{"id":"https://openalex.org/W4400188609","doi":"https://doi.org/10.1109/tpami.2024.3421300","title":"Large-Scale Object Detection in the Wild With Imbalanced Data Distribution, and Multi-Labels","display_name":"Large-Scale Object Detection in the Wild With Imbalanced Data Distribution, and Multi-Labels","publication_year":2024,"publication_date":"2024-07-01","ids":{"openalex":"https://openalex.org/W4400188609","doi":"https://doi.org/10.1109/tpami.2024.3421300","pmid":"https://pubmed.ncbi.nlm.nih.gov/38949947"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3421300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3421300","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":"https://openalex.org/A5011457041","display_name":"Cong Pan","orcid":"https://orcid.org/0000-0001-5959-4294"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Cong Pan","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5959-4294","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091958275","display_name":"Junran Peng","orcid":"https://orcid.org/0000-0001-5276-0114"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Junran Peng","raw_affiliation_strings":["Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-5276-0114","affiliations":[{"raw_affiliation_string":"Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039569339","display_name":"Xingyuan Bu","orcid":"https://orcid.org/0000-0002-6445-4306"},"institutions":[{"id":"https://openalex.org/I45928872","display_name":"Alibaba Group (China)","ror":"https://ror.org/00k642b80","country_code":"CN","type":"company","lineage":["https://openalex.org/I45928872"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingyuan Bu","raw_affiliation_strings":["Alibaba Group, Hangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Alibaba Group, Hangzhou, China","institution_ids":["https://openalex.org/I45928872"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5028016065","display_name":"Zhaoxiang Zhang","orcid":"https://orcid.org/0000-0003-2648-3875"},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]},{"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":"Zhaoxiang Zhang","raw_affiliation_strings":["New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2648-3875","affiliations":[{"raw_affiliation_string":"New Laboratory of Pattern Recognition (NLPR), State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences (CASIA), Beijing, China","institution_ids":["https://openalex.org/I19820366","https://openalex.org/I4210112150"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":2495,"currency":"USD","value_usd":2495},"apc_paid":null,"fwci":1.0706,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.75761124,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"46","issue":"12","first_page":"9255","last_page":"9271"},"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":0.7986000180244446,"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":0.7986000180244446,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.7730000019073486,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.7714999914169312,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/artificial-intelligence","display_name":"Artificial intelligence","score":0.6997767686843872},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.653226912021637},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6219883561134338},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.5849809646606445},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.575788140296936},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5161396265029907},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4630124568939209},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.33320289850234985},{"id":"https://openalex.org/keywords/cartography","display_name":"Cartography","score":0.13561025261878967},{"id":"https://openalex.org/keywords/geography","display_name":"Geography","score":0.09538114070892334}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6997767686843872},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.653226912021637},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6219883561134338},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5849809646606445},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.575788140296936},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5161396265029907},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4630124568939209},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.33320289850234985},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.13561025261878967},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.09538114070892334}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3421300","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3421300","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:38949947","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38949947","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":"Journal Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5353429300","display_name":null,"funder_award_id":"U21B2042","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5717587991","display_name":null,"funder_award_id":"2022ZD0116500","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G63062603","display_name":null,"funder_award_id":"62320106010","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/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