{"id":"https://openalex.org/W7162028740","doi":"https://doi.org/10.48550/arxiv.2605.20551","title":"Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning","display_name":"Faster or Stronger: Towards Flexible Visual Place Recognition via Weighted Aggregation and Token Pruning","publication_year":2026,"publication_date":"2026-05-19","ids":{"openalex":"https://openalex.org/W7162028740","doi":"https://doi.org/10.48550/arxiv.2605.20551"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.20551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20551","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.2605.20551","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5136626155","display_name":"Zichao Zeng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zeng, Zichao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136719458","display_name":"June Moh Goo","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Goo, June Moh","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136711682","display_name":"Junwei Zheng","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zheng, Junwei","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136631555","display_name":"Weijia Fan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Fan, Weijia","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136723585","display_name":"Jiaming Zhang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhang, Jiaming","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5136629571","display_name":"Rainer Stiefelhagen","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Stiefelhagen, Rainer","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5136647010","display_name":"Jan Boehm","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Boehm, Jan","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":0.7705000042915344,"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":0.7705000042915344,"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":0.07810000330209732,"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":0.0414000004529953,"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/security-token","display_name":"Security token","score":0.8515999913215637},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6134999990463257},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.5254999995231628},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5019999742507935},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.4968999922275543},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4587000012397766},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.4569999873638153},{"id":"https://openalex.org/keywords/token-passing","display_name":"Token passing","score":0.44769999384880066},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.4366999864578247}],"concepts":[{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.8515999913215637},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8253999948501587},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6134999990463257},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5676000118255615},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.5254999995231628},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5019999742507935},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.4968999922275543},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4587000012397766},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.4569999873638153},{"id":"https://openalex.org/C115067241","wikidata":"https://www.wikidata.org/wiki/Q1639854","display_name":"Token passing","level":3,"score":0.44769999384880066},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.4366999864578247},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.4239000082015991},{"id":"https://openalex.org/C102380595","wikidata":"https://www.wikidata.org/wiki/Q509598","display_name":"Susceptance","level":3,"score":0.37310001254081726},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.3637999892234802},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.34929999709129333},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.34790000319480896},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.3325999975204468},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.298799991607666},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.29739999771118164},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.28999999165534973},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.2888999879360199},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2881999909877777},{"id":"https://openalex.org/C2776650193","wikidata":"https://www.wikidata.org/wiki/Q264661","display_name":"Obstacle","level":2,"score":0.288100004196167},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.2721000015735626},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.271699994802475},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.2694000005722046},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.2531000077724457},{"id":"https://openalex.org/C1667742","wikidata":"https://www.wikidata.org/wiki/Q10927554","display_name":"Image retrieval","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.20551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20551","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.2605.20551","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.20551","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":[{"id":"https://metadata.un.org/sdg/10","score":0.7036843299865723,"display_name":"Reduced inequalities"}],"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":[5,10,32,39,83,99,171],"match":[6],"a":[7,18,50,113,149,166,181],"query":[8],"image":[9],"reference":[11],"images":[12],"of":[13,136],"the":[14,68,134,200],"same":[15],"place":[16],"in":[17],"large-scale":[19,117],"database.":[20],"Recent":[21],"state-of-the-art":[22],"methods":[23,59,212],"employ":[24],"Vision":[25],"Transformers":[26],"(ViTs)":[27],"as":[28],"backbone":[29],"foundation":[30],"models":[31],"extract":[33],"patch-level":[34],"features":[35],"that":[36,70,154],"are":[37,46],"robust":[38],"viewpoint,":[40],"illumination,":[41],"and":[42,80,119,196],"seasonal":[43],"variations,":[44],"which":[45,96],"then":[47],"aggregated":[48],"into":[49,64],"compact":[51],"global":[52,106,130],"descriptor":[53],"for":[54,116],"retrieval.":[55],"Most":[56],"existing":[57,209],"aggregation":[58],"uniformly":[60],"pool":[61],"patch":[62],"tokens":[63],"learned":[65],"clusters,":[66],"despite":[67],"fact":[69],"different":[71],"clusters":[72,100],"often":[73],"encode":[74],"distinct":[75],"spatial":[76],"or":[77],"semantic":[78],"patterns":[79],"contribute":[81],"unequally":[82],"VPR":[84],"performance.":[85],"To":[86],"address":[87],"this":[88],"limitation,":[89],"we":[90],"propose":[91],"Weighted":[92],"Aggregated":[93],"Descriptor":[94],"(WeiAD),":[95],"assigns":[97],"weights":[98],"during":[101],"aggregation,":[102],"producing":[103],"more":[104],"discriminative":[105],"representations.":[107],"Beyond":[108],"accuracy,":[109],"retrieval":[110],"latency":[111,127],"is":[112],"critical":[114],"concern":[115],"deployments":[118],"resource-constrained":[120],"edge":[121],"devices.":[122],"Prior":[123],"work":[124],"mainly":[125],"reduces":[126,155],"by":[128,142],"compressing":[129],"descriptors,":[131],"while":[132],"overlooking":[133],"cost":[135,158],"feature":[137,156],"extraction,":[138],"an":[139,172],"issue":[140],"exacerbated":[141],"ViT-based":[143],"backbones.":[144],"We":[145],"therefore":[146],"introduce":[147],"WeiToP,":[148],"VPR-oriented":[150],"token":[151,163,178,189,210],"pruning":[152,168,190,211],"framework":[153],"extraction":[157],"via":[159],"self-distillation,":[160],"where":[161],"aggregation-induced":[162],"importance":[164],"supervises":[165],"lightweight":[167],"module":[169],"attached":[170],"early":[173],"transformer":[174],"layer,":[175],"enabling":[176],"inference-time":[177],"pruning.":[179],"After":[180],"single":[182],"joint":[183],"training":[184],"phase,":[185],"WeiToP":[186,207],"enables":[187],"plug-and-play":[188],"at":[191],"inference":[192],"time,":[193],"allowing":[194],"flexible":[195],"on-demand":[197],"control":[198],"over":[199],"accuracy-efficiency":[201],"trade-off":[202],"without":[203],"additional":[204],"training.":[205],"Moreover,":[206],"outperforms":[208],"adapted":[213],"from":[214],"general":[215],"vision":[216],"tasks.":[217]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-22T00:00:00"}