{"id":"https://openalex.org/W7140090601","doi":"https://doi.org/10.1109/access.2026.3676403","title":"Feature Space-Preserving Machine Unlearning for Robust Image Classification With Noisy Labels","display_name":"Feature Space-Preserving Machine Unlearning for Robust Image Classification With Noisy Labels","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7140090601","doi":"https://doi.org/10.1109/access.2026.3676403"},"language":"en","primary_location":{"id":"doi:10.1109/access.2026.3676403","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676403","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3676403","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102880371","display_name":"Shohei Yamamoto","orcid":"https://orcid.org/0000-0001-8898-4603"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Shohei Yamamoto","raw_affiliation_strings":["Graduate School of Science and Engineering, Kansai University, Osaka, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Graduate School of Science and Engineering, Kansai University, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031002717","display_name":"Soh Yoshida","orcid":null},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Soh Yoshida","raw_affiliation_strings":["Faculty of Engineering Science, Kansai University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0003-0237-7461","affiliations":[{"raw_affiliation_string":"Faculty of Engineering Science, Kansai University, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5089184180","display_name":"Mitsuji Muneyasu","orcid":"https://orcid.org/0000-0002-4492-5991"},"institutions":[{"id":"https://openalex.org/I56624758","display_name":"Kansai University","ror":"https://ror.org/03xg1f311","country_code":"JP","type":"education","lineage":["https://openalex.org/I56624758"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mitsuji Muneyasu","raw_affiliation_strings":["Faculty of Engineering Science, Kansai University, Osaka, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4492-5991","affiliations":[{"raw_affiliation_string":"Faculty of Engineering Science, Kansai University, Osaka, Japan","institution_ids":["https://openalex.org/I56624758"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.39390968,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"45449","last_page":"45463"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.44699999690055847,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.44699999690055847,"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/T10057","display_name":"Face and Expression Recognition","score":0.09529999643564224,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.033399999141693115,"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/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.671500027179718},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.5864999890327454},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5084999799728394},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5080000162124634},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4043999910354614},{"id":"https://openalex.org/keywords/noisy-data","display_name":"Noisy data","score":0.3788999915122986},{"id":"https://openalex.org/keywords/statistical-classification","display_name":"Statistical classification","score":0.3774999976158142},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.35580000281333923}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7820000052452087},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7250999808311462},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.671500027179718},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.5864999890327454},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5084999799728394},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5080000162124634},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4359999895095825},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4043999910354614},{"id":"https://openalex.org/C2781170535","wikidata":"https://www.wikidata.org/wiki/Q30587856","display_name":"Noisy data","level":2,"score":0.3788999915122986},{"id":"https://openalex.org/C110083411","wikidata":"https://www.wikidata.org/wiki/Q1744628","display_name":"Statistical classification","level":2,"score":0.3774999976158142},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.35580000281333923},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.3538999855518341},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.33309999108314514},{"id":"https://openalex.org/C34872919","wikidata":"https://www.wikidata.org/wiki/Q7092302","display_name":"One-class classification","level":3,"score":0.32659998536109924},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.31349998712539673},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3075000047683716},{"id":"https://openalex.org/C2776482837","wikidata":"https://www.wikidata.org/wiki/Q3553958","display_name":"Multi-label