{"id":"https://openalex.org/W7128534282","doi":"https://doi.org/10.1109/tpami.2026.3662389","title":"Calibrating Biased Distribution in VFM-Derived Latent Space via Cross-Domain Geometric Consistency","display_name":"Calibrating Biased Distribution in VFM-Derived Latent Space via Cross-Domain Geometric Consistency","publication_year":2026,"publication_date":"2026-02-09","ids":{"openalex":"https://openalex.org/W7128534282","doi":"https://doi.org/10.1109/tpami.2026.3662389","pmid":"https://pubmed.ncbi.nlm.nih.gov/41662554"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3662389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3662389","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5020661081","display_name":"Yanbiao Ma","orcid":"https://orcid.org/0000-0002-8472-1475"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbiao Ma","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8472-1475","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5108972454","display_name":"Wei Dai","orcid":"https://orcid.org/0009-0004-7023-3966"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Dai","raw_affiliation_strings":["Xidian University, Xi’an, China"],"raw_orcid":"https://orcid.org/0009-0004-7023-3966","affiliations":[{"raw_affiliation_string":"Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115603447","display_name":"Bowei Liu","orcid":"https://orcid.org/0000-0001-8013-5527"},"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":"Bowei Liu","raw_affiliation_strings":["Tsinghua University, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Beijing, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Jiayi Chen","orcid":null},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayi Chen","raw_affiliation_strings":["Xidian University, Xi’an, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xidian University, Xi’an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Wenke Huang","orcid":"https://orcid.org/0000-0003-4819-293X"},"institutions":[{"id":"https://openalex.org/I37461747","display_name":"Wuhan University","ror":"https://ror.org/033vjfk17","country_code":"CN","type":"education","lineage":["https://openalex.org/I37461747"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wenke Huang","raw_affiliation_strings":["Wuhan University, Wuhan, China"],"raw_orcid":"https://orcid.org/0000-0003-4819-293X","affiliations":[{"raw_affiliation_string":"Wuhan University, Wuhan, China","institution_ids":["https://openalex.org/I37461747"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102638295","display_name":"Guancheng Wan","orcid":"https://orcid.org/0000-0002-7083-6423"},"institutions":[{"id":"https://openalex.org/I95457486","display_name":"University of California, Berkeley","ror":"https://ror.org/01an7q238","country_code":"US","type":"education","lineage":["https://openalex.org/I95457486"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Guancheng Wan","raw_affiliation_strings":["Department of Computer Science, University of California, Berkeley, CA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of California, Berkeley, CA, USA","institution_ids":["https://openalex.org/I95457486"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhiwu Lu","orcid":"https://orcid.org/0000-0001-6429-7956"},"institutions":[{"id":"https://openalex.org/I78988378","display_name":"Renmin University of China","ror":"https://ror.org/041pakw92","country_code":"CN","type":"education","lineage":["https://openalex.org/I78988378"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiwu Lu","raw_affiliation_strings":["Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-6429-7956","affiliations":[{"raw_affiliation_string":"Gaoling School of Artificial Intelligence, Renmin University of China, Beijing, China","institution_ids":["https://openalex.org/I78988378"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125492285","display_name":"Junchi Yan","orcid":null},"institutions":[{"id":"https://openalex.org/I183067930","display_name":"Shanghai Jiao Tong University","ror":"https://ror.org/0220qvk04","country_code":"CN","type":"education","lineage":["https://openalex.org/I183067930"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Junchi Yan","raw_affiliation_strings":["Shanghai Jiao Tong University, Shanghai, China"],"raw_orcid":"https://orcid.org/0000-0001-9639-7679","affiliations":[{"raw_affiliation_string":"Shanghai Jiao Tong