{"id":"https://openalex.org/W4413945974","doi":"https://doi.org/10.1109/icra55743.2025.11127317","title":"A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space","display_name":"A Light-Weight Framework for Open-Set Object Detection with Decoupled Feature Alignment in Joint Space","publication_year":2025,"publication_date":"2025-05-19","ids":{"openalex":"https://openalex.org/W4413945974","doi":"https://doi.org/10.1109/icra55743.2025.11127317"},"language":"en","primary_location":{"id":"doi:10.1109/icra55743.2025.11127317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5046862439","display_name":"Yonghao He","orcid":"https://orcid.org/0000-0003-1465-5510"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yonghao He","raw_affiliation_strings":["D-Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D-Robotics","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050531685","display_name":"Hu Su","orcid":"https://orcid.org/0000-0002-0551-3193"},"institutions":[{"id":"https://openalex.org/I4210094879","display_name":"Shandong Institute of Automation","ror":"https://ror.org/00qdtba35","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210094879","https://openalex.org/I4210142748"]},{"id":"https://openalex.org/I4210112150","display_name":"Institute of Automation","ror":"https://ror.org/022c3hy66","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hu Su","raw_affiliation_strings":["Institute of Automation of Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institute of Automation of Chinese Academy of Sciences,State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS)","institution_ids":["https://openalex.org/I4210112150","https://openalex.org/I4210094879"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037255040","display_name":"Haiyong Yu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Haiyong Yu","raw_affiliation_strings":["D-Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D-Robotics","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100669592","display_name":"Cong Yang","orcid":"https://orcid.org/0000-0001-5933-0950"},"institutions":[{"id":"https://openalex.org/I185940356","display_name":"Soochow University","ror":"https://ror.org/05kvm7n82","country_code":"TW","type":"education","lineage":["https://openalex.org/I185940356"]},{"id":"https://openalex.org/I3923682","display_name":"Soochow University","ror":"https://ror.org/05t8y2r12","country_code":"CN","type":"education","lineage":["https://openalex.org/I3923682"]}],"countries":["CN","TW"],"is_corresponding":false,"raw_author_name":"Cong Yang","raw_affiliation_strings":["School of Future Science and Engineering, Soochow University,BeeLab"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Future Science and Engineering, Soochow University,BeeLab","institution_ids":["https://openalex.org/I185940356","https://openalex.org/I3923682"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106407147","display_name":"Sui Wei","orcid":"https://orcid.org/0009-0007-8124-9439"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Wei Sui","raw_affiliation_strings":["D-Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D-Robotics","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115596505","display_name":"Cong Wang","orcid":"https://orcid.org/0009-0006-4543-5843"},"institutions":[{"id":"https://openalex.org/I4210116723","display_name":"Robotics Research (United States)","ror":"https://ror.org/020w2fr77","country_code":"US","type":"company","lineage":["https://openalex.org/I4210116723"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Cong Wang","raw_affiliation_strings":["D-Robotics"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"D-Robotics","institution_ids":["https://openalex.org/I4210116723"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100394717","display_name":"Song Liu","orcid":"https://orcid.org/0009-0003-0941-6619"},"institutions":[{"id":"https://openalex.org/I30809798","display_name":"ShanghaiTech University","ror":"https://ror.org/030bhh786","country_code":"CN","type":"education","lineage":["https://openalex.org/I30809798"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Song Liu","raw_affiliation_strings":["School of Information Science and Technology, ShanghaiTech University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information Science and Technology, ShanghaiTech University","institution_ids":["https://openalex.org/I30809798"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":6,"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":"13590","last_page":"13596"},"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":0.9745000004768372,"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":0.9745000004768372,"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":0.9330000281333923,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9133999943733215,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.662983775138855},{"id":"https://openalex.org/keywords/joint","display_name":"Joint (building)","score":0.638984203338623},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5976381301879883},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5789650678634644},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5671724081039429},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5656593441963196},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5267314910888672},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5075620412826538},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.48073649406433105},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.4404471814632416},{"id":"https://openalex.org/keywords/open-set","display_name":"Open