{"id":"https://openalex.org/W4396909806","doi":"https://doi.org/10.1109/tpami.2024.3401036","title":"EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training","display_name":"EfficientTrain++: Generalized Curriculum Learning for Efficient Visual Backbone Training","publication_year":2024,"publication_date":"2024-05-14","ids":{"openalex":"https://openalex.org/W4396909806","doi":"https://doi.org/10.1109/tpami.2024.3401036","pmid":"https://pubmed.ncbi.nlm.nih.gov/38743547"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2024.3401036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3401036","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/A5100418037","display_name":"Yulin Wang","orcid":"https://orcid.org/0000-0002-1363-0234"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yulin Wang","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100636019","display_name":"Yang Yue","orcid":"https://orcid.org/0000-0001-6934-2357"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yang Yue","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5112111778","display_name":"Rui Lu","orcid":"https://orcid.org/0009-0003-4850-8401"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Lu","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045569962","display_name":"Yizeng Han","orcid":"https://orcid.org/0000-0001-5706-8784"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yizeng Han","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101868179","display_name":"Shiji Song","orcid":"https://orcid.org/0000-0003-0858-1770"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shiji Song","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013240918","display_name":"Gao Huang","orcid":"https://orcid.org/0000-0002-7251-0988"},"institutions":[{"id":"https://openalex.org/I99065089","display_name":"Tsinghua University","ror":"https://ror.org/03cve4549","country_code":"CN","type":"education","lineage":["https://openalex.org/I99065089"]},{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Gao Huang","raw_affiliation_strings":["Department of Automation, BNRist, Tsinghua University, Beijing, China","Beijing Academy of Artificial Intelligence"],"affiliations":[{"raw_affiliation_string":"Department of Automation, BNRist, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]},{"raw_affiliation_string":"Beijing Academy of Artificial Intelligence","institution_ids":["https://openalex.org/I4210100255"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100418037"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":3.9247,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.94666699,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":99},"biblio":{"volume":"46","issue":"12","first_page":"8036","last_page":"8055"},"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":0.9983999729156494,"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":0.9983999729156494,"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":0.9983999729156494,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9976999759674072,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/computer-science","display_name":"Computer science","score":0.731674075126648},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.683610737323761},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.6595154404640198},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.5842206478118896},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5735113620758057},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.42279601097106934},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.33677423000335693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.731674075126648},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.683610737323761},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.6595154404640198},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.5842206478118896},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5735113620758057},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.42279601097106934},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.33677423000335693},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2024.3401036","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2024.3401036","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:38743547","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38743547","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":[{"display_name":"Reduced