University, Shanghai, China","institution_ids":["https://openalex.org/I183067930"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.16799311,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"7258","last_page":"7275"},"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":0.4496000111103058,"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":0.4496000111103058,"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/T11448","display_name":"Face recognition and analysis","score":0.22840000689029694,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.07590000331401825,"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/leverage","display_name":"Leverage (statistics)","score":0.6432999968528748},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.4853000044822693},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.462799996137619},{"id":"https://openalex.org/keywords/geometric-distribution","display_name":"Geometric distribution","score":0.45410001277923584},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.39469999074935913},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3928999900817871},{"id":"https://openalex.org/keywords/calibration","display_name":"Calibration","score":0.38960000872612},{"id":"https://openalex.org/keywords/feature-vector","display_name":"Feature vector","score":0.3840999901294708},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.3700000047683716}],"concepts":[{"id":"https://openalex.org/C153083717","wikidata":"https://www.wikidata.org/wiki/Q6535263","display_name":"Leverage (statistics)","level":2,"score":0.6432999968528748},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6018999814987183},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5410000085830688},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.4853000044822693},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.462799996137619},{"id":"https://openalex.org/C39947850","wikidata":"https://www.wikidata.org/wiki/Q729523","display_name":"Geometric distribution","level":3,"score":0.45410001277923584},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.39469999074935913},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3928999900817871},{"id":"https://openalex.org/C165838908","wikidata":"https://www.wikidata.org/wiki/Q736777","display_name":"Calibration","level":2,"score":0.38960000872612},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.3840999901294708},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3700000047683716},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.36239999532699585},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.36149999499320984},{"id":"https://openalex.org/C167723999","wikidata":"https://www.wikidata.org/wiki/Q3773214","display_name":"Sampling distribution","level":2,"score":0.3474000096321106},{"id":"https://openalex.org/C110121322","wikidata":"https://www.wikidata.org/wiki/Q865811","display_name":"Distribution (mathematics)","level":2,"score":0.33959999680519104},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33899998664855957},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3140999972820282},{"id":"https://openalex.org/C149441793","wikidata":"https://www.wikidata.org/wiki/Q200726","display_name":"Probability distribution","level":2,"score":0.29269999265670776},{"id":"https://openalex.org/C136520226","wikidata":"https://www.wikidata.org/wiki/Q302814","display_name":"Geometric data analysis","level":2,"score":0.2912999987602234},{"id":"https://openalex.org/C104065381","wikidata":"https://www.wikidata.org/wiki/Q1002535","display_name":"Geometric modeling","level":2,"score":0.2840999960899353},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.28349998593330383},{"id":"https://openalex.org/C75917345","wikidata":"https://www.wikidata.org/wiki/Q2725298","display_name":"Sampling bias","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.2720000147819519},{"id":"https://openalex.org/C7305733","wikidata":"https://www.wikidata.org/wiki/Q207961","display_name":"Geometric shape","level":2,"score":0.2687999904155731},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C108882727","wikidata":"https://www.wikidata.org/wiki/Q2991685","display_name":"Solid