{"id":"https://openalex.org/W4386047750","doi":"https://doi.org/10.1109/cvpr52729.2023.00704","title":"ScaleDet: A Scalable Multi-Dataset Object Detector","display_name":"ScaleDet: A Scalable Multi-Dataset Object Detector","publication_year":2023,"publication_date":"2023-06-01","ids":{"openalex":"https://openalex.org/W4386047750","doi":"https://doi.org/10.1109/cvpr52729.2023.00704"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52729.2023.00704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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/A5033035704","display_name":"Yanbei Chen","orcid":"https://orcid.org/0000-0002-9730-9463"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Yanbei Chen","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059021916","display_name":"Manchen Wang","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Manchen Wang","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001815363","display_name":"Abhay Mittal","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Abhay Mittal","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038332090","display_name":"Zhenlin Xu","orcid":"https://orcid.org/0000-0002-1197-4615"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Zhenlin Xu","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070940574","display_name":"Paolo Favaro","orcid":"https://orcid.org/0000-0003-3546-8247"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Paolo Favaro","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002114219","display_name":"Joseph Tighe","orcid":"https://orcid.org/0000-0002-0716-8119"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Joseph Tighe","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044605684","display_name":"Davide Modolo","orcid":"https://orcid.org/0000-0002-7625-7748"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Davide Modolo","raw_affiliation_strings":["AWS AI Labs"],"affiliations":[{"raw_affiliation_string":"AWS AI Labs","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5033035704"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.9658,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":{"value":0.92951945,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"7288","last_page":"7297"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9997000098228455,"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":0.9993000030517578,"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"}},{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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/computer-science","display_name":"Computer science","score":0.8447540998458862},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7995542287826538},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6034077405929565},{"id":"https://openalex.org/keywords/annotation","display_name":"Annotation","score":0.5833106637001038},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5705217719078064},{"id":"https://openalex.org/keywords/upstream","display_name":"Upstream (networking)","score":0.5480400323867798},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5121679306030273},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5027978420257568},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.48733410239219666},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4692383110523224},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.44026196002960205},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.43818455934524536},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.41670671105384827},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3842564523220062},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08129408955574036}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8447540998458862},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7995542287826538},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6034077405929565},{"id":"https://openalex.org/C2776321320","wikidata":"https://www.wikidata.org/wiki/Q857525","display_name":"Annotation","level":2,"score":0.5833106637001038},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5705217719078064},{"id":"https://openalex.org/C191172861","wikidata":"https://www.wikidata.org/wiki/Q7899321","display_name":"Upstream (networking)","level":2,"score":0.5480400323867798},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5121679306030273},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5027978420257568},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.48733410239219666},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4692383110523224},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.44026196002960205},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.43818455934524536},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.41670671105384827},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3842564523220062},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08129408955574036},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52729