classification","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C2983327147","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Image denoising","level":3,"score":0.29750001430511475},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.27709999680519104},{"id":"https://openalex.org/C83665646","wikidata":"https://www.wikidata.org/wiki/Q42139305","display_name":"Feature vector","level":2,"score":0.2727000117301941},{"id":"https://openalex.org/C5339829","wikidata":"https://www.wikidata.org/wiki/Q1425977","display_name":"Machine vision","level":2,"score":0.26269999146461487},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2619999945163727},{"id":"https://openalex.org/C126422989","wikidata":"https://www.wikidata.org/wiki/Q93586","display_name":"Feature detection (computer vision)","level":4,"score":0.2583000063896179}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2026.3676403","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676403","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:38635ca0181a41e19ac165b64af49f18","is_oa":true,"landing_page_url":"https://doaj.org/article/38635ca0181a41e19ac165b64af49f18","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 14, Pp 45449-45463 (2026)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3676403","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3676403","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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 Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G107856455","display_name":null,"funder_award_id":"25K00510","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G2352037752","display_name":null,"funder_award_id":"22K18007","funder_id":"https://openalex.org/F4320320212","funder_display_name":"Japan Society for the Promotion of Science London"},{"id":"https://openalex.org/G6292074020","display_name":null,"funder_award_id":"25K00510","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8237952253","display_name":null,"funder_award_id":"22K18007","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320320212","display_name":"Japan Society for the Promotion of Science London","ror":"https://ror.org/02m7axw05"},{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Deep":[0],"neural":[1],"networks":[2],"excel":[3],"in":[4,42,108],"image":[5],"classification":[6],"with":[7,17,137,186,202],"clean":[8,119],"data,":[9],"but":[10],"their":[11,125],"performance":[12],"deteriorates":[13],"significantly":[14],"when":[15,181],"trained":[16,185],"noisy":[18,51,91,110,188],"labels.":[19,92],"In":[20],"contrast":[21],"to":[22,48,159,183],"conventional":[23],"approaches,":[24],"which":[25,43,68,109],"address":[26],"this":[27,35,74],"challenge":[28],"through":[29],"sample":[30],"selection":[31],"or":[32],"loss":[33],"correction,":[34],"study":[36],"proposes":[37],"a":[38,77,104],"fundamentally":[39],"different":[40],"paradigm":[41],"machine":[44],"unlearning":[45,54,61,80,152],"is":[46,211],"employed":[47],"selectively":[49],"forget":[50],"samples.":[52],"Existing":[53],"methods":[55],"such":[56],"as":[57],"scalable":[58],"remembering":[59],"and":[60,102,134,139],"unbound":[62],"cause":[63],"detrimental":[64],"feature":[65,78],"space":[66],"dispersion,":[67],"creates":[69],"ambiguous":[70],"decision":[71],"boundaries.":[72],"Thus,":[73],"paper":[75],"introduces":[76],"space-preserving":[79],"framework":[81],"that":[82,146,175,195],"maintains":[83],"discriminative":[84],"structures":[85],"while":[86,118],"removing":[87],"the":[88,132,164],"influence":[89],"of":[90,157],"The":[93,208],"proposed":[94],"approach":[95,197],"computes":[96],"class":[97,127,200],"centroids":[98,117],"from":[99,115,143],"reliable":[100],"samples":[101,111,120],"implements":[103],"dual":[105],"optimization":[106],"strategy":[107],"are":[112,121],"pushed":[113],"away":[114],"all":[116],"simultaneously":[122],"pulled":[123],"toward":[124],"appropriate":[126],"centers.":[128],"Comprehensive":[129],"experiments":[130],"on":[131,163],"CIFAR-10":[133],"CIFAR-100":[135,167],"datasets":[136],"symmetric":[138],"asymmetric":[140],"noise":[141],"(ranging":[142],"10%\u201390%)":[144],"show":[145],"our":[147,176,196],"method":[148,177],"consistently":[149],"outperforms":[150],"standard":[151],"techniques,":[153],"achieving":[154],"accuracy":[155],"improvements":[156],"up":[158],"27.61":[160],"percentage":[161],"points":[162],"more":[165],"complex":[166],"dataset":[168],"under":[169],"high-noise":[170],"conditions.":[171],"Furthermore,":[172],"we":[173],"confirm":[174],"remains":[178],"effective":[179],"even":[180],"applied":[182],"models":[184],"state-of-the-art":[187],"label":[189],"learning":[190],"methods.":[191],"Visualization":[192],"analysis":[193],"demonstrates":[194],"preserves":[198],"compact":[199],"clusters":[201],"clear":[203],"boundaries,":[204],"despite":[205],"aggressive":[206],"unlearning.":[207],"reported":[209],"implementation":[210],"available":[212],"at":[213],"https://github.com/meruemon/FSPMU.":[214]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-03-24T00:00:00"}