modeling","level":2,"score":0.26409998536109924},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.25220000743865967}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3662389","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3662389","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41662554","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41662554","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G187169856","display_name":null,"funder_award_id":"62222607","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8775507649","display_name":null,"funder_award_id":"92370201","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":50,"referenced_works":["https://openalex.org/W2100659887","https://openalex.org/W2108598243","https://openalex.org/W2112796928","https://openalex.org/W2117539524","https://openalex.org/W2149466042","https://openalex.org/W2155904486","https://openalex.org/W2194775991","https://openalex.org/W2627183927","https://openalex.org/W2763549966","https://openalex.org/W2962895364","https://openalex.org/W2962933664","https://openalex.org/W2963351448","https://openalex.org/W2963691377","https://openalex.org/W2992308087","https://openalex.org/W3034601242","https://openalex.org/W3096688134","https://openalex.org/W3125815192","https://openalex.org/W3176474016","https://openalex.org/W3177230409","https://openalex.org/W3182158470","https://openalex.org/W3198377975","https://openalex.org/W3199144655","https://openalex.org/W3202223295","https://openalex.org/W3204874618","https://openalex.org/W3215720729","https://openalex.org/W4283796083","https://openalex.org/W4307823382","https://openalex.org/W4312699393","https://openalex.org/W4312877479","https://openalex.org/W4312986563","https://openalex.org/W4313175608","https://openalex.org/W4366352743","https://openalex.org/W4385695913","https://openalex.org/W4386066601","https://openalex.org/W4386076395","https://openalex.org/W4386076561","https://openalex.org/W4386220752","https://openalex.org/W4386790226","https://openalex.org/W4390873683","https://openalex.org/W4391537734","https://openalex.org/W4392172801","https://openalex.org/W4393156735","https://openalex.org/W4399995632","https://openalex.org/W4402753575","https://openalex.org/W4402772288","https://openalex.org/W4404914848","https://openalex.org/W4406858183","https://openalex.org/W4409263723","https://openalex.org/W4412536610","https://openalex.org/W4413147667"],"related_works":[],"abstract_inverted_index":{"Despite":[0],"the":[1,11,14,19,28,39,49,60,64,100,109,127,131,143,152],"fast":[2],"progress":[3],"of":[4,13,30,41,63,107,129],"deep":[5],"learning,":[6,140],"one":[7],"standing":[8],"challenge":[9],"is":[10],"gap":[12,32,132],"observed":[15],"training":[16],"samples":[17,123],"and":[18,73,91,96,135,177],"underlying":[20],"true":[21,153],"distribution.":[22],"There":[23],"are":[24],"multiple":[25],"reasons":[26],"for":[27,57,124,155],"causing":[29],"this":[31,118],"e.g.":[33],"sampling":[34],"bias,":[35],"noise":[36],"etc.":[37],"In":[38,99,138],"era":[40],"foundation":[42,52],"models,":[43],"we":[44,80,103],"show":[45,161],"that":[46,162],"when":[47],"leveraging":[48],"off-the-shelf":[50],"(vision)":[51],"models":[53],"(e.g.,":[54],"CLIP,":[55],"DINOv2)":[56],"feature":[58,66],"extraction,":[59],"geometric":[61,83,111,144,165],"shapes":[62],"resulting":[65],"distributions":[67],"exhibit":[68],"remarkable":[69],"transferability":[70],"across":[71,183],"domains":[72],"datasets.":[74],"To":[75],"verify":[76],"its":[77],"practical":[78],"usefulness,":[79],"embody":[81],"our":[82,163],"knowledge-guided":[84,166],"distribution":[85,154,167],"calibration":[86,168],"framework":[87],"in":[88,126],"two":[89],"popular":[90],"challenging":[92],"settings:":[93],"federated":[94,101],"learning":[95],"long-tailed":[97,139],"recognition.":[98],"setting,":[102],"devise":[104],"a":[105],"technique":[106],"acquiring":[108],"global":[110,136],"shape":[112],"under":[113],"privacy":[114],"constraints,":[115],"then":[116],"leverage":[117],"knowledge":[119,145],"to":[120,150],"generate":[121],"new":[122],"clients,":[125],"aim":[128],"bridging":[130],"between":[133],"local":[134],"observations.":[137],"it":[141],"utilizes":[142],"transferred":[146],"from":[147],"sample-rich":[148],"categories":[149],"recover":[151],"sample-scarce":[156],"tail":[157],"classes.":[158],"Comprehensive":[159],"experiments":[160],"proposed":[164],"effectively":[169],"overcomes":[170],"information":[171],"deficits":[172],"caused":[173],"by":[174],"data":[175],"heterogeneity":[176],"sample":[178],"imbalance,":[179],"with":[180],"boosted":[181],"performance":[182],"benchmarks.":[184]},"counts_by_year":[],"updated_date":"2026-07-21T08:15:58.654021","created_date":"2026-02-11T00:00:00"}