1861492603","https://openalex.org/W1905051261","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2148143831","https://openalex.org/W2156935079","https://openalex.org/W2339172597","https://openalex.org/W2440599146","https://openalex.org/W2463598282","https://openalex.org/W2469885745","https://openalex.org/W2551429935","https://openalex.org/W2560096627","https://openalex.org/W2601564443","https://openalex.org/W2736688973","https://openalex.org/W2752782242","https://openalex.org/W2765802795","https://openalex.org/W2767106145","https://openalex.org/W2797977484","https://openalex.org/W2798869704","https://openalex.org/W2808867199","https://openalex.org/W2895281799","https://openalex.org/W2896791666","https://openalex.org/W2932399282","https://openalex.org/W2936503027","https://openalex.org/W2962721361","https://openalex.org/W2963037989","https://openalex.org/W2963150697","https://openalex.org/W2963300078","https://openalex.org/W2963346784","https://openalex.org/W2963351448","https://openalex.org/W2963513598","https://openalex.org/W2963516811","https://openalex.org/W2963691377","https://openalex.org/W2963703197","https://openalex.org/W2963745697","https://openalex.org/W2964093967","https://openalex.org/W2964241181","https://openalex.org/W2966926453","https://openalex.org/W2969510879","https://openalex.org/W2983943451","https://openalex.org/W2988452521","https://openalex.org/W2989294831","https://openalex.org/W2991391304","https://openalex.org/W2998420437","https://openalex.org/W3012573144","https://openalex.org/W3034472074","https://openalex.org/W3034601242","https://openalex.org/W3035160371","https://openalex.org/W3035338251","https://openalex.org/W3096609285","https://openalex.org/W3096688134","https://openalex.org/W3128945844","https://openalex.org/W3167456680","https://openalex.org/W3171625335","https://openalex.org/W3176474016","https://openalex.org/W3184439416","https://openalex.org/W3203770998","https://openalex.org/W4213056830","https://openalex.org/W4220813865","https://openalex.org/W4225668955","https://openalex.org/W4288083516","https://openalex.org/W4289535682","https://openalex.org/W4289560542","https://openalex.org/W4312577413","https://openalex.org/W4312592425","https://openalex.org/W4366352743","https://openalex.org/W4390873752","https://openalex.org/W6630792627","https://openalex.org/W6684191040","https://openalex.org/W6713507025","https://openalex.org/W6744066916","https://openalex.org/W6752402975","https://openalex.org/W6754898322","https://openalex.org/W6754940743","https://openalex.org/W6760424586","https://openalex.org/W6762718338","https://openalex.org/W6764733053","https://openalex.org/W6784094891","https://openalex.org/W6798838024"],"related_works":["https://openalex.org/W2737719445","https://openalex.org/W4239098401","https://openalex.org/W2898210368","https://openalex.org/W2382480268","https://openalex.org/W1976518449","https://openalex.org/W2732837990","https://openalex.org/W2363366881","https://openalex.org/W4292830139","https://openalex.org/W4319309705","https://openalex.org/W3127668761"],"abstract_inverted_index":{"Training":[0],"with":[1,114,138],"more":[2],"data":[3,52],"has":[4],"always":[5],"been":[6],"the":[7,17,25,50,77,102,121,134,144,163,166,181,185],"most":[8],"stable":[9],"and":[10,33,37,44,66,84,108],"effective":[11],"way":[12],"of":[13,91,130,141,150,165,173],"improving":[14],"performance":[15,137,164],"in":[16,80,105],"deep":[18],"learning":[19],"era.":[20],"The":[21],"Open":[22,151,186],"Images":[23,187],"dataset,":[24,29],"largest":[26],"object":[27,65,82,106,146],"detection":[28,83,107,147],"presents":[30],"significant":[31],"opportunities":[32],"challenges":[34],"for":[35],"general":[36],"sophisticated":[38],"scenarios.":[39],"However,":[40],"its":[41],"semi-automatic":[42],"collection":[43],"labeling":[45],"process,":[46],"designed":[47],"to":[48,55,100,119],"manage":[49],"huge":[51],"scale,":[53],"leads":[54],"label-related":[56],"problems,":[57],"including":[58],"explicit":[59],"or":[60],"implicit":[61],"multiple":[62],"labels":[63],"per":[64],"highly":[67],"imbalanced":[68],"label":[69,122],"distribution.":[70],"In":[71],"this":[72],"work,":[73],"we":[74,95,154],"quantitatively":[75],"analyze":[76],"major":[78],"problems":[79,104],"large-scale":[81],"provide":[85],"a":[86,97,110,115,127,139,156],"detailed":[87],"yet":[88],"comprehensive":[89],"demonstration":[90],"our":[92],"solutions.":[93],"First,":[94],"design":[96],"concurrent":[98],"softmax":[99],"handle":[101],"multi-label":[103],"propose":[109],"soft-balance":[111],"sampling":[112],"method":[113],"hybrid":[116],"training":[117],"scheduler":[118],"address":[120],"imbalance.":[123],"This":[124],"approach":[125],"yields":[126],"notable":[128],"improvement":[129],"3.34":[131],"points,":[132],"achieving":[133,169],"best":[135,182],"single-model":[136],"mAP":[140,172],"60.90%":[142],"on":[143],"public":[145,188],"test":[148,189],"set":[149],"Images.":[152],"Then,":[153],"introduce":[155],"well-designed":[157],"ensemble":[158],"mechanism":[159],"that":[160],"substantially":[161],"enhances":[162],"single":[167],"model,":[168],"an":[170],"overall":[171],"67.17%,":[174],"which":[175],"is":[176],"4.29":[177],"points":[178],"higher":[179],"than":[180],"result":[183],"from":[184],"2018.":[190]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":3}],"updated_date":"2026-08-28T12:50:07.497085","created_date":"2025-10-10T00:00:00"}