{"id":"https://openalex.org/W4415482268","doi":"https://doi.org/10.1109/tcsvt.2025.3625076","title":"Self-Supervised Disentangled Representation Learning via Compositional Invariance","display_name":"Self-Supervised Disentangled Representation Learning via Compositional Invariance","publication_year":2025,"publication_date":"2025-10-23","ids":{"openalex":"https://openalex.org/W4415482268","doi":"https://doi.org/10.1109/tcsvt.2025.3625076"},"language":null,"primary_location":{"id":"doi:10.1109/tcsvt.2025.3625076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3625076","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","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/A5086908355","display_name":"Haoqiang Chen","orcid":"https://orcid.org/0009-0000-7330-4230"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haoqiang Chen","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0000-7330-4230","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004658466","display_name":"Jianxiang Sun","orcid":"https://orcid.org/0000-0003-2957-5257"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianxiang Sun","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0003-2957-5257","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100613442","display_name":"Yadong Liu","orcid":"https://orcid.org/0000-0002-6322-3944"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yadong Liu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0002-6322-3944","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Hao Shi","orcid":"https://orcid.org/0009-0007-2962-4078"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Shi","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0009-0007-2962-4078","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5071074935","display_name":"Dewen Hu","orcid":"https://orcid.org/0000-0001-7357-0053"},"institutions":[{"id":"https://openalex.org/I170215575","display_name":"National University of Defense Technology","ror":"https://ror.org/05d2yfz11","country_code":"CN","type":"education","lineage":["https://openalex.org/I170215575"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Dewen Hu","raw_affiliation_strings":["College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China"],"raw_orcid":"https://orcid.org/0000-0001-7357-0053","affiliations":[{"raw_affiliation_string":"College of Intelligence Science and Technology, National University of Defense Technology, Changsha, China","institution_ids":["https://openalex.org/I170215575"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I170215575"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25009611,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"36","issue":"3","first_page":"3201","last_page":"3214"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.9373000264167786,"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/T10057","display_name":"Face and Expression Recognition","score":0.9373000264167786,"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/T10201","display_name":"Speech Recognition and Synthesis","score":0.9065999984741211,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/interpretability","display_name":"Interpretability","score":0.7942000031471252},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5820000171661377},{"id":"https://openalex.org/keywords/generalizability-theory","display_name":"Generalizability theory","score":0.5767999887466431},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.49790000915527344},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.46320000290870667},{"id":"https://openalex.org/keywords/cognitive-reframing","display_name":"Cognitive reframing","score":0.429500013589859},{"id":"https://openalex.org/keywords/inductive-bias","display_name":"Inductive bias","score":0.3702999949455261},{"id":"https://openalex.org/keywords/cognition","display_name":"Cognition","score":0.3319999873638153}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.7942000031471252},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7188000082969666},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6104999780654907},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5820000171661377},{"id":"https://openalex.org/C27158222","wikidata":"https://www.wikidata.org/wiki/Q5532422","display_name":"Generalizability theory","level":2,"score":0.5767999887466431},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.49790000915527344},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4779999852180481},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.46320000290870667},{"id":"https://openalex.org/C187029079","wikidata":"https://www.wikidata.org/wiki/Q958679","display_name":"Cognitive reframing","level":2,"score":0.429500013589859},{"id":"https://openalex.org/C197352929","wikidata":"https://www.wikidata.org/wiki/Q1074074","display_name":"Inductive bias","level":4,"score":0.3702999949455261},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3504999876022339},{"id":"https://openalex.org/C169900460","wikidata":"https://www.wikidata.org/wiki/Q2200417","display_name":"Cognition","level":2,"score":0.3319999873638153},{"id":"https://openalex.org/C2780695315","wikidata":"https://www.wikidata.org/wiki/Q3799040","display_name":"Unobservable","level":2,"score":0.32350000739097595},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3165999948978424},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.31150001287460327},{"id":"https://openalex.org/C97256817","wikidata":"https://www.wikidata.org/wiki/Q1462316","display_name":"Spurious