{"id":"https://openalex.org/W7160301115","doi":"https://doi.org/10.1109/wacv61042.2026.00578","title":"Logit-Adjusted Test-Time Adaptation under Partial Class Imbalance","display_name":"Logit-Adjusted Test-Time Adaptation under Partial Class Imbalance","publication_year":2026,"publication_date":"2026-03-06","ids":{"openalex":"https://openalex.org/W7160301115","doi":"https://doi.org/10.1109/wacv61042.2026.00578"},"language":null,"primary_location":{"id":"doi:10.1109/wacv61042.2026.00578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5135289588","display_name":"Thilina Weerasinghe","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Thilina Weerasinghe","raw_affiliation_strings":["RMIT University,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135346687","display_name":"Ruwan Tennakoon","orcid":"https://orcid.org/0000-0001-8909-5728"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Ruwan Tennakoon","raw_affiliation_strings":["RMIT University,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060353361","display_name":"WeiQin Chuah","orcid":"https://orcid.org/0000-0001-6020-4660"},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"WeiQin Chuah","raw_affiliation_strings":["RMIT University,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5130381245","display_name":"Alireza Bab-Hadiashar","orcid":null},"institutions":[{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Alireza Bab-Hadiashar","raw_affiliation_strings":["RMIT University,Australia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"RMIT University,Australia","institution_ids":["https://openalex.org/I82951845"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I82951845"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.45824024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"5977","last_page":"5985"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.12020000070333481,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.12020000070333481,"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/T12676","display_name":"Machine Learning and ELM","score":0.06239999830722809,"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/T10136","display_name":"Statistical Methods and Inference","score":0.041999999433755875,"subfield":{"id":"https://openalex.org/subfields/2613","display_name":"Statistics and Probability"},"field":{"id":"https://openalex.org/fields/26","display_name":"Mathematics"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.4754999876022339},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.2630000114440918},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.25850000977516174},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.23989999294281006},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.23669999837875366}],"concepts":[{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.4754999876022339},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.3984000086784363},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.38909998536109924},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.28679999709129333},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2630000114440918},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.25850000977516174},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.23989999294281006},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.23669999837875366},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.22210000455379486},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.2214999943971634}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/wacv61042.2026.00578","is_oa":false,"landing_page_url":"https://doi.org/10.1109/wacv61042.2026.00578","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2026 IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Climate action","score":0.4926605522632599,"id":"https://metadata.un.org/sdg/13"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W2162651021","https://openalex.org/W2171372399","https://openalex.org/W2549139847","https://openalex.org/W2883386984","https://openalex.org/W2948982773","https://openalex.org/W2963351448","https://openalex.org/W2981720610","https://openalex.org/W4312365002","https://openalex.org/W4312897837","https://openalex.org/W4390872972","https://openalex.org/W4393160212"],"related_works":[],"abstract_inverted_index":{"Test-Time":[0],"Adaptation":[1],"(TTA)":[2],"enables":[3],"deep":[4],"neural":[5],"networks":[6],"to":[7,111,151,158],"handle":[8],"distribution":[9],"shifts":[10],"without":[11],"requiring":[12],"labels":[13],"at":[14,171],"inference.":[15],"However,":[16],"existing":[17],"methods":[18,60],"commonly":[19],"assume":[20],"complete":[21],"class":[22,96],"overlap":[23],"between":[24],"source":[25,52],"and":[26,106,126,129,142,147,161],"target":[27,45,95],"domains,":[28],"which":[29],"rarely":[30],"holds":[31],"in":[32,77,165],"practice.":[33],"We":[34,54],"study":[35],"the":[36,44,99,130],"challenging":[37],"setting":[38],"of":[39,51,115],"Partial":[40],"Class":[41],"Imbalance,":[42],"where":[43],"domain":[46],"contains":[47],"only":[48],"a":[49,88,112],"subset":[50],"classes.":[53],"show":[55],"that":[56,93,135],"entropy":[57],"minimization\u2013based":[58],"TTA":[59,116],"degrade":[61],"over":[62],"long":[63],"test":[64],"sequences":[65],"because":[66],"batch":[67],"normalization":[68],"updates":[69],"bias":[70],"feature":[71],"representations":[72],"toward":[73],"visible":[74,159],"classes,":[75],"resulting":[76],"skewed":[78],"predictions.":[79],"To":[80],"address":[81],"this,":[82],"we":[83],"propose":[84],"Logit-Adjusted":[85],"Entropy":[86],"Minimization,":[87],"simple":[89],"yet":[90],"effective":[91],"strategy":[92],"integrates":[94],"priors":[97],"into":[98],"adaptation":[100,140],"objective.":[101],"Our":[102],"method":[103,137],"is":[104,169],"model-agnostic":[105],"can":[107],"be":[108],"seamlessly":[109],"applied":[110],"wide":[113],"range":[114],"algorithms.":[117],"Extensive":[118],"experiments":[119],"on":[120],"CIFAR-100-C,":[121],"ImageNetC":[122],"under":[123],"diverse":[124],"corruptions":[125],"severity":[127],"levels,":[128],"large-scale":[131],"DomainNet-126":[132],"dataset":[133],"demonstrate":[134],"our":[136,154],"consistently":[138],"improves":[139],"stability":[141],"accuracy":[143],"for":[144],"both":[145],"CNNs":[146],"Vision":[148],"Transformers.":[149],"Compared":[150],"strong":[152],"baselines,":[153],"approach":[155],"reduces":[156],"overfitting":[157],"classes":[160],"mitigates":[162],"performance":[163],"degradation":[164],"long-sequence":[166],"adaptation.":[167],"Code":[168],"available":[170],"https://github.com/thilinawee/latta":[172]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2026-05-06T00:00:00"}