{"id":"https://openalex.org/W7165655452","doi":"https://doi.org/10.48550/arxiv.2606.22537","title":"NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models","display_name":"NegAS: Negative Label Guided Attention and Scoring for Out-of-Distribution Object Detection with Vision-Language Models","publication_year":2026,"publication_date":"2026-06-21","ids":{"openalex":"https://openalex.org/W7165655452","doi":"https://doi.org/10.48550/arxiv.2606.22537"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2606.22537","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22537","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":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2606.22537","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5139169324","display_name":"Yingjie Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Yingjie","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5139206848","display_name":"Shuai Li","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Li, Shuai","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5139157352","display_name":"Peng Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Peng","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":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":0.54339998960495,"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":0.54339998960495,"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":0.1851000040769577,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.11670000106096268,"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/object-detection","display_name":"Object detection","score":0.7542999982833862},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.710099995136261},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.6406000256538391},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.6083999872207642},{"id":"https://openalex.org/keywords/margin","display_name":"Margin (machine learning)","score":0.4726000130176544},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.4661000072956085},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4036000072956085}],"concepts":[{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7542999982833862},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7246999740600586},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.710099995136261},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6607000231742859},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.6406000256538391},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.4726000130176544},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.46630001068115234},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4661000072956085},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4036000072956085},{"id":"https://openalex.org/C43214815","wikidata":"https://www.wikidata.org/wiki/Q7310987","display_name":"Reliability (semiconductor)","level":3,"score":0.3817000091075897},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3255999982357025},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2930000126361847},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.26460000872612},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.26080000400543213},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.2565000057220459},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2563999891281128}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2606.22537","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22537","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":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2606.22537","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2606.22537","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":"Preprint"},"sustainable_development_goals":[{"score":0.41699498891830444,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Out-of-Distribution":[0],"(OOD)":[1],"detection":[2,13,57,193],"is":[3],"essential":[4],"for":[5,87,107,176,182,227],"ensuring":[6],"the":[7,34,50,205,210,216,221,249],"robustness":[8],"and":[9,94,122,170,179,213,244],"reliability":[10],"of":[11,36,251],"object":[12,38,56],"systems":[14],"deployed":[15],"in":[16,40],"safety-critical":[17],"applications.":[18],"While":[19,224],"prior":[20],"research":[21],"has":[22],"mainly":[23],"focused":[24],"on":[25,209,215],"uni-modal":[26],"detectors":[27,39,230],"or":[28],"vision-language":[29],"model":[30],"(VLM)":[31],"based":[32],"classifiers,":[33],"potential":[35,83,150],"VLM-based":[37],"OOD":[41,55,84,92,104,151,162,183,192],"scenarios":[42],"remains":[43],"underexplored.":[44],"In":[45],"this":[46],"work,":[47],"we":[48,116,128,157,233],"take":[49],"first":[51],"step":[52],"toward":[53,149],"building":[54],"methods":[58],"upon":[59],"VLMs.":[60],"We":[61],"identify":[62],"two":[63],"challenges":[64],"specific":[65],"to":[66,146,220,237],"VLM":[67,112,229,242],"detectors:":[68],"(i)":[69],"their":[70,96],"text-guided":[71],"attention":[72,134,148],"enhances":[73],"foreground":[74],"with":[75,102,111],"ID":[76,169,177,201],"labels":[77,143],"but":[78,140],"treats":[79],"background":[80,152],"uniformly,":[81],"leaving":[82],"regions":[85],"unexploited":[86],"separating":[88],"in-distribution":[89],"(ID)":[90],"from":[91],"instances;":[93],"(ii)":[95],"sigmoid-based":[97,161],"multi-label":[98],"outputs":[99],"are":[100,144],"incompatible":[101],"softmax-based":[103],"scores,":[105],"calling":[106],"scoring":[108,163],"functions":[109],"consistent":[110],"probabilistic":[113],"outputs.":[114],"Hence,":[115],"introduce":[117,158],"Negative":[118],"Label":[119],"Guided":[120],"Attention":[121],"Scoring":[123],"(NegAS).":[124],"To":[125,154],"address":[126,155],"(i),":[127],"propose":[129],"a":[130,159,196,240],"negative":[131,142,171],"label":[132],"guided":[133],"module":[135],"(NegA),":[136],"where":[137],"LLM-generated,":[138],"visually-similar":[139],"semantically-different":[141],"used":[145],"guide":[147],"regions.":[153],"(ii),":[156],"novel":[160],"function":[164],"(NegS)":[165],"that":[166,188],"leverages":[167],"both":[168],"labels,":[172],"producing":[173],"strong":[174],"responses":[175,181],"instances":[178],"suppressed":[180],"ones.":[184],"Extensive":[185],"experiments":[186],"demonstrate":[187],"our":[189,252],"approach":[190],"improves":[191],"performance":[194],"by":[195,207],"large":[197],"margin":[198],"while":[199],"maintaining":[200],"accuracy,":[202],"e.g.,":[203],"reducing":[204],"FPR95":[206],"11.4%":[208],"COCO":[211],"dataset":[212,218],"25.5%":[214],"OpenImages":[217],"compared":[219],"baseline":[222],"model.":[223],"initially":[225],"designed":[226],"dense":[228],"like":[231],"YOLO-World,":[232],"successfully":[234],"adapt":[235],"NegAS":[236],"Grounding":[238],"DINO,":[239],"query-based":[241],"transformer":[243],"achieve":[245],"significant":[246],"improvements,":[247],"demonstrating":[248],"generalizability":[250],"framework.":[253]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-06-24T00:00:00"}