{"id":"https://openalex.org/W4386025755","doi":"https://doi.org/10.1109/tmm.2023.3306840","title":"Disjoint Masking With Joint Distillation for Efficient Masked Image Modeling","display_name":"Disjoint Masking With Joint Distillation for Efficient Masked Image Modeling","publication_year":2023,"publication_date":"2023-08-21","ids":{"openalex":"https://openalex.org/W4386025755","doi":"https://doi.org/10.1109/tmm.2023.3306840"},"language":"en","primary_location":{"id":"doi:10.1109/tmm.2023.3306840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3306840","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/A5100606129","display_name":"Xin Ma","orcid":"https://orcid.org/0000-0002-1256-1767"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Xin Ma","raw_affiliation_strings":["School of Information and Communication Engineering, Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-1256-1767","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100633842","display_name":"Chang Liu","orcid":"https://orcid.org/0000-0001-6747-0646"},"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":"Chang Liu","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6747-0646","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045886141","display_name":"Chunyu Xie","orcid":"https://orcid.org/0009-0002-6607-8209"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chunyu Xie","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0009-0002-6607-8209","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100600271","display_name":"Long Ye","orcid":"https://orcid.org/0000-0002-3562-5612"},"institutions":[{"id":"https://openalex.org/I75689368","display_name":"Communication University of China","ror":"https://ror.org/04facbs33","country_code":"CN","type":"education","lineage":["https://openalex.org/I75689368"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Long Ye","raw_affiliation_strings":["School of Information and Communication Engineering, Communication University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-3562-5612","affiliations":[{"raw_affiliation_string":"School of Information and Communication Engineering, Communication University of China, Beijing, China","institution_ids":["https://openalex.org/I75689368"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040753258","display_name":"Yafeng Deng","orcid":"https://orcid.org/0000-0003-2416-6913"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Yafeng Deng","raw_affiliation_strings":["360 AI Research, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2416-6913","affiliations":[{"raw_affiliation_string":"360 AI Research, Beijing, China","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5024401174","display_name":"Xiangyang Ji","orcid":"https://orcid.org/0000-0002-7333-9975"},"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":"Xiangyang Ji","raw_affiliation_strings":["Department of Automation, Tsinghua University, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-7333-9975","affiliations":[{"raw_affiliation_string":"Department of Automation, Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100606129"],"corresponding_institution_ids":["https://openalex.org/I75689368"],"apc_list":null,"apc_paid":null,"fwci":1.8745,"has_fulltext":false,"cited_by_count":11,"citation_normalized_percentile":{"value":0.88478077,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":99},"biblio":{"volume":"26","issue":null,"first_page":"3077","last_page":"3087"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987999796867371,"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"}},"topics":[{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987999796867371,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9986000061035156,"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/T10531","display_name":"Advanced Vision and Imaging","score":0.9900000095367432,"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":0.6903436183929443},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5987613201141357},{"id":"https://openalex.org/keywords/subnetwork","display_name":"Subnetwork","score":0.5397483110427856},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5352613925933838},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4626162350177765},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3633289337158203},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3256702721118927},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3230496644973755},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1875457465648651},{"id":"https://openalex.org/keywords/discrete-mathematics","display_name":"Discrete mathematics","score":0.16131633520126343}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6903436183929443},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5987613201141357},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.5397483110427856},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5352613925933838},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4626162350177765},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3633289337158203},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3256702721118927},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3230496644973755},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1875457465648651},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.16131633520126343},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tmm.2023.3306840","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tmm.2023.3306840","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":[],"awards":[{"id":"https://openalex.org/G104419513","display_name":null,"funder_award_id":"61971383","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4779183083","display_name":null,"funder_award_id":"61827804","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6181518436","display_name":null,"funder_award_id":"2023M731964","funder_id":"https://openalex.org/F4320321543","funder_display_name":"China Postdoctoral Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321543","display_name":"China Postdoctoral