent":[13],"limitation":[14],"lies":[15],"effectively":[17],"within":[20],"local":[21,108,138,154,188,219],"regions,":[22],"hindering":[23],"applicability":[25],"and":[26,37,131,218,235],"performance.":[27],"Particularly,":[28],"fully":[29],"supervised":[30],"pre-trained":[31,68,82,200],"ViTs,":[32],"such":[33],"as":[34,127,191],"Vanilla":[35],"ViT":[36,83],"CLIP,":[38],"face":[39],"the":[40,65,115,170,213,233],"challenge":[41],"of":[42,67,117,172,215,237],"locality":[43],"vanishing":[44],"when":[45],"adapting":[46],"to":[47,63,70,101,136,151,177],"downstream":[48,71,223,230],"tasks.":[49,72],"To":[50],"address":[51],"this,":[52],"we":[53],"introduce":[54],"a":[55,75,81,86,96,118,128,144,173],"novel":[56],"LOcality-aware":[57],"pRompt":[58],"lEarning":[59],"(LORE)":[60],"method,":[61],"aiming":[62],"improve":[64],"adaptation":[66],"ViTs":[69,201],"LORE":[73],"integrates":[74],"data-driven":[76],"Black":[77,196],"Box":[78,89,93,197,210],"module":[79,94],"(i.e.,":[80],"encoder)":[84],"with":[85,114,202],"knowledge-driven":[87],"White":[88,92],"module.":[90,198],"The":[91,183],"is":[95,149],"locality-aware":[97,179,184,204],"prompt":[98,205],"learning":[99,158,206],"mechanism":[100,148],"compensate":[102],"for":[103,181,194],"ViTs'":[104],"deficiency":[105],"incorporating":[107],"information.":[109],"More":[110],"specifically,":[111],"it":[112],"begins":[113],"design":[116],"Locality":[119],"Interaction":[120],"Network":[121],"(LIN),":[122],"which":[123],"treats":[124],"an":[125],"neighbor":[129],"graph":[130,133],"employs":[132],"convolution":[134],"operations":[135],"enhance":[137],"relationships":[139],"among":[140],"Subsequently,":[143],"Knowledge-Locality":[145,159],"Attention":[146],"(KLA)":[147],"proposed":[150],"capture":[152,214],"critical":[153],"regions":[155],"images,":[157],"(K-L)":[160],"prototypes":[161,168],"utilizing":[162],"relevant":[163],"semantic":[164],"knowledge.":[165],"Afterwards,":[166],"K-L":[167],"guide":[169],"training":[171],"Prompt":[174],"Generator":[175],"(PG)":[176],"generate":[178],"prompts":[180],"images.":[182],"prompts,":[185],"aggregating":[186],"crucial":[187],"information,":[189,220],"serve":[190],"additional":[192],"input":[193],"our":[195,203,208,238],"Combining":[199],"mechanism,":[207],"Black-White":[209],"model":[211],"enables":[212],"both":[216],"facilitating":[221],"effective":[222],"task":[224],"adaptation.":[225],"Experimental":[226],"evaluations":[227],"across":[228],"four":[229],"tasks":[231],"demonstrate":[232],"effectiveness":[234],"superiority":[236],"LORE.":[239]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}