inequalities","score":0.550000011920929,"id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G2438210826","display_name":null,"funder_award_id":"62321005","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5313418749","display_name":null,"funder_award_id":"42327901","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7410564107","display_name":null,"funder_award_id":"62276150","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"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":107,"referenced_works":["https://openalex.org/W12634471","https://openalex.org/W1513879401","https://openalex.org/W1861492603","https://openalex.org/W1954152232","https://openalex.org/W1966347487","https://openalex.org/W1978924416","https://openalex.org/W1995137594","https://openalex.org/W1999908130","https://openalex.org/W2007347635","https://openalex.org/W2020919250","https://openalex.org/W2108598243","https://openalex.org/W2124219775","https://openalex.org/W2133515615","https://openalex.org/W2136922672","https://openalex.org/W2151834591","https://openalex.org/W2194775991","https://openalex.org/W2256388387","https://openalex.org/W2296073425","https://openalex.org/W2345837149","https://openalex.org/W2507296351","https://openalex.org/W2528287124","https://openalex.org/W2533598788","https://openalex.org/W2781055951","https://openalex.org/W2884822772","https://openalex.org/W2887842788","https://openalex.org/W2889081631","https://openalex.org/W2923622379","https://openalex.org/W2945472816","https://openalex.org/W2949736877","https://openalex.org/W2952474700","https://openalex.org/W2963351448","https://openalex.org/W2963390466","https://openalex.org/W2963516811","https://openalex.org/W2963809228","https://openalex.org/W2972758308","https://openalex.org/W2988396473","https://openalex.org/W2989676862","https://openalex.org/W3016317693","https://openalex.org/W3034175346","https://openalex.org/W3035424951","https://openalex.org/W3035682985","https://openalex.org/W3097527797","https://openalex.org/W3123742938","https://openalex.org/W3126121388","https://openalex.org/W3131500599","https://openalex.org/W3138516171","https://openalex.org/W3142849873","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3172942063","https://openalex.org/W4231090517","https://openalex.org/W4312312750","https://openalex.org/W4312436424","https://openalex.org/W4312443924","https://openalex.org/W4312453657","https://openalex.org/W4312820606","https://openalex.org/W4313007769","https://openalex.org/W4313043552","https://openalex.org/W4313156423","https://openalex.org/W4321151009","https://openalex.org/W4386076446","https://openalex.org/W4386221015","https://openalex.org/W4390871961","https://openalex.org/W6637373629","https://openalex.org/W6640308425","https://openalex.org/W6676481782","https://openalex.org/W6676553272","https://openalex.org/W6676769703","https://openalex.org/W6679390333","https://openalex.org/W6685444988","https://openalex.org/W6685644109","https://openalex.org/W6685663092","https://openalex.org/W6717867081","https://openalex.org/W6731990857","https://openalex.org/W6736021936","https://openalex.org/W6739622702","https://openalex.org/W6745560452","https://openalex.org/W6748208641","https://openalex.org/W6748529433","https://openalex.org/W6750523955","https://openalex.org/W6753772092","https://openalex.org/W6755845484","https://openalex.org/W6759402224","https://openalex.org/W6759902256","https://openalex.org/W6760278398","https://openalex.org/W6761472960","https://openalex.org/W6762287338","https://openalex.org/W6762448741","https://openalex.org/W6763136721","https://openalex.org/W6763310536","https://openalex.org/W6763810570","https://openalex.org/W6764322716","https://openalex.org/W6772167297","https://openalex.org/W6779815254","https://openalex.org/W6780028523","https://openalex.org/W6783989761","https://openalex.org/W6784233108","https://openalex.org/W6784333009","https://openalex.org/W6785494106","https://openalex.org/W6787972765","https://openalex.org/W6788135285","https://openalex.org/W6790978476","https://openalex.org/W6793164127","https://openalex.org/W6796761347","https://openalex.org/W6802996638","https://openalex.org/W6838710837","https://openalex.org