{"id":"https://openalex.org/W4414880268","doi":"https://doi.org/10.1109/iccv51701.2025.01938","title":"Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-Time Open-Vocabulary Object Detection","display_name":"Dynamic-DINO: Fine-Grained Mixture of Experts Tuning for Real-Time Open-Vocabulary Object Detection","publication_year":2025,"publication_date":"2025-10-19","ids":{"openalex":"https://openalex.org/W4414880268","doi":"https://doi.org/10.1109/iccv51701.2025.01938"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51701.2025.01938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2507.17436","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5113394962","display_name":"Yehao Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yehao Lu","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Minghe Weng","orcid":null},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Minghe Weng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zekang Xiao","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zekang Xiao","raw_affiliation_strings":["Polytechnic Institute, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic Institute, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014743973","display_name":"Rui Jiang","orcid":"https://orcid.org/0000-0001-7398-3851"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Jiang","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110727415","display_name":"Su Wei","orcid":"https://orcid.org/0009-0000-1417-7884"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Su","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088316957","display_name":"Guangcong Zheng","orcid":"https://orcid.org/0000-0002-9943-1577"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Guangcong Zheng","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031784349","display_name":"Ping Lu","orcid":"https://orcid.org/0000-0002-5802-7316"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ping Lu","raw_affiliation_strings":["ZTE"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"ZTE","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100407758","display_name":"Xi Li","orcid":"https://orcid.org/0000-0003-3023-1662"},"institutions":[{"id":"https://openalex.org/I168879160","display_name":"Zhejiang University of Science and Technology","ror":"https://ror.org/05mx0wr29","country_code":"CN","type":"education","lineage":["https://openalex.org/I168879160"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xi Li","raw_affiliation_strings":["College of Computer Science and Technology, Zhejiang University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Zhejiang University","institution_ids":["https://openalex.org/I168879160"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"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":"20847","last_page":"20856"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9853000044822693,"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"}},"topics":[{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.9853000044822693,"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/T10028","display_name":"Topic Modeling","score":0.9656999707221985,"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/T12031","display_name":"Speech and dialogue systems","score":0.9361000061035156,"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/leverage","display_name":"Leverage (statistics)","score":0.7508000135421753},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6467999815940857},{"id":"https://openalex.org/keywords/granularity","display_name":"Granularity","score":0.5166000127792358},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4560999870300293},{"id":"https://openalex.org/keywords/router","display_name":"Router","score":0.44179999828338623},{"id":"https://openalex.org/keywords/expert-system","display_name":"Expert system","score":0.4334000051021576},{"id":"https://openalex.org/keywords/subnet","display_name":"Subnet","score":0.40630000829696655},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.3598000109195709},{"id":"https://openalex.org/keywords/knowledge-base","display_name":"Knowledge base","score":0.35830000042915344}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.7508000135421753},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188000082969666},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6467999815940857},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5591999888420105},{"id":"https://openalex.org/C177774035","wikidata":"https://www.wikidata.org/wiki/Q1246948","display_name":"Granularity","level":2,"score":0.5166000127792358},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4560999870300293},{"id":"https://openalex.org/C2775896111","wikidata":"https://www.wikidata.org/wiki/Q642560","display_name":"Router","level":2,"score":0.44179999828338623},{"id":"https://openalex.org/C58328972","wikidata":"https://www.wikidata.org/wiki/Q184609","display_name":"Expert