{"id":"https://openalex.org/W7169796341","doi":"https://doi.org/10.48550/arxiv.2607.15563","title":"Are All Tokens Necessary for Visual Place Recognition? An Empirical Study of Token Reduction for Efficient Inference","display_name":"Are All Tokens Necessary for Visual Place Recognition? An Empirical Study of Token Reduction for Efficient Inference","publication_year":2026,"publication_date":"2026-07-17","ids":{"openalex":"https://openalex.org/W7169796341","doi":"https://doi.org/10.48550/arxiv.2607.15563"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2607.15563","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15563","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,"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.2607.15563","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136777771","display_name":"T Jin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jin, Tong","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141203975","display_name":"Yunpeng Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Yunpeng","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5105753106","display_name":"Hu S","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hu, Shuyu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141182458","display_name":"Qinghua Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Qinghua","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141192513","display_name":"Ruize Han","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Han, Ruize","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5141194489","display_name":"Song Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wang, Song","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5141212676","display_name":"Feng Lu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Feng","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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.37139999866485596,"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":0.37139999866485596,"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":0.29339998960494995,"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":0.08380000293254852,"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/security-token","display_name":"Security token","score":0.8098999857902527},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.8027999997138977},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7437999844551086},{"id":"https://openalex.org/keywords/reduction","display_name":"Reduction (mathematics)","score":0.6521999835968018},{"id":"https://openalex.org/keywords/software-deployment","display_name":"Software deployment","score":0.5479999780654907},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5001000165939331},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41179999709129333}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8098999857902527},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.8027999997138977},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7986000180244446},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7437999844551086},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.6521999835968018},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5489000082015991},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.5479999780654907},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5001000165939331},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45719999074935913},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41179999709129333},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3871000111103058},{"id":"https://openalex.org/C120936955","wikidata":"https://www.wikidata.org/wiki/Q2155640","display_name":"Empirical research","level":2,"score":0.3855000138282776},{"id":"https://openalex.org/C66024118","wikidata":"https://www.wikidata.org/wiki/Q1122506","display_name":"Computational model","level":2,"score":0.35600000619888306},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.3172999918460846},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30809998512268066},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.2946999967098236},{"id":"https://openalex.org/C115067241","wikidata":"https://www.wikidata.org/wiki/Q1639854","display_name":"Token passing","level":3,"score":0.2937000095844269},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.2531999945640564}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2607.15563","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15563","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,"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.2607.15563","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2607.15563","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,"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":[{"display_name":"Sustainable cities and communities","score":0.4019327461719513,"id":"https://metadata.un.org/sdg/11"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Recent":[0],"visual":[1,23,50,70,201],"place":[2,71],"recognition":[3,16,110,184],"(VPR)":[4],"methods":[5,85],"based":[6],"on":[7,125,196],"vision":[8],"transformers,":[9],"particularly":[10],"foundation":[11,192],"models,":[12],"have":[13],"achieved":[14],"remarkable":[15],"performance.":[17],"However,":[18],"these":[19],"models":[20,90,207],"process":[21],"all":[22,49],"tokens":[24,51],"throughout":[25],"the":[26,61,151],"entire":[27],"network,":[28],"resulting":[29],"in":[30,38,143,183],"substantial":[31],"computational":[32,116,164],"overhead,":[33],"which":[34],"hinders":[35],"their":[36],"deployment":[37,123],"real-time":[39],"and":[40,82,91,98,122,131,145,155,170,199,206],"resource-constrained":[41],"scenarios.":[42],"A":[43],"natural":[44,99],"question":[45],"thus":[46],"arises:":[47],"are":[48],"necessary":[52],"for":[53,68,193],"VPR?":[54],"To":[55],"answer":[56],"this":[57,187],"question,":[58],"we":[59],"present":[60],"first":[62],"systematic":[63],"benchmark":[64,74,93,135],"of":[65,140],"token":[66,78,80,104,141,160],"reduction":[67,105,114,142,161],"efficient":[69,200],"recognition.":[72],"Our":[73,204],"comprehensively":[75],"evaluates":[76],"representative":[77],"pruning,":[79],"merging,":[81],"hybrid":[83],"pruning-merging":[84],"across":[86],"multiple":[87,107,137],"state-of-the-art":[88],"VPR":[89,144,198],"diverse":[92],"datasets":[94],"covering":[95],"urban,":[96],"suburban,":[97],"environments.":[100],"We":[101],"further":[102],"investigate":[103],"from":[106],"perspectives,":[108],"including":[109],"performance":[111],"under":[112],"different":[113],"configurations,":[115],"complexity,":[117],"inference":[118,156],"speed,":[119],"qualitative":[120],"visualization,":[121],"efficiency":[124],"edge":[126],"devices.":[127],"Through":[128],"extensive":[129],"experiments":[130],"in-depth":[132],"analysis,":[133],"our":[134],"reveals":[136],"important":[138],"characteristics":[139],"provides":[146],"several":[147],"practical":[148],"insights":[149],"into":[150],"trade-offs":[152],"between":[153],"accuracy":[154],"efficiency.":[157],"For":[158],"example,":[159],"can":[162],"reduce":[163],"cost":[165],"by":[166,173],"up":[167,174],"to":[168,175],"29\\%":[169],"improve":[171],"throughput":[172],"44\\%,":[176],"while":[177],"incurring":[178],"less":[179],"than":[180],"1\\%":[181],"degradation":[182],"accuracy.":[185],"Overall,":[186],"work":[188],"establishes":[189],"a":[190],"comprehensive":[191],"future":[194],"research":[195],"token-efficient":[197],"retrieval":[202],"systems.":[203],"codes":[205],"will":[208],"be":[209],"available":[210],"at":[211],"https://github.com/Tong-Jin01/TokenReduction4VPR":[212]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2026-07-21T00:00:00"}