Science Foundation","ror":"https://ror.org/0426zh255"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":76,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2108598243","https://openalex.org/W2161969291","https://openalex.org/W2622263826","https://openalex.org/W2737258237","https://openalex.org/W2757910899","https://openalex.org/W2763898096","https://openalex.org/W2806070179","https://openalex.org/W2884711234","https://openalex.org/W2884822772","https://openalex.org/W2901541570","https://openalex.org/W2940460948","https://openalex.org/W2957236078","https://openalex.org/W3035452548","https://openalex.org/W3037466839","https://openalex.org/W3121523901","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3204548263","https://openalex.org/W4214634256","https://openalex.org/W4281385110","https://openalex.org/W4281393357","https://openalex.org/W4281702809","https://openalex.org/W4282004442","https://openalex.org/W4287165635","https://openalex.org/W4288581820","https://openalex.org/W4292112947","https://openalex.org/W4301914798","https://openalex.org/W4308503280","https://openalex.org/W4309398427","https://openalex.org/W4311556331","https://openalex.org/W4312262772","https://openalex.org/W4312312750","https://openalex.org/W4312535427","https://openalex.org/W4312804044","https://openalex.org/W4313156423","https://openalex.org/W4313158203","https://openalex.org/W4382465386","https://openalex.org/W4385245566","https://openalex.org/W4386071687","https://openalex.org/W4386221015","https://openalex.org/W4386566638","https://openalex.org/W6726497184","https://openalex.org/W6726983090","https://openalex.org/W6738534199","https://openalex.org/W6739622702","https://openalex.org/W6744513255","https://openalex.org/W6753209298","https://openalex.org/W6756439839","https://openalex.org/W6757817989","https://openalex.org/W6758139636","https://openalex.org/W6765518731","https://openalex.org/W6771917389","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6790978476","https://openalex.org/W6791353385","https://openalex.org/W6795737119","https://openalex.org/W6796761347","https://openalex.org/W6797371478","https://openalex.org/W6799515669","https://openalex.org/W6804160461","https://openalex.org/W6810007534","https://openalex.org/W6810784583","https://openalex.org/W6810914850","https://openalex.org/W6838332116","https://openalex.org/W6838614222","https://openalex.org/W6838673894","https://openalex.org/W6838710837","https://openalex.org/W6838961708","https://openalex.org/W6839263979","https://openalex.org/W6841885045","https://openalex.org/W6845452229","https://openalex.org/W6846629391","https://openalex.org/W6846740302"],"related_works":["https://openalex.org/W2060724872","https://openalex.org/W2082094785","https://openalex.org/W2202198356","https://openalex.org/W3087203342","https://openalex.org/W2377184161","https://openalex.org/W228984114","https://openalex.org/W2090026684","https://openalex.org/W4226360758","https://openalex.org/W2907567977","https://openalex.org/W3153861134"],"abstract_inverted_index":{"Masked":[0],"image":[1,73,91],"modeling":[2],"(MIM)":[3],"has":[4],"shown":[5],"great":[6],"promise":[7],"for":[8,15,87,127],"self-supervised":[9],"learning":[10,16,121],"(SSL)":[11],"yet":[12,38,139],"been":[13],"criticized":[14],"inefficiency.":[17],"We":[18],"believe":[19],"the":[20,78,83,94,136,142,174],"insufficient":[21],"utilization":[22],"of":[23,85,97],"training":[24,41,128,137,154],"signals":[25],"should":[26],"be":[27],"responsible.":[28],"To":[29],"alleviate":[30],"this":[31],"issue,":[32],"we":[33,66,104],"introduce":[34],"a":[35,75,106],"conceptually":[36],"simple":[37],"learning-efficient":[39],"MIM":[40],"scheme,":[42],"termed":[43],"<italic":[44,48,53,57,196],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[45,49,54,58,159,183,197],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">D</i>":[46,59],"isjoint":[47],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">M</i>":[50],"asking":[51],"with":[52,77,119,151,207],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">J</i>":[55],"oint":[56],"istillation":[60],"(DMJD).":[61],"For":[62,100],"disjoint":[63,79],"masking":[64,95],"(DM),":[65],"sequentially":[67],"sample":[68],"multiple":[69],"masked":[70],"views":[71],"per":[72],"in":[74,89,124],"mini-batch":[76],"regulation":[80],"to":[81,110,164,180],"raise":[82],"usage":[84],"tokens":[86,118],"reconstruction":[88],"each":[90,98],"while":[92],"keeping":[93],"rate":[96],"view.":[99],"joint":[101],"distillation":[102],"(JD),":[103],"adopt":[105],"dual":[107],"branch":[108],"architecture":[109],"respectively":[111],"predict":[112],"invisible":[113],"(masked)":[114],"and":[115,132],"visible":[116],"(unmasked)":[117],"superior":[120,204],"targets.":[122],"Rooting":[123],"orthogonal":[125],"perspectives":[126],"efficiency":[129],"improvement,":[130],"DM":[131,147],"JD":[133],"cooperatively":[134],"accelerate":[135],"convergence":[138],"not":[140],"sacrificing":[141],"model":[143],"generalization":[144,205],"ability.":[145],"Concretely,":[146],"can":[148],"train":[149],"ViT":[150],"less":[152,162],"effective":[153],"epochs":[155],"(at":[156],"most":[157],"<inline-formula":[158,182],"xmlns:xlink=\"http://www.w3.org/1999/xlink\"><tex-math":[160,184],"notation=\"LaTeX\">$3.7\\times$</tex-math></inline-formula>":[161],"time-consuming)":[163],"report":[165],"competitive":[166],"performance.":[167],"With":[168],"JD,":[169],"our":[170,200],"DMJD":[171,201],"clearly":[172],"improves":[173],"linear":[175],"probing":[176],"classification":[177],"accuracy,":[178],"up":[179],"3.4":[181],"notation=\"LaTeX\">$\\%$</tex-math></inline-formula>":[185],".":[186],"On":[187],"fine-grained":[188],"downstream":[189],"tasks":[190],"like":[191],"semantic":[192],"segmentation,":[193],"object":[194],"detection,":[195],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">etc.</i>":[198],",":[199],"also":[202],"presents":[203],"compared":[206],"state-of-the-art":[208],"SSL":[209],"methods.":[210]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":7},{"year":2024,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}