{"id":"https://openalex.org/W7138050693","doi":"https://doi.org/10.1609/aaai.v40i15.38303","title":"D\u00b2-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation","display_name":"D\u00b2-VPR: A Parameter-efficient Visual-foundation-model-based Visual Place Recognition Method via Knowledge Distillation and Deformable Aggregation","publication_year":2026,"publication_date":"2026-03-14","ids":{"openalex":"https://openalex.org/W7138050693","doi":"https://doi.org/10.1609/aaai.v40i15.38303"},"language":null,"primary_location":{"id":"doi:10.1609/aaai.v40i15.38303","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38303","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v40i15.38303","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5129690065","display_name":"Zheyuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Zheyuan Zhang","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129671879","display_name":"Jiwei Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiwei Zhang","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129712817","display_name":"Boyu Zhou","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Boyu Zhou","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129698038","display_name":"Linzhimeng Duan","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Linzhimeng Duan","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5129669578","display_name":"Hong Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong Chen","raw_affiliation_strings":["School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications"],"affiliations":[{"raw_affiliation_string":"School of Computer Science, Beijing University of Posts and Telecommunications\nKey Laboratory of Interactive Technology and Experience System, Ministry of Culture and Tourism, Beijing University of Posts and Telecommunications","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5129690065"],"corresponding_institution_ids":["https://openalex.org/I139759216"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.34328358,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"40","issue":"15","first_page":"13034","last_page":"13042"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7605999708175659,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.7605999708175659,"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":0.055399999022483826,"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/T10191","display_name":"Robotics and Sensor-Based Localization","score":0.053700000047683716,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6283000111579895},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5938000082969666},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5788999795913696},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5724999904632568},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5580999851226807},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5163000226020813},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.4361000061035156},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4235000014305115},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.42289999127388}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.791700005531311},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6283000111579895},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6029000282287598},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5938000082969666},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5788999795913696},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5724999904632568},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5580999851226807},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5163000226020813},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4415999948978424},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4235000014305115},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.42289999127388},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37540000677108765},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.34779998660087585},{"id":"https://openalex.org/C2776429412","wikidata":"https://www.wikidata.org/wiki/Q4688011","display_name":"Aerial image","level":3,"score":0.31679999828338623},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.30799999833106995},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.3001999855041504},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.295199990272522},{"id":"https://openalex.org/C2779757391","wikidata":"https://www.wikidata.org/wiki/Q6002292","display_name":"Image translation","level":3,"score":0.2865999937057495},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.28459998965263367},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C2781122975","wikidata":"https://www.wikidata.org/wiki/Q16928266","display_name":"Semantic feature","level":2,"score":0.2773999869823456},{"id":"https://openalex.org/C115901376","wikidata":"https://www.wikidata.org/wiki/Q184199","display_name":"Automation","level":2,"score":0.272599995136261},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.25699999928474426},{"id":"https://openalex.org/C180505990","wikidata":"https://www.wikidata.org/wiki/Q498267","display_name":"News aggregator","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1609/aaai.v40i15.38303","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38303","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1609/aaai.v40i15.38303","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v40i15.38303","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-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":{"Visual":[0],"Place":[1],"Recognition":[2],"(VPR)":[3],"aims":[4],"to":[5,132,149,167,183,196,209],"determine":[6],"the":[7,27,30,89,135,139,150,172,202],"geographic":[8],"location":[9],"of":[10,29,94,174],"a":[11,22,38,82,105,114,127,157],"query":[12],"image":[13],"by":[14,62,205],"retrieving":[15],"its":[16],"most":[17],"visually":[18],"similar":[19],"counterpart":[20],"from":[21,52],"geo-tagged":[23],"reference":[24],"database.":[25],"Recently,":[26],"emergence":[28],"powerful":[31],"visual":[32,95],"foundation":[33,96],"model,":[34],"DINOv2,":[35],"trained":[36],"in":[37],"self-supervised":[39],"manner":[40],"on":[41,72],"massive":[42],"datasets,":[43],"has":[44],"significantly":[45,99],"improved":[46],"VPR":[47],"performance.":[48],"This":[49],"improvement":[50],"stems":[51],"DINOv2\u2019s":[53],"exceptional":[54],"feature":[55,91,136],"generalization":[56],"capabilities":[57,93],"but":[58],"is":[59],"often":[60],"accompanied":[61],"increased":[63],"model":[64,101],"complexity":[65],"and":[66,84,103,122,141,169],"computational":[67],"overhead":[68],"that":[69,87,118,162,189],"impede":[70],"deployment":[71],"resource-constrained":[73],"devices.":[74],"To":[75],"address":[76],"this":[77],"challenge,":[78],"we":[79,112,125,155],"propose":[80],"D2-VPR,":[81],"Distillation-":[83],"Deformable-based":[85],"framework":[86],"retains":[88],"strong":[90],"extraction":[92],"models":[97],"while":[98],"reducing":[100],"parameters":[102],"achieving":[104],"more":[106],"favorable":[107],"performance-efficiency":[108],"trade-off.":[109],"Specifically,":[110],"first,":[111],"employ":[113],"two-stage":[115],"training":[116],"strategy":[117],"integrates":[119],"knowledge":[120,146],"distillation":[121],"fine-tuning.":[123],"Additionally,":[124],"introduce":[126],"Distillation":[128],"Recovery":[129],"Module":[130],"(DRM)":[131],"better":[133],"align":[134],"spaces":[137],"between":[138],"teacher":[140],"student":[142],"models,":[143],"thereby":[144,180],"minimizing":[145],"transfer":[147],"losses":[148],"greatest":[151],"extent":[152],"possible.":[153],"Second,":[154],"design":[156],"Top-Down-attention-based":[158],"Deformable":[159],"Aggregator":[160],"(TDDA)":[161],"leverages":[163],"global":[164],"semantic":[165],"features":[166],"dynamically":[168],"adaptively":[170],"adjust":[171],"Regions":[173],"Interest":[175],"(ROI)":[176],"used":[177],"for":[178],"aggregation,":[179],"improving":[181],"adaptability":[182],"irregular":[184],"structures.":[185],"Extensive":[186],"experiments":[187],"demonstrate":[188],"our":[190],"method":[191],"achieves":[192],"competitive":[193],"performance":[194],"compared":[195],"state-of-the-art":[197],"approaches.":[198],"Meanwhile,":[199],"it":[200],"reduces":[201],"parameter":[203],"count":[204],"approximately":[206],"64.2%":[207],"(compared":[208],"CricaVPR).":[210]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-18T00:00:00"}