set","score":0.4344837963581085},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3833964467048645},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17242184281349182},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.10816940665245056}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.662983775138855},{"id":"https://openalex.org/C18555067","wikidata":"https://www.wikidata.org/wiki/Q8375051","display_name":"Joint (building)","level":2,"score":0.638984203338623},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5976381301879883},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5789650678634644},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5671724081039429},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5656593441963196},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5267314910888672},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5075620412826538},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.48073649406433105},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.4404471814632416},{"id":"https://openalex.org/C42357961","wikidata":"https://www.wikidata.org/wiki/Q213363","display_name":"Open set","level":2,"score":0.4344837963581085},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3833964467048645},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17242184281349182},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.10816940665245056},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C170154142","wikidata":"https://www.wikidata.org/wiki/Q150737","display_name":"Architectural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra55743.2025.11127317","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icra55743.2025.11127317","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Robotics and Automation (ICRA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2102605133","https://openalex.org/W2568262903","https://openalex.org/W2570343428","https://openalex.org/W2952122856","https://openalex.org/W2963037989","https://openalex.org/W2963351448","https://openalex.org/W2963518342","https://openalex.org/W2967869116","https://openalex.org/W2982770724","https://openalex.org/W2983943451","https://openalex.org/W3009436130","https://openalex.org/W3035396860","https://openalex.org/W3096609285","https://openalex.org/W3138516171","https://openalex.org/W3159619744","https://openalex.org/W4214507171","https://openalex.org/W4285102166","https://openalex.org/W4312747482","https://openalex.org/W4312956471","https://openalex.org/W4319068933","https://openalex.org/W4320002812","https://openalex.org/W4386065936","https://openalex.org/W4386076029","https://openalex.org/W4386076539","https://openalex.org/W4390872357","https://openalex.org/W4402716047","https://openalex.org/W4404612908"],"related_works":["https://openalex.org/W1996130883","https://openalex.org/W2748574964","https://openalex.org/W2381457774","https://openalex.org/W2888483922","https://openalex.org/W4396737233","https://openalex.org/W2367747139","https://openalex.org/W4313233182","https://openalex.org/W3147584709","https://openalex.org/W4391102217","https://openalex.org/W2566187525"],"abstract_inverted_index":{"Open-set":[0],"object":[1],"detection":[2],"(OSOD)":[3],"is":[4,50,86,201],"highly":[5,54],"desirable":[6],"for":[7,181,186],"robotic":[8,24,63],"manipulation":[9],"in":[10,62,116],"unstructured":[11],"environments.":[12],"However,":[13],"existing":[14],"OSOD":[15,47,60],"methods":[16],"often":[17],"fail":[18],"to":[19,27,57,88,151,178],"meet":[20],"the":[21,69,94,102,105,117,121,138,143,152,155,192,197,217,221],"requirements":[22],"of":[23,108,174,199,223],"applications":[25],"due":[26],"their":[28],"high":[29],"computational":[30,128],"burden":[31],"and":[32,53,125,147,183,207,228],"complex":[33,122],"deployment.":[34],"To":[35],"address":[36],"this":[37,39],"issue,":[38],"paper":[40],"proposes":[41],"a":[42,51,74,79,97,133,171],"light-weight":[43],"framework":[44],"called":[45],"Decoupled":[46],"(DOSOD),":[48],"which":[49,101],"practical":[52],"efficient":[55],"solution":[56],"support":[58],"real-time":[59,160],"tasks":[61],"systems.":[64],"Specifically,":[65],"DOSOD":[66,130,157,218],"builds":[67],"upon":[68],"YOLO-World":[70],"pipeline":[71],"by":[72,93],"integrating":[73],"vision-language":[75],"model":[76,169,219],"(VLM)":[77],"with":[78],"detector.":[80],"A":[81],"Multilayer":[82],"Perceptron":[83],"(MLP)":[84],"adaptor":[85],"developed":[87],"transform":[89],"text":[90],"embeddings":[91],"extracted":[92],"VLM":[95],"into":[96],"joint":[98,118],"space,":[99,119],"within":[100],"detector":[103,136],"learns":[104],"region":[106],"representations":[107],"classagnostic":[109],"proposals.":[110],"Cross-modality":[111],"features":[112],"are":[113,230],"directly":[114],"aligned":[115],"avoiding":[120],"feature":[123],"interactions":[124],"thereby":[126],"improving":[127],"efficiency.":[129],"operates":[131],"like":[132],"traditional":[134],"closed-set":[135,146],"during":[137],"testing":[139],"phase,":[140],"effectively":[141],"bridging":[142],"gap":[144],"between":[145],"openset":[148],"detection.":[149],"Compared":[150],"baseline":[153],"YOLO-World,":[154],"proposed":[156],"significantly":[158],"enhances":[159],"performance":[161],"while":[162],"maintaining":[163],"comparable":[164],"accuracy.":[165],"The":[166,226],"slight":[167],"DOSODS":[168],"achieves":[170],"Fixed":[172],"AP":[173],"26.7":[175],"%,":[176],"compared":[177],"26.2":[179],"%":[180,185,203,209],"YOLO-World-v1-S":[182],"22.7":[184],"YOLO-World-v2-S,":[187],"using":[188],"similar":[189],"backbones":[190],"on":[191],"LVIS":[193],"minival":[194],"dataset.":[195],"Meanwhile,":[196,213],"FPS":[198],"DOSOD-S":[200],"57.1":[202],"higher":[204,210],"than":[205,211],"YOLO-World-v1S":[206],"29.6":[208],"YOLO-World-v2-S.":[212],"we":[214],"demonstrate":[215],"that":[216],"facilitates":[220],"deployment":[222],"edge":[224],"devices.":[225],"codes":[227],"models":[229],"publicly":[231],"available":[232],"at":[233],"https://github.com/D-Robotics-AI-Lab/DOSOD.":[234]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}