{"id":"https://openalex.org/W7153294289","doi":"https://doi.org/10.48550/arxiv.2604.08461","title":"OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance","display_name":"OVS-DINO: Open-Vocabulary Segmentation via Structure-Aligned SAM-DINO with Language Guidance","publication_year":2026,"publication_date":"2026-04-09","ids":{"openalex":"https://openalex.org/W7153294289","doi":"https://doi.org/10.48550/arxiv.2604.08461"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2604.08461","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08461","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.2604.08461","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5120711405","display_name":"Haoxi Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Haoxi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133333829","display_name":"Qiankun Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Qiankun","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024408423","display_name":"Yi Bin","orcid":"https://orcid.org/0000-0001-9714-8738"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bin, Yi","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133355629","display_name":"Haiyue Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Haiyue","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133388308","display_name":"Yujuan Ding","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ding, Yujuan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5133368071","display_name":"Guoqing Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Guoqing","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065413088","display_name":"Deqiang Ouyang","orcid":"https://orcid.org/0000-0003-2259-886X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ouyang, Deqiang","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5133379120","display_name":"Heng Tao Shen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shen, Heng Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":8,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.7276999950408936,"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":0.7276999950408936,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.06260000169277191,"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":0.04830000177025795,"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/segmentation","display_name":"Segmentation","score":0.7591999769210815},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6302000284194946},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4959000051021576},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.4377000033855438},{"id":"https://openalex.org/keywords/fidelity","display_name":"Fidelity","score":0.4099999964237213},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.3833000063896179},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.33230000734329224},{"id":"https://openalex.org/keywords/high-fidelity","display_name":"High fidelity","score":0.3310999870300293}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.760200023651123},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7591999769210815},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6302000284194946},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6108999848365784},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4959000051021576},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4803999960422516},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.4377000033855438},{"id":"https://openalex.org/C2776459999","wikidata":"https://www.wikidata.org/wiki/Q2119376","display_name":"Fidelity","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.3833000063896179},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3441999852657318},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33230000734329224},{"id":"https://openalex.org/C113364801","wikidata":"https://www.wikidata.org/wiki/Q26674","display_name":"High fidelity","level":2,"score":0.3310999870300293},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3262999951839447},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.32339999079704285},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.3176000118255615},{"id":"https://openalex.org/C2983448237","wikidata":"https://www.wikidata.org/wiki/Q1078276","display_name":"Language understanding","level":2,"score":0.31439998745918274},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3052000105381012},{"id":"https://openalex.org/C62354387","wikidata":"https://www.wikidata.org/wiki/Q875399","display_name":"Boundary (topology)","level":2,"score":0.2874999940395355},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.2646999955177307},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2574000060558319},{"id":"https://openalex.org/C194232998","wikidata":"https://www.wikidata.org/wiki/Q1606712","display_name":"Transition (genetics)","level":3,"score":0.2502000033855438}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2604.08461","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08461","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.2604.08461","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.08461","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":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5483182072639465}],"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],"Segmentation":[1],"(OVS)":[2],"aims":[3],"to":[4,45,131,173,195],"segment":[5],"image":[6],"regions":[7],"beyond":[8],"predefined":[9],"category":[10],"sets":[11],"by":[12,143,169],"leveraging":[13],"semantic":[14,22],"descriptions.":[15],"While":[16],"CLIP":[17],"based":[18],"approaches":[19],"excel":[20],"in":[21,182],"generalization,":[23],"they":[24],"frequently":[25],"lack":[26],"the":[27,55,114,166],"fine-grained":[28],"spatial":[29],"awareness":[30,79],"required":[31],"for":[32,60],"dense":[33],"prediction.":[34],"Recent":[35],"efforts":[36],"have":[37],"incorporated":[38],"Vision":[39],"Foundation":[40],"Models":[41],"(VFMs)":[42],"like":[43],"DINO":[44,72,109,137],"alleviate":[46],"these":[47,50],"limitations.":[48],"However,":[49],"methods":[51],"still":[52],"struggle":[53],"with":[54,113,186],"precise":[56],"edge":[57],"perception":[58],"necessary":[59],"high":[61],"fidelity":[62],"segmentation.":[63],"In":[64],"this":[65],"paper,":[66],"we":[67,98,120],"analyze":[68],"internal":[69],"representations":[70],"of":[71,108,136,189],"and":[73,126],"discover":[74],"that":[75,104,154],"its":[76],"inherent":[77],"boundary":[78,134],"is":[80],"not":[81],"absent":[82],"but":[83],"rather":[84],"undergoes":[85],"progressive":[86],"attenuation":[87],"as":[88],"features":[89,135],"transition":[90],"into":[91],"deeper":[92],"transformer":[93],"blocks.":[94],"To":[95],"address":[96],"this,":[97],"propose":[99],"OVS-DINO,":[100],"a":[101,122,127,144,187],"novel":[102],"framework":[103],"revitalizes":[105],"latent":[106],"edge-sensitivity":[107],"through":[110],"structural":[111,140],"alignment":[112],"Segment":[115],"Anything":[116],"Model":[117],"(SAM).":[118],"Specifically,":[119],"introduce":[121],"Structure-Aware":[123],"Encoder":[124],"(SAE)":[125],"Structure-Modulated":[128],"Decoder":[129],"(SMD)":[130],"effectively":[132],"activate":[133],"using":[138],"SAM's":[139],"priors,":[141],"complemented":[142],"supervision":[145],"strategy":[146],"utilizing":[147],"SAM":[148],"generated":[149],"pseudo-masks.":[150],"Extensive":[151],"experiments":[152],"demonstrate":[153],"our":[155,176],"method":[156],"achieves":[157],"state-of-the-art":[158],"performance":[159],"across":[160],"multiple":[161],"weakly-supervised":[162],"OVS":[163],"benchmarks,":[164],"improving":[165],"average":[167],"score":[168],"2.1%":[170],"(from":[171,193],"44.8%":[172],"46.9%).":[174],"Notably,":[175],"approach":[177],"significantly":[178],"enhances":[179],"segmentation":[180],"accuracy":[181],"complex,":[183],"cluttered":[184],"scenarios,":[185],"gain":[188],"6.3%":[190],"on":[191],"Cityscapes":[192],"36.6%":[194],"42.9%).":[196]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-04-11T00:00:00"}