{"id":"https://openalex.org/W7133196023","doi":"https://doi.org/10.1109/access.2026.3669132","title":"Contrastive Learning or Masked Autoencoder? Understanding and Improving Self-Supervised Knowledge Distillation","display_name":"Contrastive Learning or Masked Autoencoder? Understanding and Improving Self-Supervised Knowledge Distillation","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7133196023","doi":"https://doi.org/10.1109/access.2026.3669132"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3669132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3669132","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3669132","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5127813830","display_name":"Taegoo Kang","orcid":null},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Taegoo Kang","raw_affiliation_strings":["Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0009-0002-9869-2393","affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005200603","display_name":"Sung\u2010Ho Bae","orcid":"https://orcid.org/0000-0003-2677-3186"},"institutions":[{"id":"https://openalex.org/I35928602","display_name":"Kyung Hee University","ror":"https://ror.org/01zqcg218","country_code":"KR","type":"education","lineage":["https://openalex.org/I35928602"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Sung-Ho Bae","raw_affiliation_strings":["Department of Artificial Intelligence, Kyung Hee University, Yongin-si, Republic of Korea"],"raw_orcid":"https://orcid.org/0000-0003-2677-3186","affiliations":[{"raw_affiliation_string":"Department of Artificial Intelligence, Kyung Hee University, Yongin-si, Republic of Korea","institution_ids":["https://openalex.org/I35928602"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5057230698","display_name":"Chaoning Zhang","orcid":"https://orcid.org/0000-0001-6007-6099"},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chaoning Zhang","raw_affiliation_strings":["University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":"https://orcid.org/0000-0001-6007-6099","affiliations":[{"raw_affiliation_string":"University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.20516268,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"39472","last_page":"39482"},"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":0.1429000049829483,"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":0.1429000049829483,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.027699999511241913,"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":0.02539999969303608,"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":0.5939000248908997},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.5723000168800354},{"id":"https://openalex.org/keywords/distillation","display_name":"Distillation","score":0.5576000213623047},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.517300009727478},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.4260999858379364},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3375000059604645},{"id":"https://openalex.org/keywords/lying","display_name":"Lying","score":0.33320000767707825},{"id":"https://openalex.org/keywords/lexical-diversity","display_name":"Lexical diversity","score":0.33250001072883606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.718500018119812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6373000144958496},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6141999959945679},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.5939000248908997},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.5723000168800354},{"id":"https://openalex.org/C204030448","wikidata":"https://www.wikidata.org/wiki/Q101017","display_name":"Distillation","level":2,"score":0.5576000213623047},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.517300009727478},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.4260999858379364},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.42579999566078186},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3375000059604645},{"id":"https://openalex.org/C119421448","wikidata":"https://www.wikidata.org/wiki/Q2268776","display_name":"Lying","level":2,"score":0.33320000767707825},{"id":"https://openalex.org/C2781202465","wikidata":"https://www.wikidata.org/wiki/Q18346297","display_name":"Lexical diversity","level":3,"score":0.33250001072883606},{"id":"https://openalex.org/C2777508537","wikidata":"https://www.wikidata.org/wiki/Q7936620","display_name":"Visual reasoning","level":2,"score":0.3321000039577484},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.320499986410141},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.30059999227523804},{"id":"https://openalex.org/C2781316041","wikidata":"https://www.wikidata.org/wiki/Q1230584","display_name":"Diversity (politics)","level":2,"score":0.29420000314712524},{"id":"https://openalex.org/C2777629044","wikidata":"https://www.wikidata.org/wiki/Q614959","display_name":"Contrastive analysis","level":2,"score":0.2808000147342682},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.272599995136261},{"id":"https://openalex.org/C2779321571","wikidata":"https://www.wikidata.org/wiki/Q7936605","display_name":"Visual learning","level":2,"score":0.2605000138282776},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2533000111579895}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3669132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3669132","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:cf48d0a6239e41dea054d859ed4bfd9e","is_oa":true,"landing_page_url":"https://doaj.org/article/cf48d0a6239e41dea054d859ed4bfd9e","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 39472-39482 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3669132","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3669132","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":37,"referenced_works":["https://openalex.org/W753847829","https://openalex.org/W1821462560","https://openalex.org/W1861492603","https://openalex.org/W1965555277","https://openalex.org/W2108598243","https://openalex.org/W2194775991","https://openalex.org/W2321533354","https://openalex.org/W2507296351","https://openalex.org/W2884822772","https://openalex.org/W2963150697","https://openalex.org/W2987861506","https://openalex.org/W3034429256","https://openalex.org/W3035524453","https://openalex.org/W3138516171","https://openalex.org/W3145450063","https://openalex.org/W3159481202","https://openalex.org/W3177096435","https://openalex.org/W3204610735","https://openalex.org/W4214524539","https://openalex.org/W4224075564","https://openalex.org/W4225463624","https://openalex.org/W4226426325","https://openalex.org/W4280557312","https://openalex.org/W4283732568","https://openalex.org/W4312273141","https://openalex.org/W4312446817","https://openalex.org/W4312652289","https://openalex.org/W4312671791","https://openalex.org/W4312764321","https://openalex.org/W4312804044","https://openalex.org/W4313156423","https://openalex.org/W4386065386","https://openalex.org/W4386072286","https://openalex.org/W4386075861","https://openalex.org/W4386076073","https://openalex.org/W4390873298","https://openalex.org/W4392903947"],"related_works":[],"abstract_inverted_index":{"Lying":[0],"at":[1],"the":[2,22,56,129,136],"intersection":[3],"of":[4,60,102,131],"self-supervised":[5,68,179],"learning":[6,62],"(SSL)":[7],"and":[8,90,148,163],"knowledge":[9,69,180],"distillation":[10,130],"(KD),":[11],"Self-supervised":[12],"KD":[13,18],"(SSKD)":[14],"differs":[15],"from":[16,97],"classical":[17],"frameworks":[19],"by":[20,123],"assuming":[21],"teacher":[23,66],"model":[24],"is":[25],"pretrained":[26],"without":[27],"labels.":[28],"As":[29],"SSKD":[30,138],"relies":[31],"on":[32],"SSL-pretrained":[33],"teachers,":[34,45],"recent":[35],"works":[36],"have":[37],"largely":[38],"employed":[39],"masked":[40,47],"image":[41],"modeling":[42],"(MIM)":[43],"based":[44],"especially":[46],"autoencoder":[48],"(MAE).":[49],"In":[50,167],"this":[51,93,124],"work,":[52],"however,":[53],"we":[54,106,127],"explore":[55],"previously":[57],"untapped":[58],"potential":[59],"contrastive":[61],"(CL)":[63],"as":[64],"a":[65,100,175],"in":[67,81,152],"distillation.":[70,181],"Our":[71,142],"findings":[72],"reveal":[73],"that":[74,108],"(1)":[75],"CL-pretrained":[76],"teachers":[77],"outperform":[78],"MIM-pretrained":[79],"ones":[80],"student":[82,95],"training":[83],"due":[84],"to":[85],"their":[86],"richer":[87,117],"semantic":[88,165],"representations,":[89],"(2)":[91],"despite":[92],"advantage,":[94],"distilled":[96],"CL":[98],"exhibit":[99],"lack":[101],"attention":[103,118,133,146],"diversity.":[104],"Remarkably,":[105],"observe":[107],"MAE,":[109],"while":[110],"less":[111],"effective":[112],"for":[113,178],"direct":[114],"distillation,":[115],"exhibits":[116],"patterns":[119],"than":[120],"CL.":[121],"Motivated":[122],"complementary":[125],"property,":[126],"integrate":[128],"MAE":[132],"scores":[134],"into":[135],"CL-based":[137],"framework,":[139],"named":[140],"I-SSKD.":[141],"approach":[143],"effectively":[144],"enhances":[145],"diversity":[147],"demonstrates":[149],"improved":[150],"performance":[151],"downstream":[153],"visual":[154],"recognition":[155],"tasks,":[156],"including":[157],"ImageNet-1K":[158],"classification,":[159],"MS-COCO":[160],"object":[161],"detection,":[162],"ADE20K":[164],"segmentation.":[166],"addition,":[168],"it":[169],"outperforms":[170],"current":[171],"state-of-the-art":[172],"methods,":[173],"establishing":[174],"strong":[176],"baseline":[177]},"counts_by_year":[],"updated_date":"2026-03-20T20:47:17.329874","created_date":"2026-03-03T00:00:00"}