{"id":"https://openalex.org/W4375868901","doi":"https://doi.org/10.1109/icassp49357.2023.10096059","title":"CLMAE: A Liter and Faster Masked Autoencoders","display_name":"CLMAE: A Liter and Faster Masked Autoencoders","publication_year":2023,"publication_date":"2023-05-05","ids":{"openalex":"https://openalex.org/W4375868901","doi":"https://doi.org/10.1109/icassp49357.2023.10096059"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49357.2023.10096059","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-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/A5102966924","display_name":"Yiran Song","orcid":"https://orcid.org/0000-0003-0872-4479"},"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":true,"raw_author_name":"Yiran Song","raw_affiliation_strings":["Shanghai Jiao Tong University"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]},{"author_position":"last","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"],"affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5102966924"],"corresponding_institution_ids":["https://openalex.org/I183067930"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.03825405,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9997000098228455,"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/T10331","display_name":"Video Surveillance and Tracking Methods","score":0.9958000183105469,"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":0.7787888050079346},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6139621138572693},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5941513776779175},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.5764199495315552},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5410787463188171},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5108287334442139},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.45861151814460754},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4501936733722687},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4222710430622101},{"id":"https://openalex.org/keywords/schedule","display_name":"Schedule","score":0.41751545667648315},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3835955262184143},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.33163154125213623},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.12809431552886963},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.12791869044303894},{"id":"https://openalex.org/keywords/voltage","display_name":"Voltage","score":0.12424400448799133}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7787888050079346},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6139621138572693},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5941513776779175},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.5764199495315552},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5410787463188171},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5108287334442139},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.45861151814460754},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4501936733722687},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4222710430622101},{"id":"https://openalex.org/C68387754","wikidata":"https://www.wikidata.org/wiki/Q7271585","display_name":"Schedule","level":2,"score":0.41751545667648315},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3835955262184143},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.33163154125213623},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.12809431552886963},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.12791869044303894},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.12424400448799133},{"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},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49357.2023.10096059","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icassp49357.2023.10096059","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"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":29,"referenced_works":["https://openalex.org/W2108598243","https://openalex.org/W2531409750","https://openalex.org/W2866343820","https://openalex.org/W2896457183","https://openalex.org/W2996428491","https://openalex.org/W3034429256","https://openalex.org/W3094502228","https://openalex.org/W3136416617","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3170863103","https://openalex.org/W4214493665","https://openalex.org/W4254912792","https://openalex.org/W4281677079","https://openalex.org/W4292779060","https://openalex.org/W4297775537","https://openalex.org/W4313156423","https://openalex.org/W4385245566","https://openalex.org/W6737664043","https://openalex.org/W6753640285","https://openalex.org/W6768021236","https://openalex.org/W6774314701","https://openalex.org/W6778883912","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6796761347","https://openalex.org/W6803870738","https://openalex.org/W6838672995"],"related_works":["https://openalex.org/W2058965144","https://openalex.org/W2164382479","https://openalex.org/W2146343568","https://openalex.org/W98480971","https://openalex.org/W2150291671","https://openalex.org/W2013643406","https://openalex.org/W2027972911","https://openalex.org/W2157978810","https://openalex.org/W4391547476","https://openalex.org/W3157543420"],"abstract_inverted_index":{"Self-supervised":[0],"pre-training":[1,16],"has":[2],"been":[3],"widely":[4],"utilized":[5],"on":[6,17,96,126,165],"various":[7],"vision":[8],"tasks":[9,128],"and":[10,25,61,132,147,149],"gains":[11],"a":[12,21,35,116,151,161],"great":[13],"success.":[14],"However,":[15],"big":[18],"datasets":[19],"suffers":[20],"lengthy":[22],"training":[23,140],"schedule":[24],"large":[26],"memory":[27],"consumption.":[28],"To":[29,44],"alleviate":[30],"these":[31],"problems,":[32],"we":[33],"propose":[34],"light-weighted":[36],"model":[37,91],"called":[38,84],"Convolutional":[39],"Lite":[40],"Masked":[41],"AutoEncoder":[42],"(CLMAE).":[43],"improve":[45],"the":[46,50,66,76,97,109,122,130,139],"convergence":[47],"speed":[48],"of":[49,118,135,153],"transformer":[51],"during":[52],"pre-training.":[53],"We":[54,99],"introduce":[55],"two-stage":[56],"convolutional":[57],"progressive":[58],"patch":[59],"embedding":[60],"an":[62],"additional":[63],"convolution":[64],"in":[65,75],"feed-forward":[67],"layer,":[68],"which":[69,89,137],"promote":[70],"better":[71],"correlation":[72],"among":[73,104],"patches":[74],"spatial":[77],"dimensions.":[78],"The":[79],"most":[80],"important":[81],"design":[82],"is":[83],"cross-layer":[85],"parameter":[86,110],"sharing":[87,102],"mechanism,":[88],"reduces":[90,150],"parameters":[92,103,154],"with":[93,160],"little":[94],"impact":[95],"performance.":[98],"find":[100],"that":[101,120],"layers":[105],"not":[106],"only":[107],"improves":[108],"efficiency,":[111],"but":[112],"also":[113],"acts":[114],"as":[115],"form":[117],"regularization":[119],"stabilizes":[121],"training.":[123],"Experimental":[124],"results":[125],"downstream":[127],"show":[129],"effectiveness":[131],"generalization":[133],"ability":[134],"CLMAE,":[136],"accelerates":[138],"process":[141],"significantly":[142],"(by":[143,155],"5\u00d7":[144],"for":[145,158],"ViT-B":[146],"MAE)":[148],"quarter":[152],"25M":[156],"fewer":[157],"ViT-B),":[159],"competitive":[162],"accuracy":[163],"(82.8%":[164],"ImageNet-1K).":[166]},"counts_by_year":[],"updated_date":"2025-12-21T01:58:51.020947","created_date":"2025-10-10T00:00:00"}