{"id":"https://openalex.org/W4405868195","doi":"https://doi.org/10.1145/3696409.3700195","title":"CFRL: Coarse-Fine Decoupled Representation Learning For Long-Tailed Recognition","display_name":"CFRL: Coarse-Fine Decoupled Representation Learning For Long-Tailed Recognition","publication_year":2024,"publication_date":"2024-12-03","ids":{"openalex":"https://openalex.org/W4405868195","doi":"https://doi.org/10.1145/3696409.3700195"},"language":"en","primary_location":{"id":"doi:10.1145/3696409.3700195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700195","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696409.3700195?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3696409.3700195?download=true","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5109752616","display_name":"Yiran Song","orcid":"https://orcid.org/0009-0003-6619-7889"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yiran Song","raw_affiliation_strings":["Shanghai Jiao Tong University, SHANGHAI, China"],"raw_orcid":"https://orcid.org/0009-0003-6619-7889","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, SHANGHAI, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031210225","display_name":"Qianyu Zhou","orcid":"https://orcid.org/0000-0002-5331-050X"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qianyu Zhou","raw_affiliation_strings":["Shanghai Jiao Tong University, shanghai, China"],"raw_orcid":"https://orcid.org/0000-0002-5331-050X","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668926","display_name":"Kun Hu","orcid":"https://orcid.org/0000-0002-6891-8059"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Kun Hu","raw_affiliation_strings":["The University of Sydney, Sydney, AUSTRALIA"],"raw_orcid":"https://orcid.org/0000-0002-6891-8059","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, AUSTRALIA","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5084218062","display_name":"Lizhuang Ma","orcid":"https://orcid.org/0000-0003-1653-4341"},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Lizhuang Ma","raw_affiliation_strings":["Shanghai Jiao Tong University, shanghai, China"],"raw_orcid":"https://orcid.org/0000-0003-1653-4341","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019288783","display_name":"Xuequan Lu","orcid":"https://orcid.org/0000-0003-0959-408X"},"institutions":[{"id":"https://openalex.org/I196829312","display_name":"La Trobe University","ror":"https://ror.org/01rxfrp27","country_code":"AU","type":"education","lineage":["https://openalex.org/I196829312"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Xuequan Lu","raw_affiliation_strings":["La Trobe University, Melbourne, AUSTRALIA"],"raw_orcid":"https://orcid.org/0000-0003-0959-408X","affiliations":[{"raw_affiliation_string":"La Trobe University, Melbourne, AUSTRALIA","institution_ids":["https://openalex.org/I196829312"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9995999932289124,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9976999759674072,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9955000281333923,"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":0.7072321176528931},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6161230206489563},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5697736144065857},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.526386022567749},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.48869088292121887}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7072321176528931},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6161230206489563},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5697736144065857},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.526386022567749},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.48869088292121887},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3696409.3700195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700195","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696409.3700195?