{"id":"https://openalex.org/W4321021073","doi":"https://doi.org/10.1109/tmm.2023.3244340","title":"Fine-Grained Visual Classification via Internal Ensemble Learning Transformer","display_name":"Fine-Grained Visual Classification via Internal Ensemble Learning Transformer","publication_year":2023,"publication_date":"2023-01-01","ids":{"openalex":"https://openalex.org/W4321021073","doi":"https://doi.org/10.1109/tmm.2023.3244340"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3244340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3244340","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-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/A5081006499","display_name":"Qin Xu","orcid":"https://orcid.org/0000-0002-9020-2006"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qin Xu","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-9020-2006","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100446916","display_name":"Jiahui Wang","orcid":"https://orcid.org/0000-0002-6438-1506"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiahui Wang","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6438-1506","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053609164","display_name":"Bo Jiang","orcid":"https://orcid.org/0000-0002-6238-1596"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bo Jiang","raw_affiliation_strings":["Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Computer Science and Technology, Anhui University, Hefei, China","Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-6238-1596","affiliations":[{"raw_affiliation_string":"Information Materials and Intelligent Sensing Laboratory of Anhui Province, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]},{"raw_affiliation_string":"Institute of Artificial Intelligence, Hefei Comprehensive National Science Center, Hefei, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5107117636","display_name":"Bin Luo","orcid":"https://orcid.org/0000-0002-1414-3307"},"institutions":[{"id":"https://openalex.org/I143868143","display_name":"Anhui University","ror":"https://ror.org/05th6yx34","country_code":"CN","type":"education","lineage":["https://openalex.org/I143868143"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Luo","raw_affiliation_strings":["Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China"],"raw_orcid":"https://orcid.org/0000-0002-1414-3307","affiliations":[{"raw_affiliation_string":"Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University, Hefei, China","institution_ids":["https://openalex.org/I143868143"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I143868143"],"apc_list":null,"apc_paid":null,"fwci":15.1763,"has_fulltext":false,"cited_by_count":157,"citation_normalized_percentile":{"value":0.99596398,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"25","issue":null,"first_page":"9015","last_page":"9028"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9970999956130981,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.9969000220298767,"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":0.8407211303710938},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7328708171844482},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.6711622476577759},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.5979101061820984},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5753179788589478},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5532040596008301},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.5347662568092346},{"id":"https://openalex.org/keywords/ensemble-learning","display_name":"Ensemble learning","score":0.5234995484352112},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.44624584913253784},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4263332486152649},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.41931402683258057},{"id":"https://openalex.org/keywords/voting","display_name":"Voting","score":0.4134995937347412},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.41280776262283325},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37927985191345215}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8407211303710938},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7328708171844482},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.6711622476577759},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.5979101061820984},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5753179788589478},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5532040596008301},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.5347662568092346},{"id":"https://openalex.org/C45942800","wikidata":"https://www.wikidata.org/wiki/Q245652","display_name":"Ensemble learning","level":2,"score":0.5234995484352112},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.44624584913253784},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4263332486152649},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.41931402683258057},{"id":"https://openalex.org/C520049643","wikidata":"https://www.wikidata.org/wiki/Q189760","display_name":"Voting","level":3,"score":0.4134995937347412},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.41280776262283325},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37927985191345215},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"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/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0},{"id":"https://openalex.org/C126838900","wikidata":"https://www.wikidata.org/wiki/Q77604","display_name":"Radiology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3244340","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3244340","pdf_url":null,"source":{"id":"https://openalex.org/S137030581","display_name":"IEEE Transactions on Multimedia","issn_l":"1520-9210","issn":["1520-9210","1941-0077"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["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 Multimedia","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6700000166893005,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[{"id":"https://openalex.org/G1048221617","display_name":null,"funder_award_id":"2108085Y23","funder_id":"https://openalex.org/F4320334897","funder_display_name":"Natural Science Foundation of Anhui