{"id":"https://openalex.org/W4390872047","doi":"https://doi.org/10.1109/iccv51070.2023.01501","title":"Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization","display_name":"Towards Open-Set Test-Time Adaptation Utilizing the Wisdom of Crowds in Entropy Minimization","publication_year":2023,"publication_date":"2023-10-01","ids":{"openalex":"https://openalex.org/W4390872047","doi":"https://doi.org/10.1109/iccv51070.2023.01501"},"language":"en","primary_location":{"id":"doi:10.1109/iccv51070.2023.01501","doi":"https://doi.org/10.1109/iccv51070.2023.01501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.01501","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2308.06879","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100776321","display_name":"Jungsoo Lee","orcid":"https://orcid.org/0000-0001-9439-0166","observed_orcids":["https://orcid.org/0000-0001-9439-0166"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]},{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["KR","US"],"is_corresponding":false,"raw_author_name":"Jungsoo Lee","raw_affiliation_strings":["Qualcomm AI Research","KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I4210087596"]},{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003034727","display_name":"Debasmit Das","orcid":"https://orcid.org/0000-0003-2910-5079","observed_orcids":["https://orcid.org/0000-0003-2910-5079"]},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Debasmit Das","raw_affiliation_strings":["Qualcomm AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I4210087596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047912015","display_name":"Jaegul Choo","orcid":"https://orcid.org/0000-0003-1071-4835","observed_orcids":["https://orcid.org/0000-0003-1071-4835"]},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jaegul Choo","raw_affiliation_strings":["KAIST"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"KAIST","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060613793","display_name":"Sungha Choi","orcid":"https://orcid.org/0000-0003-2313-9243","observed_orcids":["https://orcid.org/0000-0003-2313-9243"]},"institutions":[{"id":"https://openalex.org/I4210087596","display_name":"Qualcomm (United States)","ror":"https://ror.org/002zrf773","country_code":"US","type":"company","lineage":["https://openalex.org/I4210087596"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sungha Choi","raw_affiliation_strings":["Qualcomm AI Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Qualcomm AI Research","institution_ids":["https://openalex.org/I4210087596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":2.6068,"has_fulltext":true,"cited_by_count":23,"citation_normalized_percentile":{"value":0.93221405,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":93,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"16334","last_page":"16334"},"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":1.0,"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":1.0,"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":0.0,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.0,"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/test-time-adaptation","display_name":"test-time adaptation","score":0.9309999942779541},{"id":"https://openalex.org/keywords/entropy-minimization","display_name":"entropy minimization","score":0.9279999732971191},{"id":"https://openalex.org/keywords/wisdom-of-crowds","display_name":"wisdom of crowds","score":0.9010000228881836},{"id":"https://openalex.org/keywords/confidence-scores","display_name":"confidence scores","score":0.550000011920929},{"id":"https://openalex.org/keywords/sample-selection","display_name":"sample selection","score":0.75},{"id":"https://openalex.org/keywords/unlabeled-target-domain","display_name":"unlabeled target domain","score":0.7139999866485596},{"id":"https://openalex.org/keywords/tents","display_name":"tents","score":0.625},{"id":"https://openalex.org/keywords/semantic-segmentation","display_name":"semantic segmentation","score":0.6980000138282776},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.9139999747276306}],"concepts":[{"id":"https://openalex.org/C2777852691","wikidata":"https://www.wikidata.org/wiki/Q13430821","display_name":"Crowds","level":2,"score":0.7337876558303833},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6664855480194092},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.5728901028633118},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5398584604263306},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.4706268310546875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3393690586090088},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.10590651631355286},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.10217082500457764},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09758630394935608},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/iccv51070.2023.01501","doi":"https://doi.org/10.1109/iccv51070.2023.01501","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iccv51070.2023.01501","pdf_url":null,"source":{"id":"https://openalex.org/S4363607764","display_name":"IEEE/CVF International Conference on Computer Vision (ICCV)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE/CVF International Conference on Computer Vision (ICCV)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2308.06879","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.06879","pdf_url":"https://arxiv.org/pdf/2308.06879","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2308.06879","doi":"https://doi.org/10.48550/arxiv.2308.06879","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2308.06879","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2308.06879","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2308.06879","pdf_url":"https://arxiv.org/pdf/2308.06879","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390872047.pdf","grobid_xml":"https://content.openalex.org/works/W4390872047.grobid-xml"},"referenced_works_count":66,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W2097482982","https://openalex.org/W2194775991","https://openalex.org/W2279034837","https://openalex.org/W2335728318","https://openalex.org/W2340897893","https://openalex.org/W2403257023","https://openalex.org/W2431874326","https://openalex.org/W2487365028","https://openalex.org/W2531327146","https://openalex.org/W2551176409","https://openalex.org/W2592691248","https://openalex.org/W2781228439","https://openalex.org/W2803187616","https://openalex.org/W2885593519","https://openalex.org/W2941387380","https://openalex.org/W2945007112","https://openalex.org/W2963735582","https://openalex.org/W2964137095","https://openalex.org/W2964309882","https://openalex.org/W2964677000","https://openalex.org/W2981512393","https://openalex.org/W2996108195","https://openalex.org/W3007769536","https://openalex.org/W3034218934","https://openalex.org/W3035564946","https://openalex.org/W3036825277","https://openalex.org/W3039431315","https://openalex.org/W3098071563","https://openalex.org/W3101367735","https://openalex.org/W3113089224","https://openalex.org/W3113151582","https://openalex.org/W3113775519","https://openalex.org/W3119543788","https://openalex.org/W3124626396","https://openalex.org/W3150373995","https://openalex.org/W3153511633","https://openalex.org/W3153518538","https://openalex.org/W3158278463","https://openalex.org/W3165959647","https://openalex.org/W3177096435","https://openalex.org/W3183613752","https://openalex.org/W3187775224","https://openalex.org/W4224797805","https://openalex.org/W4225774191","https://openalex.org/W4292447903","https://openalex.org/W4312249250","https://openalex.org/W4312365002","https://openalex.org/W4312367364","https://openalex.org/W4312657985","https://openalex.org/W4312717513","https://openalex.org/W4312897837","https://openalex.org/W4313045831","https://openalex.org/W4318719469","https://openalex.org/W4320559463","https://openalex.org/W4322616269","https://openalex.org/W4372348372","https://openalex.org/W4382239347","https://openalex.org/W4382317875","https://openalex.org/W4386076614","https://openalex.org/W4386811916","https://openalex.org/W4390872026","https://openalex.org/W6703116779","https://openalex.org/W6787972765","https://openalex.org/W7133200675","https://openalex.org/W7133206185"],"related_works":["https://openalex.org/W4402727003","https://openalex.org/W4388441936","https://openalex.org/W7077908342","https://openalex.org/W4409366334","https://openalex.org/W4408959970","https://openalex.org/W7133214672","https://openalex.org/W3036246552","https://openalex.org/W3119543788","https://openalex.org/W4394625772","https://openalex.org/W4403573050"],"abstract_inverted_index":{"Test-time":[0],"adaptation":[1,39,223],"(TTA)":[2],"methods,":[3],"which":[4],"generally":[5,159],"rely":[6],"on":[7,181],"the":[8,16,21,76,85,89,117,135,162,168,187,195,200],"model\u2019s":[9],"predictions":[10,142],"(e.g.,":[11,229,239],"entropy":[12,82,112],"minimization)":[13],"to":[14,20,87,115,134,148,166,177,207,215],"adapt":[15],"source":[17],"pretrained":[18],"model":[19,86,197],"unlabeled":[22],"target":[23],"domain,":[24],"suffer":[25],"from":[26,30,139],"noisy":[27,44,101,151],"signals":[28,138,152],"originating":[29],"1)":[31],"incorrect":[32],"or":[33,131],"2)":[34],"open-set":[35,63],"predictions.":[36],"Long-term":[37],"stable":[38],"is":[40,53,212],"hampered":[41],"by":[42,75],"such":[43,50,155,182],"signals,":[45,164],"so":[46],"training":[47],"models":[48],"without":[49],"error":[51,232],"accumulation":[52],"crucial":[54,78],"for":[55],"practical":[56],"TTA.":[57],"To":[58,108],"address":[59],"these":[60],"issues,":[61],"including":[62],"TTA,":[64],"we":[65,98,184],"propose":[66],"a":[67],"simple":[68],"yet":[69],"effective":[70],"sample":[71],"selection":[72],"method":[73,211],"inspired":[74],"following":[77],"empirical":[79],"finding.":[80],"While":[81],"minimization":[83,113],"compels":[84],"increase":[88,178],"probability":[90],"of":[91,120,137,145,157,172],"its":[92],"predicted":[93],"label":[94],"(i.e.,":[95,143],"confidence":[96,106,118,127,170,190],"values),":[97],"found":[99,160],"that":[100],"samples":[102,188],"rather":[103],"show":[104],"decreased":[105],"values.":[107],"be":[109,208],"more":[110],"specific,":[111],"attempts":[114,176],"raise":[116,167],"values":[119,128,171,191],"an":[121],"individual":[122,126,169],"sample\u2019s":[123],"prediction,":[124],"but":[125],"may":[129],"rise":[130],"fall":[132],"due":[133],"influence":[136],"numerous":[140],"other":[141],"wisdom":[144],"crowds).":[146],"Due":[147],"this":[149],"fact,":[150],"misaligned":[153],"with":[154,234,244],"\u2018wisdom":[156],"crowds\u2019,":[158],"in":[161,194,199,225,242],"correct":[163],"fail":[165],"wrong":[173],"samples,":[174],"despite":[175],"them.":[179],"Based":[180],"findings,":[183],"filter":[185],"out":[186],"whose":[189],"are":[192,205],"lower":[193],"adapted":[196],"than":[198],"original":[201],"model,":[202],"as":[203],"they":[204],"likely":[206],"noisy.":[209],"Our":[210],"widely":[213],"applicable":[214],"existing":[216],"TTA":[217],"methods":[218],"and":[219,236],"improves":[220],"their":[221],"long-term":[222],"performance":[224],"both":[226],"image":[227],"classification":[228],"49.4%":[230],"reduced":[231],"rates":[233],"TENT)":[235],"semantic":[237],"segmentation":[238],"11.7%":[240],"gain":[241],"mIoU":[243],"TENT).":[245]},"counts_by_year":[{"year":2026,"cited_by_count":8},{"year":2025,"cited_by_count":9},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":2}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2024-01-16T00:00:00"}