{"id":"https://openalex.org/W4400447864","doi":"https://doi.org/10.1109/tnnls.2024.3419898","title":"Teaching Masked Autoencoder With Strong Augmentations","display_name":"Teaching Masked Autoencoder With Strong Augmentations","publication_year":2024,"publication_date":"2024-07-09","ids":{"openalex":"https://openalex.org/W4400447864","doi":"https://doi.org/10.1109/tnnls.2024.3419898","pmid":"https://pubmed.ncbi.nlm.nih.gov/38980783"},"language":"en","primary_location":{"id":"doi:10.1109/tnnls.2024.3419898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3419898","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","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/A5100281939","display_name":"Rui Zhu","orcid":"https://orcid.org/0000-0001-8892-247X"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Rui Zhu","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0001-8892-247X","affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054533256","display_name":"Yalong Bai","orcid":"https://orcid.org/0000-0002-8416-9027"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yalong Bai","raw_affiliation_strings":["Du Xiaoman, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8416-9027","affiliations":[{"raw_affiliation_string":"Du Xiaoman, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088760097","display_name":"Ting Yao","orcid":"https://orcid.org/0000-0001-7587-101X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ting Yao","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7587-101X","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032552506","display_name":"Jingen Liu","orcid":"https://orcid.org/0000-0003-3133-3644"},"institutions":[{"id":"https://openalex.org/I1311688040","display_name":"Amazon (United States)","ror":"https://ror.org/04mv4n011","country_code":"US","type":"company","lineage":["https://openalex.org/I1311688040"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jingen Liu","raw_affiliation_strings":["Amazon, New York, NY, USA"],"raw_orcid":"https://orcid.org/0000-0003-3133-3644","affiliations":[{"raw_affiliation_string":"Amazon, New York, NY, USA","institution_ids":["https://openalex.org/I1311688040"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087628708","display_name":"Zhenglong Sun","orcid":"https://orcid.org/0000-0002-8135-1659"},"institutions":[{"id":"https://openalex.org/I4210116924","display_name":"Chinese University of Hong Kong, Shenzhen","ror":"https://ror.org/02d5ks197","country_code":"CN","type":"education","lineage":["https://openalex.org/I177725633","https://openalex.org/I180726961","https://openalex.org/I4210116924"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenglong Sun","raw_affiliation_strings":["School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-8135-1659","affiliations":[{"raw_affiliation_string":"School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen, China","institution_ids":["https://openalex.org/I4210116924"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5017597537","display_name":"Tao Mei","orcid":"https://orcid.org/0000-0003-2497-7732"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Tao Mei","raw_affiliation_strings":["HiDream.ai, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2497-7732","affiliations":[{"raw_affiliation_string":"HiDream.ai, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002277899","display_name":"Chang Wen Chen","orcid":"https://orcid.org/0000-0002-6720-234X"},"institutions":[{"id":"https://openalex.org/I14243506","display_name":"Hong Kong Polytechnic University","ror":"https://ror.org/0030zas98","country_code":"HK","type":"education","lineage":["https://openalex.org/I14243506"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chang Wen Chen","raw_affiliation_strings":["Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hung Hom, China","Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China"],"raw_orcid":"https://orcid.org/0000-0002-6720-234X","affiliations":[{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, Hung Hom, China","institution_ids":["https://openalex.org/I14243506"]},{"raw_affiliation_string":"Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China","institution_ids":["https://openalex.org/I14243506"]}]}],"institutions":[],"countries_distinct_count":3,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6486,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.69855837,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":97},"biblio":{"volume":"36","issue":"5","first_page":"9550","last_page":"9564"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.41100001335144043,"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"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.41100001335144043,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.37950000166893005,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.3743000030517578,"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/autoencoder","display_name":"Autoencoder","score":0.9002498388290405},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.48578977584838867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4136025309562683},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3471231162548065},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.0977623462677002}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.9002498388290405},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.48578977584838867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4136025309562683},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3471231162548065},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.0977623462677002}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tnnls.2024.3419898","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tnnls.2024.3419898","pdf_url":null,"source":{"id":"https://openalex.org/S4210175523","display_name":"IEEE Transactions on Neural Networks and Learning Systems","issn_l":"2162-237X","issn":["2162-237X","2162-2388"],"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 Neural Networks and Learning Systems","raw_type":"journal-article"},{"id":"pmid:38980783","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38980783","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 neural networks and learning systems","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G6388710455","display_name":null,"funder_award_id":"RCYX20200714114736115","funder_id":"https://openalex.org/F4320336569","funder_display_name":"Shenzhen