system","level":2,"score":0.4334000051021576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4219000041484833},{"id":"https://openalex.org/C21099817","wikidata":"https://www.wikidata.org/wiki/Q7631721","display_name":"Subnet","level":2,"score":0.40630000829696655},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3610000014305115},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.3598000109195709},{"id":"https://openalex.org/C4554734","wikidata":"https://www.wikidata.org/wiki/Q593744","display_name":"Knowledge base","level":2,"score":0.35830000042915344},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.3377000093460083},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.33480000495910645},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.32440000772476196},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.32170000672340393},{"id":"https://openalex.org/C21782646","wikidata":"https://www.wikidata.org/wiki/Q841666","display_name":"Search cost","level":2,"score":0.319599986076355},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3156000077724457},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.3059000074863434},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.29649999737739563},{"id":"https://openalex.org/C168993435","wikidata":"https://www.wikidata.org/wiki/Q6501125","display_name":"Ground","level":2,"score":0.2897999882698059},{"id":"https://openalex.org/C42058472","wikidata":"https://www.wikidata.org/wiki/Q810214","display_name":"Base (topology)","level":2,"score":0.28610000014305115},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.25290000438690186},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.2502000033855438}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51701.2025.01938","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51701.2025.01938","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2507.17436","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17436","pdf_url":"https://arxiv.org/pdf/2507.17436","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2507.17436","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2507.17436","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2507.17436","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2507.17436","pdf_url":"https://arxiv.org/pdf/2507.17436","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"The":[0],"Mixture":[1],"of":[2,119,139],"Experts":[3],"(MoE)":[4],"architecture":[5],"has":[6],"excelled":[7],"in":[8,16,57,78],"Large":[9],"Vision-Language":[10],"Models":[11],"(LVLMs),":[12],"yet":[13],"its":[14],"potential":[15],"real-time":[17],"open-vocabulary":[18],"object":[19],"detectors,":[20],"which":[21,86],"also":[22],"leverage":[23],"large-scale":[24],"vision-language":[25],"datasets":[26],"but":[27],"smaller":[28,124],"models,":[29],"remains":[30],"unexplored.":[31],"This":[32],"work":[33],"investigates":[34],"this":[35],"domain,":[36],"revealing":[37],"intriguing":[38],"insights.":[39],"In":[40],"the":[41,53,58,115,128,137,150,161,188],"shallow":[42],"layers,":[43,60],"experts":[44,163],"tend":[45],"to":[46,51,96,113,166],"cooperate":[47],"with":[48,153,175],"diverse":[49],"peers":[50],"expand":[52],"search":[54,130],"space.":[55,131],"While":[56],"deeper":[59],"fixed":[61,70],"collaborative":[62],"structures":[63],"emerge,":[64],"where":[65],"each":[66],"expert":[67,74,125],"maintains":[68],"2-3":[69],"partners":[71],"and":[72],"distinct":[73],"combinations":[75],"are":[76,164],"specialized":[77],"processing":[79],"specific":[80,155],"patterns.":[81],"Concretely,":[82],"we":[83,107,141],"propose":[84,143],"Dynamic-DINO,":[85],"extends":[87],"Grounding":[88,182],"DINO":[89,183],"1.5":[90,184],"Edge":[91],"from":[92],"a":[93,97,109,144,154,168],"dense":[94],"model":[95,121],"dynamic":[98],"inference":[99],"framework":[100],"via":[101],"an":[102],"efficient":[103],"MoE-Tuning":[104],"strategy.":[105],"Additionally,":[106],"design":[108],"granularity":[110],"decomposition":[111],"mechanism":[112],"decompose":[114],"Feed-Forward":[116],"Network":[117],"(FFN)":[118],"base":[120],"into":[122],"multiple":[123],"networks,":[126],"expanding":[127],"subnet":[129],"To":[132],"prevent":[133],"performance":[134],"degradation":[135],"at":[136],"start":[138],"fine-tuning,":[140],"further":[142],"pre-trained":[145],"weight":[146],"allocation":[147],"strategy":[148],"for":[149],"experts,":[151],"coupled":[152],"router":[156],"initialization.":[157],"During":[158],"inference,":[159],"only":[160],"input-relevant":[162],"activated":[165],"form":[167],"compact":[169],"subnet.":[170],"Experiments":[171],"show":[172],"that,":[173],"pretrained":[174,186],"merely":[176],"1.56M":[177],"open-source":[178],"data,":[179],"Dynamic-DINO":[180],"outperforms":[181],"Edge,":[185],"on":[187],"private":[189],"Grounding20M":[190],"dataset.":[191]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}