{"id":"https://openalex.org/W4416635526","doi":"https://doi.org/10.48550/arxiv.2505.10641","title":"FRET: Feature Redundancy Elimination for Test Time Adaptation","display_name":"FRET: Feature Redundancy Elimination for Test Time Adaptation","publication_year":2025,"publication_date":"2025-05-15","ids":{"openalex":"https://openalex.org/W4416635526","doi":"https://doi.org/10.48550/arxiv.2505.10641"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2505.10641","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10641","pdf_url":"https://arxiv.org/pdf/2505.10641","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2505.10641","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078930542","display_name":"Linjing You","orcid":"https://orcid.org/0000-0002-1399-4468"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"You, Linjing","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044208426","display_name":"Jing Lu","orcid":"https://orcid.org/0000-0002-8323-3082"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lu, Jiabao","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085759154","display_name":"Xiayuan Huang","orcid":"https://orcid.org/0000-0002-3730-5014"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Huang, Xiayuan","raw_affiliation_strings":[],"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5049695170","display_name":"Xiangli Nie","orcid":"https://orcid.org/0000-0001-5208-4670"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nie, Xiangli","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5078930542"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"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":0.7458000183105469,"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":0.7458000183105469,"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.041600000113248825,"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":0.02759999968111515,"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/redundancy","display_name":"Redundancy (engineering)","score":0.7508000135421753},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.7401000261306763},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.6205999851226807},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.5796999931335449},{"id":"https://openalex.org/keywords/adaptability","display_name":"Adaptability","score":0.5715000033378601},{"id":"https://openalex.org/keywords/feature-learning","display_name":"Feature learning","score":0.5235999822616577},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5105999708175659},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5034999847412109},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.4717000126838684}],"concepts":[{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.7508000135421753},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.7401000261306763},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6988999843597412},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6399000287055969},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.6205999851226807},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.5796999931335449},{"id":"https://openalex.org/C177606310","wikidata":"https://www.wikidata.org/wiki/Q5674297","display_name":"Adaptability","level":2,"score":0.5715000033378601},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5235999822616577},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5105999708175659},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5034999847412109},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4871000051498413},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.4717000126838684},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.41029998660087585},{"id":"https://openalex.org/C16910744","wikidata":"https://www.wikidata.org/wiki/Q7705759","display_name":"Test data","level":2,"score":0.4083999991416931},{"id":"https://openalex.org/C16811321","wikidata":"https://www.wikidata.org/wiki/Q17138905","display_name":"Minimum redundancy feature selection","level":3,"score":0.3725000023841858},{"id":"https://openalex.org/C188198153","wikidata":"https://www.wikidata.org/wiki/Q1613840","display_name":"Limiting","level":2,"score":0.3357999920845032},{"id":"https://openalex.org/C51632099","wikidata":"https://www.wikidata.org/wiki/Q3985153","display_name":"Training set","level":2,"score":0.31610000133514404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30469998717308044},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.2987000048160553},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.2897000014781952},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.275299996137619},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.26339998841285706},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.26330000162124634},{"id":"https://openalex.org/C160920958","wikidata":"https://www.wikidata.org/wiki/Q7662746","display_name":"Synthetic data","level":2,"score":0.26260000467300415},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.25999999046325684}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2505.10641","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10641","pdf_url":"https://arxiv.org/pdf/2505.10641","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2505.10641","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2505.10641","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2505.10641","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2505.10641","pdf_url":"https://arxiv.org/pdf/2505.10641","source":{"id":"https://openalex.org/S4393918464","display_name":"ArXiv.org","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Test-Time":[0],"Adaptation":[1,91],"(TTA)":[2],"aims":[3],"to":[4,55,77,103,114,201],"enhance":[5],"the":[6,22,74,106,167,182,199],"generalization":[7],"of":[8,184],"deep":[9],"learning":[10],"models":[11],"when":[12],"faced":[13],"with":[14,124,150],"test":[15,34],"data":[16,35],"that":[17,49,188,196],"exhibits":[18],"distribution":[19],"shifts":[20,59],"from":[21],"training":[23],"data.":[24,79],"In":[25,45],"this":[26,69,82,135],"context,":[27],"only":[28,156],"a":[29,93,145],"pre-trained":[30],"model":[31,176,200],"and":[32,120,169,179,186,204],"unlabeled":[33],"are":[36],"available,":[37],"making":[38],"it":[39],"particularly":[40],"relevant":[41],"for":[42,89,96],"privacy-sensitive":[43],"applications.":[44],"practice,":[46],"we":[47,84,137],"observe":[48],"feature":[50,107,158,163],"redundancy":[51,108,159],"in":[52,61,130,165],"embeddings":[53],"tends":[54],"increase":[56],"as":[57,110],"domain":[58],"intensify":[60],"TTA.":[62,97],"However,":[63],"existing":[64],"TTA":[65],"methods":[66],"often":[67],"overlook":[68],"redundancy,":[70],"which":[71,143],"can":[72],"hinder":[73],"model's":[75],"adaptability":[76],"new":[78],"To":[80,133],"address":[81],"issue,":[83],"introduce":[85],"Feature":[86],"Redundancy":[87],"Elimination":[88],"Test-time":[90],"(FRET),":[92],"novel":[94],"perspective":[95],"A":[98],"straightforward":[99],"approach":[100],"(S-FRET)":[101],"is":[102],"directly":[104],"minimize":[105],"score":[109],"an":[111],"optimization":[112],"objective":[113],"improve":[115],"adaptation.":[116,215],"Despite":[117],"its":[118,128],"simplicity":[119],"effectiveness,":[121],"S-FRET":[122,185],"struggles":[123],"label":[125],"shifts,":[126],"limiting":[127],"robustness":[129],"real-world":[131],"scenarios.":[132],"mitigate":[134],"limitation,":[136],"further":[138],"propose":[139],"Graph-based":[140],"FRET":[141],"(G-FRET),":[142],"integrates":[144],"Graph":[146],"Convolutional":[147],"Network":[148],"(GCN)":[149],"contrastive":[151],"learning.":[152],"This":[153],"design":[154],"not":[155],"reduces":[157],"but":[160],"also":[161],"enhances":[162],"discriminability":[164],"both":[166],"representation":[168],"prediction":[170],"layers.":[171],"Extensive":[172],"experiments":[173],"across":[174],"multiple":[175],"architectures,":[177],"tasks,":[178],"datasets":[180],"demonstrate":[181],"effectiveness":[183],"show":[187],"G-FRET":[189,197],"achieves":[190],"state-of-the-art":[191],"performance.":[192],"Further":[193],"analysis":[194],"reveals":[195],"enables":[198],"extract":[202],"non-redundant":[203],"highly":[205],"discriminative":[206],"features":[207],"during":[208],"inference,":[209],"thereby":[210],"facilitating":[211],"more":[212],"robust":[213],"test-time":[214]},"counts_by_year":[],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2025-10-10T00:00:00"}