Science and Technology Innovation Program"}],"funders":[{"id":"https://openalex.org/F4320336569","display_name":"Shenzhen Science and Technology Innovation Program","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":91,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1836533770","https://openalex.org/W1933349210","https://openalex.org/W2025768430","https://openalex.org/W2108598243","https://openalex.org/W2138011018","https://openalex.org/W2138621090","https://openalex.org/W2171590421","https://openalex.org/W2183341477","https://openalex.org/W2507296351","https://openalex.org/W2533598788","https://openalex.org/W2842511635","https://openalex.org/W2883725317","https://openalex.org/W2884822772","https://openalex.org/W2965373594","https://openalex.org/W2987741655","https://openalex.org/W2987861506","https://openalex.org/W2992308087","https://openalex.org/W3035524453","https://openalex.org/W3035682985","https://openalex.org/W3035725276","https://openalex.org/W3112889778","https://openalex.org/W3133518153","https://openalex.org/W3145450063","https://openalex.org/W3158714121","https://openalex.org/W3159481202","https://openalex.org/W3168822201","https://openalex.org/W3169827396","https://openalex.org/W3171007011","https://openalex.org/W3172615411","https://openalex.org/W3174415835","https://openalex.org/W3176276772","https://openalex.org/W3201916717","https://openalex.org/W3203752493","https://openalex.org/W3207924272","https://openalex.org/W4214634256","https://openalex.org/W4214642259","https://openalex.org/W4282913028","https://openalex.org/W4288325606","https://openalex.org/W4312262772","https://openalex.org/W4312309398","https://openalex.org/W4312764321","https://openalex.org/W4312784228","https://openalex.org/W4312891165","https://openalex.org/W4312891522","https://openalex.org/W4312939373","https://openalex.org/W4313019631","https://openalex.org/W4313125078","https://openalex.org/W4313156423","https://openalex.org/W4313158203","https://openalex.org/W4323065138","https://openalex.org/W4367663188","https://openalex.org/W4375839990","https://openalex.org/W4382465386","https://openalex.org/W4386076428","https://openalex.org/W4387092606","https://openalex.org/W4388692326","https://openalex.org/W4402727704","https://openalex.org/W6683825394","https://openalex.org/W6684809622","https://openalex.org/W6724365450","https://openalex.org/W6726497184","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6761190116","https://openalex.org/W6771917389","https://openalex.org/W6774314701","https://openalex.org/W6777179611","https://openalex.org/W6777265123","https://openalex.org/W6779879114","https://openalex.org/W6779997284","https://openalex.org/W6785324187","https://openalex.org/W6786093290","https://openalex.org/W6788135285","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6791713434","https://openalex.org/W6795818041","https://openalex.org/W6796761347","https://openalex.org/W6804160461","https://openalex.org/W6809260186","https://openalex.org/W6810400276","https://openalex.org/W6810423238","https://openalex.org/W6838706884","https://openalex.org/W6838816370","https://openalex.org/W6839286798","https://openalex.org/W6840202747","https://openalex.org/W6841478064","https://openalex.org/W6845452229","https://openalex.org/W6846091820","https://openalex.org/W6849294424"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W3013693939","https://openalex.org/W2159052453","https://openalex.org/W2566616303","https://openalex.org/W3131327266","https://openalex.org/W2734887215","https://openalex.org/W4297051394","https://openalex.org/W4220775285","https://openalex.org/W3204019825"],"abstract_inverted_index":{"Masked":[0],"autoencoder":[1,110],"(MAE)":[2],"has":[3],"been":[4],"regarded":[5],"as":[6,139],"a":[7,104,116,120],"capable":[8],"self-supervised":[9],"learner":[10],"for":[11],"various":[12],"downstream":[13,183],"tasks.":[14,184],"Nevertheless,":[15],"the":[16,32,56,66,78,86,131,135,148,158,173,205,217],"model":[17,174],"still":[18],"lacks":[19],"high-level":[20,145],"discriminability,":[21],"which":[22,113],"results":[23],"in":[24,41,50],"poor":[25],"linear":[26,186],"probing":[27,187],"performance.":[28,79],"In":[29,80],"view":[30,138],"of":[31,88,115,216,223],"fact":[33],"that":[34,63,153,172],"strong":[35,48,61,72,89,137],"augmentation":[36,49,62,73],"plays":[37],"an":[38,140],"essential":[39],"role":[40],"contrastive":[42],"learning,":[43],"can":[44,156],"we":[45,83,102],"capitalize":[46],"on":[47,189,201,207],"MAE?":[51],"The":[52,123],"difficulty":[53],"originates":[54],"from":[55,193],"pixel":[57],"uncertainty":[58],"caused":[59],"by":[60,176],"may":[64],"affect":[65],"reconstruction,":[67],"and":[68,119,130,221,226],"thus,":[69],"directly":[70],"introducing":[71],"into":[74,85],"MAE":[75,94,200],"often":[76],"hurts":[77],"this":[81,100],"article,":[82],"delve":[84],"potential":[87],"augmented":[90],"views":[91],"to":[92,143,196],"enhance":[93],"while":[95],"maintaining":[96],"MAE's":[97,127],"advantages.":[98],"To":[99],"end,":[101],"propose":[103],"simple":[105],"yet":[106],"effective":[107],"masked":[108],"Siamese":[109],"(MSA)":[111],"model,":[112],"consists":[114],"student":[117,124,149],"branch":[118,125,133],"teacher":[121,132,142],"branch.":[122,150],"derives":[126],"advanced":[128],"architecture,":[129],"treats":[134],"unmasked":[136],"exemplary":[141],"impose":[144],"discrimination":[146],"onto":[147],"We":[151],"demonstrate":[152],"our":[154],"MSA":[155,177,194],"improve":[157],"model's":[159],"spatial":[160],"perception":[161],"capability":[162],"and,":[163],"therefore,":[164],"globally":[165],"favors":[166],"interimage":[167],"discrimination.":[168],"Empirical":[169],"evidence":[170],"shows":[171],"pretrained":[175],"provides":[178],"superior":[179],"performances":[180],"across":[181],"different":[182],"Notably,":[185],"performance":[188],"frozen":[190],"features":[191],"extracted":[192],"leads":[195],"6.1%":[197],"gains":[198],"over":[199],"ImageNet-1k.":[202],"Fine-tuning":[203],"(FT)":[204],"network":[206],"VQAv2":[208],"task":[209],"finally":[210],"achieves":[211],"67.4%":[212],"accuracy,":[213],"outperforming":[214],"1.6%":[215],"supervised":[218],"method":[219],"DeiT":[220],"1.2%":[222],"MAE.":[224],"Codes":[225],"models":[227],"are":[228],"available":[229],"at":[230],"https://github.com/KimSoybean/MSA.":[231]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T09:40:50.615796","created_date":"2025-10-10T00:00:00"}