{"id":"https://openalex.org/W4389104669","doi":"https://doi.org/10.1109/tpami.2023.3336525","title":"Contrastive Masked Autoencoders are Stronger Vision Learners","display_name":"Contrastive Masked Autoencoders are Stronger Vision Learners","publication_year":2023,"publication_date":"2023-11-28","ids":{"openalex":"https://openalex.org/W4389104669","doi":"https://doi.org/10.1109/tpami.2023.3336525","pmid":"https://pubmed.ncbi.nlm.nih.gov/38015699"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2023.3336525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3336525","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/A5103193409","display_name":"Zhicheng Huang","orcid":"https://orcid.org/0000-0001-6532-7643"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhicheng Huang","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6532-7643","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100668699","display_name":"Xiaojie Jin","orcid":"https://orcid.org/0000-0002-7850-1353"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaojie Jin","raw_affiliation_strings":["Bytedance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7850-1353","affiliations":[{"raw_affiliation_string":"Bytedance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065936389","display_name":"Cheng-Ze Lu","orcid":"https://orcid.org/0000-0002-8225-6311"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chengze Lu","raw_affiliation_strings":["School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8225-6311","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040392623","display_name":"Qibin Hou","orcid":"https://orcid.org/0000-0002-8388-8708"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Qibin Hou","raw_affiliation_strings":["School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0002-8388-8708","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037131575","display_name":"Ming\u2010Ming Cheng","orcid":"https://orcid.org/0000-0001-5550-8758"},"institutions":[{"id":"https://openalex.org/I205237279","display_name":"Nankai University","ror":"https://ror.org/01y1kjr75","country_code":"CN","type":"education","lineage":["https://openalex.org/I205237279"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Ming-Ming Cheng","raw_affiliation_strings":["School of Computer Science, Nankai University, Tianjin, China"],"raw_orcid":"https://orcid.org/0000-0001-5550-8758","affiliations":[{"raw_affiliation_string":"School of Computer Science, Nankai University, Tianjin, China","institution_ids":["https://openalex.org/I205237279"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5016681542","display_name":"Dongmei Fu","orcid":"https://orcid.org/0000-0003-3918-9448"},"institutions":[{"id":"https://openalex.org/I92403157","display_name":"University of Science and Technology Beijing","ror":"https://ror.org/02egmk993","country_code":"CN","type":"education","lineage":["https://openalex.org/I92403157"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dongmei Fu","raw_affiliation_strings":["School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-3918-9448","affiliations":[{"raw_affiliation_string":"School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing, China","institution_ids":["https://openalex.org/I92403157"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047385834","display_name":"Xiaohui Shen","orcid":"https://orcid.org/0000-0001-7739-339X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xiaohui Shen","raw_affiliation_strings":["Bytedance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-7739-339X","affiliations":[{"raw_affiliation_string":"Bytedance Inc., Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100668696","display_name":"Jiashi Feng","orcid":"https://orcid.org/0000-0001-6843-0064"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jiashi Feng","raw_affiliation_strings":["Bytedance Inc., Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6843-0064","affiliations":[{"raw_affiliation_string":"Bytedance Inc., Beijing, China","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":15.6273,"has_fulltext":false,"cited_by_count":159,"citation_normalized_percentile":{"value":0.99620946,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"46","issue":"4","first_page":"2506","last_page":"2517"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9969000220298767,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9965000152587891,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7096635103225708},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.65456223487854},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5612793564796448},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.41367676854133606},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.39082658290863037},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.33392074704170227}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7096635103225708},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.65456223487854},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5612793564796448},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.41367676854133606},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.39082658290863037},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.33392074704170227}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2023.3336525","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2023.3336525","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:38015699","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/38015699","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":[{"score":0.6899999976158142,"display_name":"Reduced