{"id":"https://openalex.org/W4405785054","doi":"https://doi.org/10.1109/iros58592.2024.10802460","title":"Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection","display_name":"Cross-Architecture Auxiliary Feature Space Translation for Efficient Few-Shot Personalized Object Detection","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785054","doi":"https://doi.org/10.1109/iros58592.2024.10802460"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10802460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068387663","display_name":"Francesco Barbato","orcid":"https://orcid.org/0000-0001-9893-5813"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Francesco Barbato","raw_affiliation_strings":["Communications House,Samsung R&D Institute UK (SRUK),Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Communications House,Samsung R&D Institute UK (SRUK),Surrey,United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075734012","display_name":"Umberto Michieli","orcid":"https://orcid.org/0000-0003-2666-4342"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Umberto Michieli","raw_affiliation_strings":["Communications House,Samsung R&D Institute UK (SRUK),Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Communications House,Samsung R&D Institute UK (SRUK),Surrey,United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072414837","display_name":"Jijoong Moon","orcid":"https://orcid.org/0000-0003-0888-2143"},"institutions":[{"id":"https://openalex.org/I2250650973","display_name":"Samsung (South Korea)","ror":"https://ror.org/04w3jy968","country_code":"KR","type":"company","lineage":["https://openalex.org/I2250650973"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jijoong Moon","raw_affiliation_strings":["Seoul R&D Campus,Samsung Research Korea,Seoul,Rep. of Korea"],"affiliations":[{"raw_affiliation_string":"Seoul R&D Campus,Samsung Research Korea,Seoul,Rep. of Korea","institution_ids":["https://openalex.org/I2250650973"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070777118","display_name":"Pietro Zanuttigh","orcid":"https://orcid.org/0000-0002-9502-2389"},"institutions":[{"id":"https://openalex.org/I138689650","display_name":"University of Padua","ror":"https://ror.org/00240q980","country_code":"IT","type":"education","lineage":["https://openalex.org/I138689650"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Pietro Zanuttigh","raw_affiliation_strings":["University of Padova,Padova,Italy,35131"],"affiliations":[{"raw_affiliation_string":"University of Padova,Padova,Italy,35131","institution_ids":["https://openalex.org/I138689650"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5054882290","display_name":"Mete \u00d6zay","orcid":"https://orcid.org/0000-0002-7189-7260"},"institutions":[{"id":"https://openalex.org/I4210117523","display_name":"Samsung (United Kingdom)","ror":"https://ror.org/01w6gjq94","country_code":"GB","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210117523"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Mete Ozay","raw_affiliation_strings":["Communications House,Samsung R&D Institute UK (SRUK),Surrey,United Kingdom"],"affiliations":[{"raw_affiliation_string":"Communications House,Samsung R&D Institute UK (SRUK),Surrey,United Kingdom","institution_ids":["https://openalex.org/I4210117523"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5068387663"],"corresponding_institution_ids":["https://openalex.org/I4210117523"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.24958272,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"8587","last_page":"8594"},"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":0.9951000213623047,"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":0.9951000213623047,"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":0.9817000031471252,"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":0.9739000201225281,"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/computer-science","display_name":"Computer science","score":0.7535635232925415},{"id":"https://openalex.org/keywords/translation","display_name":"Translation (biology)","score":0.6708053946495056},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.576731264591217},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5711619257926941},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5703117251396179},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5251407623291016},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48910313844680786},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4744223952293396},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4204557538032532},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.31704992055892944}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7535635232925415},{"id":"https://openalex.org/C149364088","wikidata":"https://www.wikidata.org/wiki/Q185917","display_name":"Translation (biology)","level":4,"score":0.6708053946495056},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.576731264591217},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5711619257926941},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5703117251396179},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5251407623291016},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48910313844680786},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4744223952293396},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4204557538032532},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.31704992055892944},{"id":"https://openalex.org/C153349607","wikidata":"https://www.wikidata.org/wiki/Q36649","display_name":"Visual