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3696409.3700195","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3696409.3700195","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3696409.3700195?download=true","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 6th ACM International Conference on Multimedia in Asia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1014109120","display_name":null,"funder_award_id":"72192821","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3429353868","display_name":null,"funder_award_id":"21511101200","funder_id":"https://openalex.org/F4320321885","funder_display_name":"Science and Technology Commission of Shanghai Municipality"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321885","display_name":"Science and Technology Commission of Shanghai Municipality","ror":"https://ror.org/03kt66j61"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4405868195.pdf","grobid_xml":"https://content.openalex.org/works/W4405868195.grobid-xml"},"referenced_works_count":37,"referenced_works":["https://openalex.org/W2117539524","https://openalex.org/W2194775991","https://openalex.org/W2781292787","https://openalex.org/W2797977484","https://openalex.org/W2962933664","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W3034601242","https://openalex.org/W3035054804","https://openalex.org/W3035524453","https://openalex.org/W3035552357","https://openalex.org/W3095707208","https://openalex.org/W3096121526","https://openalex.org/W3128945844","https://openalex.org/W3166596953","https://openalex.org/W3167251133","https://openalex.org/W3176346992","https://openalex.org/W3176474016","https://openalex.org/W3196349267","https://openalex.org/W3201565470","https://openalex.org/W3202087803","https://openalex.org/W3204140421","https://openalex.org/W4214519401","https://openalex.org/W4214718285","https://openalex.org/W4312244159","https://openalex.org/W4312344855","https://openalex.org/W4312453657","https://openalex.org/W4312702685","https://openalex.org/W4312768099","https://openalex.org/W4312866014","https://openalex.org/W4312877479","https://openalex.org/W4312910036","https://openalex.org/W4312986563","https://openalex.org/W4313066313","https://openalex.org/W4313151233","https://openalex.org/W4313156423","https://openalex.org/W4386076553"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2033914206","https://openalex.org/W2042327336"],"abstract_inverted_index":{"Data":[0],"often":[1,41],"faces":[2],"a":[3,23,86],"severe":[4],"class":[5,58],"imbalance":[6],"issue":[7],"in":[8,117],"the":[9,14,28,45,54,78,105,118,130,139,151,164,169,177],"real":[10],"world,":[11],"meaning":[12],"that":[13,163,197],"number":[15],"of":[16,31,56,132,171,179,184],"instances":[17],"within":[18],"classes":[19,173],"varies":[20],"greatly,":[21],"following":[22],"long-tailed":[24,37],"distribution.In":[25],"this":[26,82,198],"case,":[27],"direct":[29],"application":[30],"supervised":[32],"learning":[33,110,124],"yields":[34],"poor":[35],"performance.Existing":[36],"recognition":[38],"(LTR)":[39,209],"methods":[40],"heavily":[42],"rely":[43],"on":[44,125,189],"label":[46,72,133],"information":[47,127],"to":[48,65,100,128,153],"enhance":[49],"tail":[50,180],"classes'":[51],"accuracy":[52,170],"at":[53],"expense":[55],"head":[57,172],"by":[59,136],"an":[60],"image-level":[61,114,119,126],"end-to-end":[62],"resampling":[63],"strategy":[64],"address":[66],"data":[67,102],"distribution":[68],"imbalance.Nevertheless,":[69],"they":[70],"neglect":[71],"bias,":[73],"which":[74],"can":[75,201],"severely":[76],"affect":[77],"LTR":[79],"model's":[80],"accuracy.In":[81],"paper,":[83],"we":[84,121,142,195],"propose":[85],"novel":[87],"approach,":[88],"namely":[89],"Coarse-Fine":[90],"Decoupled":[91],"Representation":[92],"Learning":[93],"(CFRL)":[94],"for":[95],"LTR.Our":[96],"core":[97],"idea":[98],"is":[99],"decouple":[101],"representations":[103],"from":[104],"classifier":[106],"and":[107,115,159,192],"decompose":[108],"representation":[109],"into":[111],"two":[112],"stages:":[113],"patch-level.Specifically,":[116],"stage,":[120,141],"leverage":[122],"unsupervised":[123],"reduce":[129],"impact":[131],"bias":[134],"caused":[135],"imbalanced":[137],"datasets.In":[138],"patch-level":[140,144],"introduce":[143],"rotation":[145],"augmentation":[146],"as":[147],"negative":[148],"samples,":[149],"forcing":[150],"model":[152],"acquire":[154],"more":[155],"comprehensive":[156],"information.Our":[157],"theoretical":[158],"empirical":[160],"analyses":[161],"demonstrate":[162],"approach":[165],"does":[166],"not":[167],"sacrifice":[168],"while":[174],"significantly":[175],"reducing":[176],"overfitting":[178],"classes,":[181],"improving":[182],"both":[183],"them.We":[185],"showcase":[186],"state-of-the-art":[187],"results":[188],"CIFAR,":[190],"ImageNet,":[191],"iNaturalist":[193],"datasets.Furthermore,":[194],"illustrate":[196],"training":[199],"methodology":[200],"be":[202],"combined":[203],"with":[204],"various":[205],"existing":[206],"Long-Tailed":[207],"Recognition":[208],"methods,":[210],"further":[211],"enhancing":[212],"their":[213],"performance.":[214]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}