inequalities","id":"https://metadata.un.org/sdg/10"}],"awards":[{"id":"https://openalex.org/G6285826764","display_name":null,"funder_award_id":"62273034","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":77,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2138621090","https://openalex.org/W2147800946","https://openalex.org/W2161969291","https://openalex.org/W2171590421","https://openalex.org/W2321533354","https://openalex.org/W2326925005","https://openalex.org/W2331143823","https://openalex.org/W2507296351","https://openalex.org/W2622263826","https://openalex.org/W2797977484","https://openalex.org/W2798991696","https://openalex.org/W2883725317","https://openalex.org/W2884822772","https://openalex.org/W2896457183","https://openalex.org/W2908510526","https://openalex.org/W2963150697","https://openalex.org/W2987741655","https://openalex.org/W2989676862","https://openalex.org/W2992308087","https://openalex.org/W3035524453","https://openalex.org/W3094502228","https://openalex.org/W3108655343","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3170863103","https://openalex.org/W3171007011","https://openalex.org/W3215434919","https://openalex.org/W3216272314","https://openalex.org/W4221144677","https://openalex.org/W4226095806","https://openalex.org/W4280617157","https://openalex.org/W4281702809","https://openalex.org/W4281875059","https://openalex.org/W4286695273","https://openalex.org/W4297808394","https://openalex.org/W4312312750","https://openalex.org/W4312804044","https://openalex.org/W4312891522","https://openalex.org/W4313156423","https://openalex.org/W4313158203","https://openalex.org/W4320458322","https://openalex.org/W4382467347","https://openalex.org/W4385245566","https://openalex.org/W4386072059","https://openalex.org/W4386076385","https://openalex.org/W4386221015","https://openalex.org/W6631943919","https://openalex.org/W6675401909","https://openalex.org/W6679792166","https://openalex.org/W6682132143","https://openalex.org/W6682962330","https://openalex.org/W6726497184","https://openalex.org/W6739622702","https://openalex.org/W6745136726","https://openalex.org/W6754278344","https://openalex.org/W6755207826","https://openalex.org/W6757817989","https://openalex.org/W6763416564","https://openalex.org/W6779879114","https://openalex.org/W6779997284","https://openalex.org/W6784333009","https://openalex.org/W6790978476","https://openalex.org/W6791742336","https://openalex.org/W6795754764","https://openalex.org/W6796761347","https://openalex.org/W6804160461","https://openalex.org/W6804229649","https://openalex.org/W6804608498","https://openalex.org/W6810107437","https://openalex.org/W6838637664","https://openalex.org/W6838673894","https://openalex.org/W6838961708","https://openalex.org/W6839306587","https://openalex.org/W6844194202","https://openalex.org/W6849575128"],"related_works":["https://openalex.org/W2772917594","https://openalex.org/W2036807459","https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"Masked":[0,38],"image":[1,62,200],"modeling":[2],"(MIM)":[3,64],"has":[4],"achieved":[5],"promising":[6],"results":[7,223],"on":[8,195,213,218],"various":[9],"vision":[10,30,52],"tasks.":[11],"However,":[12],"the":[13,91,99,109,130,134,180,192],"limited":[14],"discriminability":[15,80,136],"of":[16,87,118,169,199],"learned":[17],"representation":[18,181],"manifests":[19],"there":[20],"is":[21,94,102],"still":[22],"plenty":[23],"to":[24,121,173],"go":[25],"for":[26,46,158,166],"making":[27],"a":[28,41,103],"stronger":[29],"learner.":[31],"Towards":[32],"this":[33],"goal,":[34],"we":[35],"propose":[36],"Contrastive":[37],"Autoencoders":[39],"(CMAE),":[40],"new":[42,153],"self-supervised":[43],"pre-training":[44],"method":[45],"learning":[47,58,139],"more":[48],"comprehensive":[49],"and":[50,60,73,81,98,163,183,204,215,226],"capable":[51],"representations.":[53],"By":[54],"elaboratively":[55],"unifying":[56],"contrastive":[57,138,170],"(CL)":[59],"masked":[61,119],"model":[63],"through":[65],"novel":[66,175],"designs,":[67,176],"CMAE":[68,85,150,177,190],"leverages":[69],"their":[70],"respective":[71],"advantages":[72],"learns":[74],"representations":[75,117],"with":[76,129,140,148],"both":[77],"strong":[78],"instance":[79],"local":[82],"perceptibility.":[83],"Specifically,":[84],"consists":[86],"two":[88,152],"branches":[89],"where":[90],"online":[92,110,142],"branch":[93,101],"an":[95],"asymmetric":[96],"encoder-decoder":[97],"momentum":[100,104,126],"updated":[105],"encoder.":[106],"During":[107],"training,":[108],"encoder":[111],"reconstructs":[112],"original":[113],"images":[114,120],"from":[115],"latent":[116],"learn":[122],"holistic":[123],"features.":[124],"The":[125],"encoder,":[127],"fed":[128],"full":[131],"images,":[132],"enhances":[133],"feature":[135,164],"via":[137],"its":[141,187],"counterpart.":[143,189],"To":[144],"make":[145],"CL":[146],"compatible":[147],"MIM,":[149],"introduces":[151],"components,":[154],"i.e.,":[155],"pixel":[156],"shifting":[157],"generating":[159],"plausible":[160],"positive":[161],"views":[162],"decoder":[165],"complementing":[167],"features":[168],"pairs.":[171],"Thanks":[172],"these":[174],"effectively":[178],"improves":[179],"quality":[182],"transfer":[184],"performance":[185,194],"over":[186],"MIM":[188],"achieves":[191,209],"state-of-the-art":[193],"highly":[196],"competitive":[197],"benchmarks":[198],"classification,":[201],"semantic":[202],"segmentation":[203],"object":[205],"detection.":[206],"Notably,":[207],"CMAE-Base":[208],"85.3%":[210],"top-1":[211],"accuracy":[212],"ImageNet":[214],"52.5%":[216],"mIoU":[217],"ADE20k,":[219],"surpassing":[220],"previous":[221],"best":[222],"by":[224],"0.7%":[225],"1.8%":[227],"respectively.":[228]},"counts_by_year":[{"year":2026,"cited_by_count":24},{"year":2025,"cited_by_count":67},{"year":2024,"cited_by_count":49},{"year":2023,"cited_by_count":19}],"updated_date":"2026-07-15T18:14:33.161393","created_date":"2025-10-10T00:00:00"}