{"id":"https://openalex.org/W7151458955","doi":"https://doi.org/10.48550/arxiv.2604.04444","title":"Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection","display_name":"Parameter-Efficient Semantic Augmentation for Enhancing Open-Vocabulary Object Detection","publication_year":2026,"publication_date":"2026-04-06","ids":{"openalex":"https://openalex.org/W7151458955","doi":"https://doi.org/10.48550/arxiv.2604.04444"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.04444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2604.04444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101886287","display_name":"Weihao Cao","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cao, Weihao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133103210","display_name":"Runqi Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Runqi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133136419","display_name":"Xiaoyue Duan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Xiaoyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133135734","display_name":"Jinchao Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jinchao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133101306","display_name":"Ang Yang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yang, Ang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133101554","display_name":"Liping Jing","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jing, Liping","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7355999946594238,"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":0.7355999946594238,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.14980000257492065,"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":0.052299998700618744,"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/semantics","display_name":"Semantics (computer science)","score":0.7912999987602234},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6470999717712402},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5846999883651733},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5734000205993652},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5430999994277954},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5162000060081482},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.4674000144004822},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4291999936103821}],"concepts":[{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.7912999987602234},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7900999784469604},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6470999717712402},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6200000047683716},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5846999883651733},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5734000205993652},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5430999994277954},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5162000060081482},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4674000144004822},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4291999936103821},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4059999883174896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.40209999680519104},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.36090001463890076},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.36010000109672546},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.34450000524520874},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33239999413490295},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3142000138759613},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.30640000104904175},{"id":"https://openalex.org/C90312973","wikidata":"https://www.wikidata.org/wiki/Q7449052","display_name":"Semantic data model","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.26910001039505005},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26570001244544983},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.2653000056743622}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.04444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2604.04444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.04444","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"object":[1,9,90],"detection":[2,23],"(OVOD)":[3],"enables":[4],"models":[5,66],"to":[6,37,67,104,120],"detect":[7],"any":[8],"category,":[10],"including":[11],"unseen":[12],"ones.":[13],"Benefiting":[14],"from":[15,47,118,143],"large-scale":[16],"pre-training,":[17],"existing":[18,65],"OVOD":[19,151],"methods":[20],"achieve":[21],"strong":[22],"performance":[24,33],"on":[25,156],"general":[26],"scenarios":[27],"(e.g.,":[28],"OV-COCO)":[29],"but":[30],"suffer":[31],"severe":[32],"drops":[34],"when":[35],"transferred":[36],"downstream":[38],"tasks":[39],"with":[40],"substantial":[41],"domain":[42,160,182],"shifts.":[43],"This":[44],"degradation":[45],"stems":[46],"the":[48,62,132,145,149],"scarcity":[49],"and":[50,108,162,184],"weak":[51],"semantics":[52,70,107],"of":[53,64,148],"category":[54,73],"labels":[55],"in":[56],"domain-specific":[57,110],"task,":[58],"as":[59,61],"well":[60],"inability":[63],"capture":[68,105],"auxiliary":[69],"beyond":[71],"coarse-grained":[72],"label.":[74],"To":[75],"address":[76],"these":[77],"issues,":[78],"we":[79,93,124],"propose":[80,94],"HSA-DINO,":[81],"a":[82,95,126,178],"parameter-efficient":[83],"semantic":[84,112,134],"augmentation":[85,135],"framework":[86],"for":[87],"enhancing":[88],"open-vocabulary":[89,185],"detection.":[91],"Specifically,":[92],"multi-scale":[96],"prompt":[97],"bank":[98],"that":[99,129,169],"leverages":[100],"image":[101],"feature":[102],"pyramids":[103],"hierarchical":[106],"select":[109],"local":[111],"prompts,":[113],"progressively":[114],"enriching":[115],"textual":[116],"representations":[117],"coarse":[119],"fine-grained":[121],"levels.":[122],"Furthermore,":[123],"introduce":[125],"semantic-aware":[127],"router":[128],"dynamically":[130],"selects":[131],"appropriate":[133],"strategy":[136],"during":[137],"inference,":[138],"thereby":[139],"preventing":[140],"parameter":[141],"updates":[142],"degrading":[144],"generalization":[146],"ability":[147],"pre-trained":[150],"model.":[152],"We":[153],"evaluate":[154],"HSA-DINO":[155,170],"OV-COCO,":[157],"several":[158],"vertical":[159],"datasets,":[161],"modified":[163],"benchmark":[164],"settings.":[165],"The":[166],"results":[167],"show":[168],"performs":[171],"favorably":[172],"against":[173],"previous":[174],"state-of-the-art":[175],"methods,":[176],"achieving":[177],"superior":[179],"trade-off":[180],"between":[181],"adaptability":[183],"generalization.":[186]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-08T00:00:00"}