{"id":"https://openalex.org/W4407128922","doi":"https://doi.org/10.1109/tpami.2025.3538473","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection","display_name":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-Time Object Detection","publication_year":2025,"publication_date":"2025-02-04","ids":{"openalex":"https://openalex.org/W4407128922","doi":"https://doi.org/10.1109/tpami.2025.3538473","pmid":"https://pubmed.ncbi.nlm.nih.gov/40031746"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3538473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3538473","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Yuming Chen","orcid":"https://orcid.org/0009-0008-6357-8375"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yuming Chen","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0008-6357-8375","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015965681","display_name":"Xinbin Yuan","orcid":null},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbin Yuan","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0009-0009-8715-5497","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633431","display_name":"Jiabao Wang","orcid":"https://orcid.org/0000-0003-4951-3088"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiabao Wang","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0003-4951-3088","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101911284","display_name":"Ruiqi Wu","orcid":"https://orcid.org/0000-0002-7722-8025"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ruiqi Wu","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100693026","display_name":"Xiang Li","orcid":"https://orcid.org/0000-0002-4996-7365"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiang Li","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-4996-7365","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040392623","display_name":"Qibin Hou","orcid":"https://orcid.org/0000-0002-8388-8708"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibin Hou","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8388-8708","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037131575","display_name":"Ming\u2010Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["VCIP, School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5550-8758","affiliations":[{"raw_affiliation_string":"VCIP, School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205237279"],"apc_list":null,"apc_paid":null,"fwci":92.6544,"has_fulltext":false,"cited_by_count":168,"citation_normalized_percentile":{"value":0.99993008,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":"47","issue":"6","first_page":"4240","last_page":"4252"},"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":0.98089998960495,"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":0.98089998960495,"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":0.9782999753952026,"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":0.9638000130653381,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.717340886592865},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6666760444641113},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6641160249710083},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5438237190246582},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5295126438140869},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5117042064666748},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.49452754855155945},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.43034419417381287},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4285241365432739},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3723112940788269}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.717340886592865},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6666760444641113},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6641160249710083},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5438237190246582},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5295126438140869},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5117042064666748},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.49452754855155945},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.43034419417381287},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4285241365432739},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3723112940788269},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3538473","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3538473","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:40031746","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40031746","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G101772633","display_name":null,"funder_award_id":"070-63223049","funder_id":"https://openalex.org/F4320335787","funder_display_name":"Fundamental Research Funds for the Central Universities"},{"id":"https://openalex.org/G3149626323","display_name":null,"funder_award_id":"62276145","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6785956370","display_name":null,"funder_award_id":"62225604","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335787","display_name":"Fundamental Research Funds for the Central