{"id":"https://openalex.org/W7127087797","doi":"https://doi.org/10.48550/arxiv.2601.22685","title":"OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection","display_name":"OOVDet: Low-Density Prior Learning for Zero-Shot Out-of-Vocabulary Object Detection","publication_year":2026,"publication_date":"2026-01-30","ids":{"openalex":"https://openalex.org/W7127087797","doi":"https://doi.org/10.48550/arxiv.2601.22685"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2601.22685","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22685","pdf_url":"https://arxiv.org/pdf/2601.22685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2601.22685","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5011920646","display_name":"Binyi Su","orcid":"https://orcid.org/0000-0002-8024-347X","observed_orcids":["https://orcid.org/0000-0002-8024-347X","https://orcid.org/0000-0002-9234-2002"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Su, Binyi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5124791899","display_name":"Chenghao Huang","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Chenghao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5149428680","display_name":"Haiyong Chen","orcid":"https://orcid.org/0000-0002-5262-4208","observed_orcids":["https://orcid.org/0000-0002-5262-4208"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Haiyong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.7929999828338623,"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":0.7929999828338623,"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":0.19779999554157257,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0020000000949949026,"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/zero-shot-object-detection","display_name":"zero-shot detection","score":0.8840000033378601},{"id":"https://openalex.org/keywords/latent-space","display_name":"latent space","score":0.4860000014305115},{"id":"https://openalex.org/keywords/forecast-uncertainty","display_name":"forecast uncertainty","score":0.7120000123977661},{"id":"https://openalex.org/keywords/gaussian-kernel-density-estimation","display_name":"Gaussian kernel density estimation","score":0.7689999938011169}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6915000081062317},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.685699999332428},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.5921000242233276},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4975999891757965},{"id":"https://openalex.org/C71134354","wikidata":"https://www.wikidata.org/wiki/Q458825","display_name":"Kernel density estimation","level":3,"score":0.490200012922287},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.48969998955726624},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4449999928474426},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.4415999948978424},{"id":"https://openalex.org/C177769412","wikidata":"https://www.wikidata.org/wiki/Q278090","display_name":"Prior probability","level":3,"score":0.43639999628067017},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.4056999981403351},{"id":"https://openalex.org/C2780801425","wikidata":"https://www.wikidata.org/wiki/Q5164392","display_name":"Construct (python library)","level":2,"score":0.374099999666214},{"id":"https://openalex.org/C2776836416","wikidata":"https://www.wikidata.org/wiki/Q1364844","display_name":"False alarm","level":2,"score":0.3736000061035156},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.3668999969959259},{"id":"https://openalex.org/C61326573","wikidata":"https://www.wikidata.org/wiki/Q1496376","display_name":"Gaussian process","level":3,"score":0.350600004196167},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34850001335144043},{"id":"https://openalex.org/C169214877","wikidata":"https://www.wikidata.org/wiki/Q981016","display_name":"Dirichlet distribution","level":3,"score":0.3463999927043915},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34130001068115234},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33489999175071716},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.32850000262260437},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.3206999897956848},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.32010000944137573},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.31779998540878296},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.3140999972820282},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.3003999888896942},{"id":"https://openalex.org/C189950617","wikidata":"https://www.wikidata.org/wiki/Q937228","display_name":"Property (philosophy)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C19768560","wikidata":"https://www.wikidata.org/wiki/Q320727","display_name":"Dependency (UML)","level":2,"score":0.2906000018119812},{"id":"https://openalex.org/C61224824","wikidata":"https://www.wikidata.org/wiki/Q2260434","display_name":"Mixture model","level":2,"score":0.28139999508857727},{"id":"https://openalex.org/C42023084","wikidata":"https://www.wikidata.org/wiki/Q5249231","display_name":"Decision boundary","level":3,"score":0.26660001277923584},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.260699987411499},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.2583000063896179},{"id":"https://openalex.org/C52740198","wikidata":"https://www.wikidata.org/wiki/Q1539564","display_name":"Importance sampling","level":3,"score":0.2524999976158142},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.2506999969482422},{"id":"https://openalex.org/C189508267","wikidata":"https://www.wikidata.org/wiki/Q17088227","display_name":"Density estimation","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2601.22685","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22685","pdf_url":"https://arxiv.org/pdf/2601.22685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2601.22685","doi":"https://doi.org/10.48550/arxiv.2601.22685","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2601.22685","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2601.22685","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2601.22685","pdf_url":"https://arxiv.org/pdf/2601.22685","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7127087797.pdf","grobid_xml":"https://content.openalex.org/works/W7127087797.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7202342568","https://openalex.org/W7212075295","https://openalex.org/W4378768723","https://openalex.org/W4283819124","https://openalex.org/W4402351250","https://openalex.org/W7160335125","https://openalex.org/W4221167530","https://openalex.org/W4409263263","https://openalex.org/W7084503617","https://openalex.org/W6930730854"],"abstract_inverted_index":{"Zero-shot":[0],"out-of-vocabulary":[1],"detection":[2,225],"(ZS-OOVD)":[3],"aims":[4],"to":[5,34,40,86,129,149,163],"accurately":[6],"recognize":[7],"objects":[8],"of":[9,90,96,110,134,201],"in-vocabulary":[10],"(IV)":[11],"categories":[12],"provided":[13],"at":[14,234],"zero-shot":[15,64,82,228],"inference,":[16],"while":[17,76],"simultaneously":[18],"rejecting":[19,78],"undefined":[20,44,79],"ones":[21,50,80],"(out-of-vocabulary,":[22],"OOV)":[23],"that":[24,71,123,218],"lack":[25,89],"corresponding":[26],"category":[27],"prompts.":[28],"However,":[29],"previous":[30],"methods":[31],"are":[32,126,158,172],"prone":[33],"overfitting":[35],"the":[36,41,87,94,107,111,116,121,135,155,188,199,212,223],"IV":[37,49],"classes,":[38],"leading":[39],"OOV":[42,65,97,102,139,181,189,202,224],"or":[43],"classes":[45,75,203],"being":[46],"misclassified":[47],"as":[48,160,174],"with":[51,169,211],"a":[52,63,68,144,193],"high":[53,170],"confidence":[54],"score.":[55],"To":[56],"address":[57],"this":[58,60],"issue,":[59],"paper":[61],"proposes":[62],"detector":[66],"(OOVDet),":[67],"novel":[69],"framework":[70],"effectively":[72],"detects":[73],"predefined":[74],"reliably":[77],"in":[81,115,131,209,227],"scenes.":[83,229],"Specifically,":[84],"due":[85],"model's":[88],"prior":[91,195],"knowledge":[92],"about":[93],"distribution":[95],"data,":[98],"we":[99,141,186],"synthesize":[100],"region-level":[101],"prompts":[103,182],"by":[104,120],"sampling":[105],"from":[106],"low-likelihood":[108],"regions":[109],"class-conditional":[112],"Gaussian":[113,205],"distributions":[114],"hidden":[117],"space,":[118],"motivated":[119],"assumption":[122],"unknown":[124],"semantics":[125],"more":[127],"likely":[128],"emerge":[130],"low-density":[132,194],"areas":[133],"latent":[136],"space.":[137],"For":[138],"images,":[140,185],"further":[142],"propose":[143],"Dirichlet-based":[145],"gradient":[146],"attribution":[147,156],"mechanism":[148],"mine":[150],"pseudo-OOV":[151,175,184],"image":[152],"samples,":[153],"where":[154],"gradients":[157],"interpreted":[159],"Dirichlet":[161],"evidence":[162],"estimate":[164],"prediction":[165],"uncertainty,":[166],"and":[167,183],"samples":[168],"uncertainty":[171],"selected":[173],"images.":[176],"Building":[177],"on":[178],"these":[179],"synthesized":[180],"construct":[187],"decision":[190],"boundary":[191],"through":[192],"constraint,":[196],"which":[197],"regularizes":[198],"optimization":[200],"using":[204],"kernel":[206],"density":[207],"estimation":[208],"accordance":[210],"above":[213],"assumption.":[214],"Experimental":[215],"results":[216],"show":[217],"our":[219],"method":[220],"significantly":[221],"improves":[222],"performance":[226],"The":[230],"code":[231],"is":[232],"available":[233],"https://github.com/binyisu/OOV-detector.":[235]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2026-02-03T00:00:00"}