/W6850644760"],"related_works":["https://openalex.org/W4389116644","https://openalex.org/W2153315159","https://openalex.org/W3103844505","https://openalex.org/W259157601","https://openalex.org/W4205463238","https://openalex.org/W2761785940","https://openalex.org/W1482209366","https://openalex.org/W2404514746","https://openalex.org/W1652783584","https://openalex.org/W2082783427"],"abstract_inverted_index":{"The":[0,265],"superior":[1],"performance":[2],"of":[3,33,68,85,92,157,189,209,220,284],"modern":[4],"computer":[5],"vision":[6,9],"backbones":[7],"(e.g.,":[8,288,315],"Transformers":[10],"learned":[11],"on":[12,81,301],"ImageNet-1":[13,302],"K/22":[14,303],"K)":[15],"usually":[16],"comes":[17],"with":[18,163],"a":[19,53,135,176,182],"costly":[20],"training":[21,41,50,144,169,282],"procedure.":[22],"This":[23],"study":[24],"contributes":[25],"to":[26,98,153,195],"this":[27,173],"issue":[28],"by":[29,77,130,216,234,297],"generalizing":[30],"the":[31,49,82,89,94,105,120,138,143,151,154,186,190,193,199,207,218,281],"idea":[32,174],"curriculum":[34,51,136,231],"learning":[35,83,148,232,314],"beyond":[36],"its":[37],"original":[38],"formulation,":[39],"i.e.,":[40],"models":[42,287],"using":[43],"easier-to-harder":[44,70],"data.":[45,106],"Specifically,":[46],"we":[47,133,180,203,224,240],"reformulate":[48],"as":[52,168,254],"soft-selection":[54],"function,":[55],"which":[56],"uncovers":[57],"progressively":[58],"more":[59],"difficult":[60],"patterns":[61,103,156,165],"within":[62],"each":[63,158],"example":[64,159],"during":[65,88],"training,":[66,93,257],"instead":[67],"performing":[69],"sample":[71],"selection.":[72],"Our":[73],"work":[74],"is":[75,160,269],"inspired":[76],"an":[78,276],"intriguing":[79],"observation":[80],"dynamics":[84],"visual":[86],"backbones:":[87],"earlier":[90],"stages":[91],"model":[95,139,194],"predominantly":[96],"learns":[97],"recognize":[99],"some":[100],"'easier-to-learn'":[101,155],"discriminative":[102],"in":[104,175,185,249,312],"These":[107],"patterns,":[108],"when":[109],"observed":[110],"through":[111],"frequency":[112],"and":[113,119,229,258,295],"spatial":[114],"domains,":[115],"incorporate":[116],"lower-frequency":[117,200],"components,":[118],"natural":[121,210],"image":[122],"contents":[123,208],"without":[124,305],"distortion":[125],"or":[126,261],"data":[127,145,221,262],"augmentation.":[128,222],"Motivated":[129],"these":[131,226],"findings,":[132],"propose":[134],"where":[137],"always":[140],"leverages":[141],"all":[142],"at":[146],"every":[147],"stage,":[149],"yet":[150,272],"exposure":[152],"initiated":[161],"first,":[162],"harder":[164],"gradually":[166],"introduced":[167],"progresses.":[170],"To":[171],"implement":[172],"computationally":[177],"efficient":[178],"way,":[179],"introduce":[181],"cropping":[183],"operation":[184],"Fourier":[187],"spectrum":[188],"inputs,":[191],"enabling":[192],"learn":[196],"from":[197],"only":[198],"components.":[201],"Then":[202],"show":[204],"that":[205],"exposing":[206],"images":[211],"can":[212],"be":[213],"readily":[214],"achieved":[215],"modulating":[217],"intensity":[219],"Finally,":[223],"integrate":[225],"two":[227],"aspects":[228],"design":[230],"schedules":[233],"proposing":[235],"tailored":[236],"searching":[237],"algorithms.":[238],"Moreover,":[239],"present":[241],"useful":[242],"techniques":[243],"for":[244],"deploying":[245],"our":[246],"approach":[247],"efficiently":[248],"challenging":[250],"practical":[251],"scenarios,":[252],"such":[253],"large-scale":[255],"parallel":[256],"limited":[259],"input/output":[260],"pre-processing":[263],"speed.":[264],"resulting":[266],"method,":[267],"EfficientTrain++,":[268],"simple,":[270],"general,":[271],"surprisingly":[273],"effective.":[274],"As":[275],"off-the-shelf":[277],"approach,":[278],"it":[279],"reduces":[280],"time":[283],"various":[285],"popular":[286],"ResNet,":[289],"ConvNeXt,":[290],"DeiT,":[291],"PVT,":[292],"Swin,":[293],"CSWin,":[294],"CAFormer)":[296],"[Formula:":[298],"see":[299],"text]":[300],"K":[304],"sacrificing":[306],"accuracy.":[307],"It":[308],"also":[309],"demonstrates":[310],"efficacy":[311],"self-supervised":[313],"MAE).":[316]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":11},{"year":2024,"cited_by_count":3}],"updated_date":"2026-03-08T08:50:53.379069","created_date":"2025-10-10T00:00:00"}