Province"},{"id":"https://openalex.org/G2231845458","display_name":null,"funder_award_id":"61860206004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4959458362","display_name":"\u57fa\u4e8e\u591a\u6e90\u65f6\u7a7a\u4fe1\u606f\u878d\u5408\u7684\u51b7\u94fe\u7269\u6d41\u9700\u6c42\u7a7a\u95f4\u7ec4\u5408\u9884\u6d4b\u65b9\u6cd5\u7814\u7a76","funder_award_id":"72071001","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/F4320334897","display_name":"Natural Science Foundation of Anhui Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":80,"referenced_works":["https://openalex.org/W1496650988","https://openalex.org/W1797268635","https://openalex.org/W1954152232","https://openalex.org/W1977295328","https://openalex.org/W2194775991","https://openalex.org/W2202499615","https://openalex.org/W2345500696","https://openalex.org/W2533598788","https://openalex.org/W2731821979","https://openalex.org/W2737725206","https://openalex.org/W2747623286","https://openalex.org/W2763070548","https://openalex.org/W2765268259","https://openalex.org/W2773003563","https://openalex.org/W2789758093","https://openalex.org/W2798381792","https://openalex.org/W2808035123","https://openalex.org/W2810447190","https://openalex.org/W2883776044","https://openalex.org/W2891951760","https://openalex.org/W2896457183","https://openalex.org/W2961018736","https://openalex.org/W2963407932","https://openalex.org/W2965318645","https://openalex.org/W2965898445","https://openalex.org/W2981165461","https://openalex.org/W2981609437","https://openalex.org/W2982512212","https://openalex.org/W2986821660","https://openalex.org/W2990495699","https://openalex.org/W2997300818","https://openalex.org/W2997426000","https://openalex.org/W2998345525","https://openalex.org/W2998619563","https://openalex.org/W3008809756","https://openalex.org/W3009073662","https://openalex.org/W3042175414","https://openalex.org/W3101840387","https://openalex.org/W3108870912","https://openalex.org/W3109241881","https://openalex.org/W3129197028","https://openalex.org/W3130788242","https://openalex.org/W3137963805","https://openalex.org/W3139434170","https://openalex.org/W3174336354","https://openalex.org/W3174350209","https://openalex.org/W3182672186","https://openalex.org/W3195399086","https://openalex.org/W3200944276","https://openalex.org/W3204058594","https://openalex.org/W3204826552","https://openalex.org/W3206734547","https://openalex.org/W3212813052","https://openalex.org/W3213192039","https://openalex.org/W3213639431","https://openalex.org/W4200056912","https://openalex.org/W4206237889","https://openalex.org/W4206378740","https://openalex.org/W4207054665","https://openalex.org/W4212883601","https://openalex.org/W4214493665","https://openalex.org/W4285256277","https://openalex.org/W4312359177","https://openalex.org/W4312361652","https://openalex.org/W4313009108","https://openalex.org/W6620707391","https://openalex.org/W6638319203","https://openalex.org/W6676769703","https://openalex.org/W6681049983","https://openalex.org/W6739901393","https://openalex.org/W6755207826","https://openalex.org/W6763310536","https://openalex.org/W6766978945","https://openalex.org/W6767612737","https://openalex.org/W6778883912","https://openalex.org/W6780226713","https://openalex.org/W6784333009","https://openalex.org/W6790732931","https://openalex.org/W6791705549","https://openalex.org/W6798264847"],"related_works":["https://openalex.org/W2965546495","https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W3119773509","https://openalex.org/W3208297503","https://openalex.org/W2889153461","https://openalex.org/W2964117661","https://openalex.org/W4388405611","https://openalex.org/W2619127353"],"abstract_inverted_index":{"Recently,":[0],"vision":[1],"transformers":[2],"(ViTs)":[3],"have":[4],"been":[5,222],"investigated":[6],"in":[7,32,45,101],"fine-grained":[8,195],"visual":[9],"recognition":[10],"(FGVC)":[11],"and":[12,38,74,107,122,131,146,224],"are":[13],"now":[14],"considered":[15],"state":[16,210],"of":[17,29,83,87,98,111,176,185,211],"the":[18,25,30,33,81,84,92,99,119,128,133,135,141,147,154,165,177,183,191,209,212],"art.":[19],"However,":[20],"most":[21],"ViT-based":[22],"works":[23],"ignore":[24],"different":[26],"learning":[27,54,187],"performances":[28,86],"heads":[31,100],"multi-head":[34,66],"self-attention":[35],"(MHSA)":[36],"mechanism":[37],"its":[39],"layers.":[40],"To":[41,79,125],"address":[42],"these":[43],"issues,":[44],"this":[46,181],"paper,":[47],"we":[48,90],"propose":[49,91],"a":[50,159],"novel":[51],"internal":[52],"ensemble":[53,186],"transformer":[55],"(IELT)":[56],"for":[57,109,153],"FGVC.":[58],"The":[59,198],"proposed":[60],"IELT":[61],"involves":[62],"three":[63],"main":[64],"modules:":[65],"voting":[67],"(MHV)":[68],"module,":[69,73,94],"cross-layer":[70,115,129],"refinement":[71],"(CLR)":[72],"dynamic":[75],"selection":[76,167],"(DS)":[77],"module.":[78],"solve":[80],"problem":[82],"inconsistent":[85],"multiple":[88],"heads,":[89],"MHV":[93],"which":[95],"considers":[96],"all":[97],"each":[102,170],"layer":[103,171],"as":[104,114],"weak":[105],"learners":[106],"votes":[108],"tokens":[110],"discriminative":[112],"regions":[113],"feature":[116,130,143,196],"based":[117],"on":[118,214],"attention":[120],"maps":[121],"spatial":[123],"relationships.":[124],"effectively":[126],"mine":[127],"suppress":[132],"noise,":[134],"CLR":[136],"module":[137,163],"is":[138,144,151,188],"proposed,":[139],"where":[140],"refined":[142,178],"extracted":[145],"assist":[148],"logits":[149],"operation":[150],"developed":[152],"final":[155],"prediction.":[156],"In":[157,180],"addition,":[158],"newly":[160],"designed":[161],"DS":[162],"adjusts":[164],"token":[166],"number":[168],"at":[169],"by":[172],"weighting":[173],"their":[174],"contributions":[175],"feature.":[179],"way,":[182],"idea":[184],"combined":[189],"with":[190,208],"ViT":[192],"to":[193],"improve":[194],"representation.":[197],"experiments":[199],"demonstrate":[200],"that":[201],"our":[202],"method":[203],"achieves":[204],"competitive":[205],"results":[206],"compared":[207],"art":[213],"five":[215],"popular":[216],"FGVC":[217],"datasets.":[218],"Source":[219],"code":[220],"has":[221],"released":[223],"can":[225],"be":[226],"found":[227],"athttps://github.com/mobulan/IELT.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":31},{"year":2025,"cited_by_count":60},{"year":2024,"cited_by_count":58},{"year":2023,"cited_by_count":8}],"updated_date":"2026-08-05T07:39:15.569665","created_date":"2025-10-10T00:00:00"}