arts","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C105580179","wikidata":"https://www.wikidata.org/wiki/Q188928","display_name":"Messenger RNA","level":3,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/iros58592.2024.10802460","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10802460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4699999988079071,"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":45,"referenced_works":["https://openalex.org/W2133774033","https://openalex.org/W2168334281","https://openalex.org/W2917626743","https://openalex.org/W2966861238","https://openalex.org/W3035163969","https://openalex.org/W3047235076","https://openalex.org/W3065974826","https://openalex.org/W3094502228","https://openalex.org/W3114632476","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3159481202","https://openalex.org/W4214700015","https://openalex.org/W4220846750","https://openalex.org/W4287879563","https://openalex.org/W4288083516","https://openalex.org/W4312398779","https://openalex.org/W4372346764","https://openalex.org/W4387968076","https://openalex.org/W4389665586","https://openalex.org/W4389665851","https://openalex.org/W4390874575","https://openalex.org/W4392904247","https://openalex.org/W6624454233","https://openalex.org/W6631190155","https://openalex.org/W6637551013","https://openalex.org/W6639102338","https://openalex.org/W6691473716","https://openalex.org/W6735236233","https://openalex.org/W6737377802","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6766723483","https://openalex.org/W6770404601","https://openalex.org/W6780205758","https://openalex.org/W6785174661","https://openalex.org/W6791353385","https://openalex.org/W6839461871","https://openalex.org/W6851800889","https://openalex.org/W6852107595","https://openalex.org/W6852612167","https://openalex.org/W6852694211","https://openalex.org/W6855097393","https://openalex.org/W6857692509","https://openalex.org/W6870574882"],"related_works":["https://openalex.org/W2588198209","https://openalex.org/W1909006023","https://openalex.org/W4205824991","https://openalex.org/W3147584709","https://openalex.org/W3200723557","https://openalex.org/W2737719445","https://openalex.org/W4312713546","https://openalex.org/W2362195430","https://openalex.org/W4292830139","https://openalex.org/W4319309705"],"abstract_inverted_index":{"Recent":[0],"years":[1],"have":[2],"seen":[3],"object":[4,130],"detection":[5],"robotic":[6],"systems":[7],"deployed":[8],"in":[9,23,70,196],"several":[10],"personal":[11],"devices":[12],"(e.g.,":[13,41,165],"home":[14],"robots":[15],"and":[16,38,68,184,223],"appliances).":[17],"This":[18],"has":[19],"highlighted":[20],"a":[21,42,71,108,116,149,162,206],"challenge":[22],"their":[24,31,90],"design,":[25],"i.e.,":[26],"they":[27],"cannot":[28],"efficiently":[29],"update":[30],"knowledge":[32],"to":[33,49,121,139,143],"distinguish":[34],"between":[35],"general":[36],"classes":[37],"user-specific":[39],"instances":[40],"dog":[43],"vs.":[44],"user\u2019s":[45],"dog).":[46],"We":[47,114,176],"refer":[48],"this":[50],"challenging":[51],"task":[52,61],"as":[53],"Instance-level":[54],"Personalized":[55],"Object":[56],"Detection":[57],"(IPOD).":[58],"The":[59],"personalization":[60,141],"requires":[62],"many":[63],"samples":[64],"for":[65,189],"model":[66,137,164,227],"tuning":[67],"optimization":[69],"centralized":[72],"server,":[73],"raising":[74],"privacy":[75],"concerns.":[76],"An":[77],"alternative":[78],"is":[79],"provided":[80],"by":[81,127,161],"approaches":[82],"based":[83],"on":[84,179],"recent":[85],"large-scale":[86],"Foundation":[87],"Models,":[88],"but":[89],"compute":[91],"costs":[92],"preclude":[93],"on-device":[94],"applications.":[95],"In":[96],"our":[97],"work":[98],"we":[99,147],"tackle":[100],"both":[101],"problems":[102],"at":[103,213],"the":[104,123,171,174,190,217,226],"same":[105],"time,":[106,219],"designing":[107],"Few-Shot":[109],"IPOD":[110,191],"strategy":[111],"called":[112],"AuXFT.":[113],"introduce":[115,148],"conditional":[117],"coarse-to-fine":[118],"few-shot":[119],"learner":[120],"refine":[122],"coarse":[124],"predictions":[125],"made":[126],"an":[128,135,154],"efficient":[129],"detector,":[131],"showing":[132],"that":[133,152],"using":[134],"off-the-shelf":[136],"leads":[138],"poor":[140],"due":[142],"neural":[144],"collapse.":[145],"Therefore,":[146],"Translator":[150],"block":[151],"generates":[153],"auxiliary":[155],"feature":[156],"space":[157],"where":[158],"features":[159],"generated":[160],"self-supervised":[163],"DINOv2)":[166],"are":[167],"distilled":[168],"without":[169],"impacting":[170],"performance":[172,207],"of":[173,208,216,221,225],"detector.":[175],"validate":[177],"AuXFT":[178,204],"three":[180],"publicly":[181],"available":[182],"datasets":[183],"one":[185],"in-house":[186],"benchmark":[187],"designed":[188],"task,":[192],"achieving":[193],"remarkable":[194],"gains":[195],"all":[197],"considered":[198],"scenarios":[199],"with":[200],"excellent":[201],"time-complexity":[202],"trade-off:":[203],"reaches":[205],"80%":[209],"its":[210],"upper":[211],"bound":[212],"just":[214],"32%":[215],"inference":[218],"13%":[220],"VRAM":[222],"19%":[224],"size.":[228]},"counts_by_year":[],"updated_date":"2025-12-27T23:08:20.325037","created_date":"2025-10-10T00:00:00"}