Universities","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":79,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1984685202","https://openalex.org/W2102605133","https://openalex.org/W2108598243","https://openalex.org/W2109255472","https://openalex.org/W2133155955","https://openalex.org/W2565639579","https://openalex.org/W2570343428","https://openalex.org/W2616247523","https://openalex.org/W2884561390","https://openalex.org/W2928165649","https://openalex.org/W2962721361","https://openalex.org/W2962749812","https://openalex.org/W2962766617","https://openalex.org/W2962834855","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963163009","https://openalex.org/W2963179609","https://openalex.org/W2963849369","https://openalex.org/W2963857746","https://openalex.org/W2963928582","https://openalex.org/W2964241181","https://openalex.org/W2982770724","https://openalex.org/W2990763144","https://openalex.org/W3035396860","https://openalex.org/W3042011474","https://openalex.org/W3096609285","https://openalex.org/W3167939936","https://openalex.org/W3176187859","https://openalex.org/W3176659256","https://openalex.org/W3180134609","https://openalex.org/W3212386989","https://openalex.org/W4206706211","https://openalex.org/W4213019189","https://openalex.org/W4214507171","https://openalex.org/W4214627427","https://openalex.org/W4226334005","https://openalex.org/W4283030623","https://openalex.org/W4307900253","https://openalex.org/W4312312588","https://openalex.org/W4312443924","https://openalex.org/W4320036918","https://openalex.org/W4323647442","https://openalex.org/W4385245566","https://openalex.org/W4385346076","https://openalex.org/W4386076325","https://openalex.org/W4390873076","https://openalex.org/W4396918399","https://openalex.org/W4401328675","https://openalex.org/W4402754006","https://openalex.org/W4403770406","https://openalex.org/W4406657538","https://openalex.org/W6631190155","https://openalex.org/W6714138976","https://openalex.org/W6729983426","https://openalex.org/W6739696289","https://openalex.org/W6745136726","https://openalex.org/W6750227808","https://openalex.org/W6750697433","https://openalex.org/W6764322716","https://openalex.org/W6766978945","https://openalex.org/W6777046832","https://openalex.org/W6779586474","https://openalex.org/W6784094891","https://openalex.org/W6784333009","https://openalex.org/W6798838024","https://openalex.org/W6809665764","https://openalex.org/W6810974023","https://openalex.org/W6811230874","https://openalex.org/W6842806116","https://openalex.org/W6843239693","https://openalex.org/W6847207718","https://openalex.org/W6847876731","https://openalex.org/W6856831935","https://openalex.org/W6868582632","https://openalex.org/W6875057238"],"related_works":["https://openalex.org/W1834370135","https://openalex.org/W2114275278","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W3127668761","https://openalex.org/W1489511283","https://openalex.org/W2974914859","https://openalex.org/W2026565050","https://openalex.org/W2110244802","https://openalex.org/W2163728705"],"abstract_inverted_index":{"We":[0],"aim":[1],"at":[2,47],"providing":[3],"the":[4,32,42,69,79,104,116,143,166],"object":[5,13,65,108],"detection":[6,43],"community":[7],"with":[8,37,142,184],"an":[9,122,127],"efficient":[10],"and":[11,35,99,113,169,176,181,188],"performant":[12],"detector,":[14],"termed":[15],"YOLO-MS.":[16],"The":[17,50],"core":[18],"design":[19],"is":[20,52,136],"based":[21],"on":[22,27,78,87,132],"a":[23,53,154],"series":[24],"of":[25,31,45,63,71,119,130,171],"investigations":[26],"how":[28],"multi-branch":[29],"features":[30],"basic":[33],"block":[34],"convolutions":[36],"different":[38,48],"kernel":[39],"sizes":[40],"affect":[41],"performance":[44],"objects":[46],"scales.":[49],"outcome":[51],"new":[54],"strategy":[55],"that":[56],"can":[57,125,150],"significantly":[58,164],"enhance":[59],"multi-scale":[60],"feature":[61],"representations":[62],"real-time":[64,107],"detectors.":[66],"To":[67],"verify":[68],"effectiveness":[70],"our":[72,76,101,148,162],"work,":[73],"we":[74],"train":[75],"YOLO-MS":[77,102,120],"MS":[80,133],"COCO":[81],"dataset":[82],"from":[83,173],"scratch":[84],"without":[85],"relying":[86],"any":[88],"other":[89,158],"large-scale":[90],"datasets,":[91],"like":[92],"ImageNet":[93],"or":[94],"pre-trained":[95],"weights.":[96],"Without":[97],"bells":[98],"whistles,":[100],"outperforms":[103],"recent":[105],"state-of-the-art":[106],"detectors,":[109],"including":[110],"YOLO-v7,":[111],"RTMDet,":[112],"YOLO-v8.":[114],"Taking":[115],"XS":[117],"version":[118],"as":[121,153],"example,":[123],"it":[124],"achieve":[126],"AP":[128,170],"score":[129],"42+%":[131],"COCO,":[134],"which":[135],"about":[137],"2%":[138],"higher":[139],"than":[140],"RTMDet":[141],"same":[144],"model":[145],"size.":[146],"Furthermore,":[147],"work":[149],"also":[151],"serve":[152],"plug-and-play":[155],"module":[156],"for":[157],"YOLO":[159],"models.":[160],"Typically,":[161],"method":[163],"advances":[165],"APs,":[167],"APl,":[168],"YOLOv8-N":[172],"18%+,":[174],"52%+,":[175],"37%+":[177],"to":[178],"20%+,":[179],"55%+,":[180],"40%+,":[182],"respectively,":[183],"even":[185],"fewer":[186],"parameters":[187],"MACs.":[189]},"counts_by_year":[{"year":2026,"cited_by_count":65},{"year":2025,"cited_by_count":100},{"year":2024,"cited_by_count":3}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}