{"id":"https://openalex.org/W4304092157","doi":"https://doi.org/10.1145/3503161.3547984","title":"Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration","display_name":"Tackling Instance-Dependent Label Noise with Dynamic Distribution Calibration","publication_year":2022,"publication_date":"2022-10-10","ids":{"openalex":"https://openalex.org/W4304092157","doi":"https://doi.org/10.1145/3503161.3547984"},"language":"en","primary_location":{"id":"doi:10.1145/3503161.3547984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547984","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547984","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5036563704","display_name":"Manyi Zhang","orcid":"https://orcid.org/0009-0002-7381-4497"},"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":true,"raw_author_name":"Manyi Zhang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005766227","display_name":"Yuxin Ren","orcid":"https://orcid.org/0000-0003-1065-4350"},"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":"Yuxin Ren","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100413085","display_name":"Zihao Wang","orcid":"https://orcid.org/0000-0002-3919-0396"},"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":"Zihao Wang","raw_affiliation_strings":["Tsinghua University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University, Shenzhen, China","institution_ids":["https://openalex.org/I99065089"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101456902","display_name":"Chun Yuan","orcid":"https://orcid.org/0000-0002-3590-6676"},"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"]},{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chun Yuan","raw_affiliation_strings":["Tsinghua University & Peng Cheng National Laboratory, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tsinghua University & Peng Cheng National Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793","https://openalex.org/I99065089"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5036563704"],"corresponding_institution_ids":["https://openalex.org/I99065089"],"apc_list":null,"apc_paid":null,"fwci":0.4153,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":{"value":0.58690697,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"4635","last_page":"4644"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9995999932289124,"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":0.9995999932289124,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.95660001039505,"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/T11606","display_name":"Infrastructure Maintenance and Monitoring","score":0.9564999938011169,"subfield":{"id":"https://openalex.org/subfields/2205","display_name":"Civil and Structural Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6071498990058899},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5966272950172424},{"id":"https://openalex.org/keywords/gaussian-noise","display_name":"Gaussian noise","score":0.5729082822799683},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.5633026361465454},{"id":"https://openalex.org/keywords/robustness","display_name":"Robustness (evolution)","score":0.5375767350196838},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47597187757492065},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44542306661605835},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.4190569818019867},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37977051734924316},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.36114272475242615},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3051490783691406},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.22795018553733826}],"concepts":[{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6071498990058899},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5966272950172424},{"id":"https://openalex.org/C4199805","wikidata":"https://www.wikidata.org/wiki/Q2725903","display_name":"Gaussian noise","level":2,"score":0.5729082822799683},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.5633026361465454},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.5375767350196838},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47597187757492065},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44542306661605835},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.4190569818019867},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37977051734924316},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.36114272475242615},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3051490783691406},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.22795018553733826},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3503161.3547984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547984","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3503161.3547984","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3503161.3547984","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3503161.3547984","source":{"id":"https://openalex.org/S4363608757","display_name":"Proceedings of the 30th ACM International Conference on Multimedia","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":"conference"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 30th ACM International Conference on Multimedia","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4304092157.pdf","grobid_xml":"https://content.openalex.org/works/W4304092157.grobid-xml"},"referenced_works_count":19,"referenced_works":["https://openalex.org/W1493730910","https://openalex.org/W1921293667","https://openalex.org/W2752782242","https://openalex.org/W2795431618","https://openalex.org/W2963351358","https://openalex.org/W2964274690","https://openalex.org/W2964350391","https://openalex.org/W2967052791","https://openalex.org/W2988966271","https://openalex.org/W3035546924","https://openalex.org/W3110483780","https://openalex.org/W3156669901","https://openalex.org/W3171635822","https://openalex.org/W3173685130","https://openalex.org/W3175103763","https://openalex.org/W3190486510","https://openalex.org/W3204593736","https://openalex.org/W3205655893","https://openalex.org/W4249033934"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2510582230","https://openalex.org/W2978674666","https://openalex.org/W2074430941","https://openalex.org/W2113096305","https://openalex.org/W1977636359","https://openalex.org/W2772305933","https://openalex.org/W2572355887"],"abstract_inverted_index":{"Instance-dependent":[0],"label":[1,73,91,159,192],"noise":[2,106,193],"is":[3,79,150,171],"realistic":[4],"but":[5],"rather":[6],"challenging,":[7],"where":[8],"the":[9,23,32,44,66,102,111,118,127,176,181],"label-corruption":[10],"process":[11],"depends":[12],"on":[13,52,126,188],"instances":[14],"directly.":[15],"It":[16],"causes":[17],"a":[18,75,97,141,155,166],"severe":[19],"distribution":[20,67,100,134,167],"shift":[21,68,110],"between":[22],"distributions":[24],"of":[25,34,131,185],"training":[26,86],"and":[27,129,183,194],"test":[28],"data,":[29],"which":[30,149,170],"impairs":[31],"generalization":[33],"trained":[35],"models.":[36],"Prior":[37],"works":[38,48,139,164],"put":[39],"great":[40],"effort":[41],"into":[42],"tackling":[43],"issue.":[45],"Unfortunately,":[46],"these":[47],"always":[49],"highly":[50],"rely":[51],"strong":[53],"assumptions":[54],"or":[55],"remain":[56],"heuristic":[57],"without":[58],"theoretical":[59],"guarantees.":[60],"In":[61],"this":[62],"paper,":[63],"to":[64,96,109,116,153,174],"address":[65],"in":[69,140,165],"learning":[70],"with":[71,190],"instance-dependent":[72],"noise,":[74,92],"dynamic":[76],"distribution-calibration":[77],"strategy":[78],"adopted.":[80],"Specifically,":[81],"we":[82,121],"hypothesize":[83],"that,":[84],"before":[85],"data":[87],"are":[88],"corrupted":[89],"by":[90],"each":[93],"class":[94],"conforms":[95],"multivariate":[98,132],"Gaussian":[99,112,133],"at":[101],"feature":[103],"level.":[104],"Label":[105],"produces":[107],"outliers":[108],"distribution.":[113],"During":[114],"training,":[115],"calibrate":[117],"shifted":[119],"distribution,":[120],"propose":[122],"two":[123],"methods":[124,187],"based":[125],"mean":[128,147],"covariance":[130],"respectively.":[135],"The":[136,161],"mean-based":[137],"method":[138,163],"recursive":[142],"dimension-reduction":[143],"manner":[144],"for":[145],"robust":[146],"estimation,":[148],"theoretically":[151],"guaranteed":[152],"train":[154],"high-quality":[156],"model":[157,177],"against":[158],"noise.":[160,197],"covariance-based":[162],"disturbance":[168],"manner,":[169],"experimentally":[172],"verified":[173],"improve":[175],"robustness.":[178],"We":[179],"demonstrate":[180],"utility":[182],"effectiveness":[184],"our":[186],"datasets":[189],"synthetic":[191],"real-world":[195],"unknown":[196]},"counts_by_year":[{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1}],"updated_date":"2026-06-07T08:38:57.713557","created_date":"2025-10-10T00:00:00"}