.2023.00704","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52729.2023.00704","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":66,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1522301498","https://openalex.org/W1773149199","https://openalex.org/W1861492603","https://openalex.org/W1927052826","https://openalex.org/W2108598243","https://openalex.org/W2109586012","https://openalex.org/W2194775991","https://openalex.org/W2277195237","https://openalex.org/W2886641317","https://openalex.org/W2939059980","https://openalex.org/W2948672349","https://openalex.org/W2963150697","https://openalex.org/W2963524571","https://openalex.org/W2963936013","https://openalex.org/W2964241181","https://openalex.org/W2982770724","https://openalex.org/W2983943451","https://openalex.org/W2998575480","https://openalex.org/W3030520226","https://openalex.org/W3035086574","https://openalex.org/W3106827427","https://openalex.org/W3126337491","https://openalex.org/W3138006590","https://openalex.org/W3138516171","https://openalex.org/W3143320354","https://openalex.org/W3159619744","https://openalex.org/W3166396011","https://openalex.org/W3171660447","https://openalex.org/W3173859428","https://openalex.org/W3176641147","https://openalex.org/W3176659256","https://openalex.org/W3182683290","https://openalex.org/W3206072662","https://openalex.org/W3212456749","https://openalex.org/W3213454282","https://openalex.org/W4282919422","https://openalex.org/W4287203292","https://openalex.org/W4288083516","https://openalex.org/W4310486995","https://openalex.org/W4312424618","https://openalex.org/W4312456860","https://openalex.org/W4312563428","https://openalex.org/W4312691946","https://openalex.org/W4312956471","https://openalex.org/W4312980231","https://openalex.org/W4313136445","https://openalex.org/W4313139494","https://openalex.org/W6620707391","https://openalex.org/W6631190155","https://openalex.org/W6639102338","https://openalex.org/W6676497082","https://openalex.org/W6750462345","https://openalex.org/W6760424586","https://openalex.org/W6778485988","https://openalex.org/W6782072296","https://openalex.org/W6790019176","https://openalex.org/W6791353385","https://openalex.org/W6792148081","https://openalex.org/W6792860290","https://openalex.org/W6794559225","https://openalex.org/W6802517928","https://openalex.org/W6803953248","https://openalex.org/W6809576537","https://openalex.org/W6809783041","https://openalex.org/W6839745749"],"related_works":["https://openalex.org/W2361861616","https://openalex.org/W2263699433","https://openalex.org/W2377979023","https://openalex.org/W2218034408","https://openalex.org/W2392921965","https://openalex.org/W2358755282","https://openalex.org/W2625833328","https://openalex.org/W1533177136","https://openalex.org/W4380994516","https://openalex.org/W2251519152"],"abstract_inverted_index":{"Multi-dataset":[0],"training":[1,38],"provides":[2],"a":[3,20,61,68],"viable":[4],"solution":[5],"for":[6,73],"exploiting":[7],"heterogeneous":[8],"large-scale":[9],"datasets":[10,32,105,125],"without":[11],"extra":[12],"annotation":[13],"cost.":[14],"In":[15],"this":[16],"work,":[17],"we":[18,59],"propose":[19],"scalable":[21,64],"multi-dataset":[22,42,74],"detector":[23],"(ScaleDet)":[24],"that":[25,44,139],"can":[26,96],"scale":[27],"up":[28],"its":[29],"generalization":[30],"across":[31,57,91],"when":[33],"increasing":[34],"the":[35,84,130,170],"number":[36],"of":[37,149],"datasets.":[39,92,135],"Unlike":[40],"existing":[41],"learners":[43],"mostly":[45],"rely":[46],"on":[47,99,151,154,157,160,164],"manual":[48],"relabelling":[49],"efforts":[50],"or":[51],"sophisticated":[52],"optimizations":[53],"to":[54,66,82],"unify":[55],"labels":[56],"datasets,":[58,122],"introduce":[60],"simple":[62],"yet":[63],"formulation":[65],"derive":[67],"unified":[69],"semantic":[70,89],"label":[71,85,88],"space":[72],"training.":[75],"ScaleDet":[76,95,140],"is":[77],"trained":[78],"by":[79],"visual-textual":[80],"alignment":[81],"learn":[83],"assignment":[86],"with":[87,106,146,169],"similarities":[90],"Once":[93],"trained,":[94],"generalize":[97],"well":[98],"any":[100],"given":[101],"upstream":[102,121],"and":[103,108,123,162],"downstream":[104,134],"seen":[107],"unseen":[109],"classes.":[110],"We":[111],"conduct":[112],"extensive":[113],"experiments":[114],"using":[115],"LVIS,":[116,152],"COCO,":[117,155],"Objects365,":[118,158],"OpenImages":[119],"as":[120,133],"13":[124],"from":[126],"Object":[127],"Detection":[128],"in":[129],"Wild":[131],"(ODinW)":[132],"Our":[136],"results":[137],"show":[138],"achieves":[141],"compelling":[142],"strong":[143],"model":[144],"performance":[145],"an":[147],"mAP":[148],"50.7":[150],"58.8":[153],"46.8":[156],"76.2":[159],"OpenImages,":[161],"71.8":[163],"ODinW,":[165],"surpassing":[166],"state-of-the-art":[167],"detectors":[168],"same":[171],"backbone.":[172]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":8},{"year":2024,"cited_by_count":14}],"updated_date":"2026-03-05T09:29:38.588285","created_date":"2025-10-10T00:00:00"}