relationship","level":2,"score":0.29100000858306885},{"id":"https://openalex.org/C177877439","wikidata":"https://www.wikidata.org/wiki/Q7604413","display_name":"Statistical relational learning","level":3,"score":0.2721000015735626},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.26159998774528503},{"id":"https://openalex.org/C105409693","wikidata":"https://www.wikidata.org/wiki/Q5937824","display_name":"Human intelligence","level":2,"score":0.2590000033378601},{"id":"https://openalex.org/C2777723229","wikidata":"https://www.wikidata.org/wiki/Q4367921","display_name":"Learnability","level":2,"score":0.25290000438690186}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/tcsvt.2025.3625076","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tcsvt.2025.3625076","pdf_url":null,"source":{"id":"https://openalex.org/S115173108","display_name":"IEEE Transactions on Circuits and Systems for Video Technology","issn_l":"1051-8215","issn":["1051-8215","1558-2205"],"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 Circuits and Systems for Video Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G5670962352","display_name":null,"funder_award_id":"62036013","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6480039051","display_name":null,"funder_award_id":"T2521006","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8998979053","display_name":null,"funder_award_id":"2024QK2006","funder_id":"https://openalex.org/F4320330206","funder_display_name":"Science and Technology Program of Hunan Province"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320330206","display_name":"Science and Technology Program of Hunan Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":24,"referenced_works":["https://openalex.org/W2163922914","https://openalex.org/W2583591231","https://openalex.org/W2903782687","https://openalex.org/W3035524453","https://openalex.org/W3134309210","https://openalex.org/W3164354101","https://openalex.org/W3171007011","https://openalex.org/W3176726917","https://openalex.org/W4319299836","https://openalex.org/W4360993849","https://openalex.org/W4382449618","https://openalex.org/W4386811774","https://openalex.org/W4387949708","https://openalex.org/W4388145580","https://openalex.org/W4389815697","https://openalex.org/W4393154717","https://openalex.org/W4393159686","https://openalex.org/W4393853176","https://openalex.org/W4401607461","https://openalex.org/W4402774417","https://openalex.org/W4404386031","https://openalex.org/W4404654662","https://openalex.org/W4407449628","https://openalex.org/W4415796825"],"related_works":[],"abstract_inverted_index":{"Images":[0],"serve":[1],"as":[2],"a":[3,32,103],"crucial":[4],"information":[5],"source":[6],"for":[7,189,208],"machine":[8,89,209],"intelligence":[9],"to":[10,16,35,58,111,124,199],"understand":[11],"the":[12,21,60,130,135,180],"world,":[13],"while":[14],"how":[15],"represent":[17],"images":[18,207],"significantly":[19],"impacting":[20],"generalizability":[22],"and":[23,90,170,178,203],"interpretability":[24],"of":[25,41,132,137],"intelligent":[26],"systems.":[27],"Disentangled":[28],"representation":[29],"learning":[30,106,183],"offers":[31],"promising":[33],"approach":[34],"improve":[36],"both":[37,66],"aspects.":[38],"However,":[39],"most":[40],"existing":[42],"methods":[43],"predominantly":[44],"rely":[45],"on":[46,165,168,172,193],"statistical":[47,142],"independence":[48],"assumptions.":[49],"This":[50,144,196],"poses":[51],"two":[52],"key":[53],"limitations:":[54],"first,":[55],"it":[56,71],"fails":[57],"capture":[59],"reality":[61],"that":[62,108],"many":[63],"concepts":[64,78],"are":[65],"disentangled":[67],"yet":[68],"interrelated;":[69],"second,":[70],"conflicts":[72],"with":[73,116,151],"human":[74,91,117],"cognitive":[75,118],"patterns":[76],"where":[77],"naturally":[79],"exhibit":[80],"complex":[81],"dependencies.":[82],"These":[83],"limitations":[84],"further":[85],"hinder":[86],"collaboration":[87],"between":[88],"beings.":[92],"To":[93],"overcome":[94],"these":[95],"limitations,":[96],"we":[97,128],"propose":[98],"Compositional":[99],"Invariant":[100],"Disentanglement":[101],"(CID),":[102],"novel":[104],"self-supervised":[105,182],"method":[107],"enables":[109],"models":[110],"learn":[112],"composable":[113],"representations":[114,205],"aligned":[115],"habits.":[119],"Inspired":[120],"by":[121,163,175],"humans\u2019":[122],"ability":[123],"flexibly":[125],"recombine":[126],"concepts,":[127],"reframe":[129],"definition":[131],"disentanglement":[133,149,156,191],"through":[134],"lens":[136],"compositional":[138],"invariance":[139],"rather":[140],"than":[141],"independence.":[143],"paradigm":[145],"shift":[146],"allows":[147],"effective":[148],"even":[150],"correlated":[152],"factors,":[153],"achieving":[154],"state-of-the-art":[155],"performance":[157],"across":[158],"multiple":[159],"standard":[160],"benchmarks":[161],"(improved":[162],"4.0%":[164],"Shapes3D,":[166],"4.5%":[167],"Dsprites,":[169],"28.6%":[171],"MPI3D).":[173],"Furthermore,":[174],"building":[176],"upon":[177],"extending":[179],"successful":[181],"framework":[184],"BYOL,":[185],"CID":[186],"demonstrates":[187],"potential":[188],"large-scale":[190],"pre-training":[192],"unlabeled":[194],"data.":[195],"work":[197],"contributes":[198],"extracting":[200],"more":[201],"robust":[202],"interpretable":[204],"from":[206],"intelligence.":[210]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-10-23T00:00:00"}