{"id":"https://openalex.org/W4221163831","doi":"https://doi.org/10.1109/icassp43922.2022.9747470","title":"Synergistic Network Learning and Label Correction for Noise-Robust Image Classification","display_name":"Synergistic Network Learning and Label Correction for Noise-Robust Image Classification","publication_year":2022,"publication_date":"2022-04-27","ids":{"openalex":"https://openalex.org/W4221163831","doi":"https://doi.org/10.1109/icassp43922.2022.9747470"},"language":"en","primary_location":{"id":"doi:10.1109/icassp43922.2022.9747470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747470","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5100389824","display_name":"Chen Gong","orcid":"https://orcid.org/0000-0001-9305-6908"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Chen Gong","raw_affiliation_strings":["Mechanical Engineering, University of Washington,Seattle,WA,USA,98195"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, University of Washington,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103960897","display_name":"Kong Bin","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kong Bin","raw_affiliation_strings":["Keya Medical,Seattle,WA,USA,98104"],"affiliations":[{"raw_affiliation_string":"Keya Medical,Seattle,WA,USA,98104","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004492656","display_name":"Eric J. Seibel","orcid":"https://orcid.org/0000-0002-3382-6541"},"institutions":[{"id":"https://openalex.org/I201448701","display_name":"University of Washington","ror":"https://ror.org/00cvxb145","country_code":"US","type":"education","lineage":["https://openalex.org/I201448701"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Eric J. Seibel","raw_affiliation_strings":["Mechanical Engineering, University of Washington,Seattle,WA,USA,98195"],"affiliations":[{"raw_affiliation_string":"Mechanical Engineering, University of Washington,Seattle,WA,USA,98195","institution_ids":["https://openalex.org/I201448701"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100327833","display_name":"Xin Wang","orcid":"https://orcid.org/0000-0001-7955-2884"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xin Wang","raw_affiliation_strings":["Keya Medical,Seattle,WA,USA,98104"],"affiliations":[{"raw_affiliation_string":"Keya Medical,Seattle,WA,USA,98104","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037389227","display_name":"Youbing Yin","orcid":"https://orcid.org/0000-0001-9913-134X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Youbing Yin","raw_affiliation_strings":["Keya Medical,Seattle,WA,USA,98104"],"affiliations":[{"raw_affiliation_string":"Keya Medical,Seattle,WA,USA,98104","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100772304","display_name":"Qi Song","orcid":"https://orcid.org/0009-0003-5357-1931"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Qi Song","raw_affiliation_strings":["Keya Medical,Seattle,WA,USA,98104"],"affiliations":[{"raw_affiliation_string":"Keya Medical,Seattle,WA,USA,98104","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100389824"],"corresponding_institution_ids":["https://openalex.org/I201448701"],"apc_list":null,"apc_paid":null,"fwci":0.2079,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.37039431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"23","issue":null,"first_page":"4253","last_page":"4257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9998000264167786,"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":0.9998000264167786,"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":0.9914000034332275,"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/T12072","display_name":"Machine Learning and Algorithms","score":0.9848999977111816,"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/overfitting","display_name":"Overfitting","score":0.9389463663101196},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7753468751907349},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6697756052017212},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.657050371170044},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5829684734344482},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5354245901107788},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5075544118881226},{"id":"https://openalex.org/keywords/ground-truth","display_name":"Ground truth","score":0.5024333000183105},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.47944942116737366},{"id":"https://openalex.org/keywords/deep-neural-networks","display_name":"Deep neural networks","score":0.46387067437171936},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.4516262114048004},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4366699159145355}],"concepts":[{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.9389463663101196},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7753468751907349},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6697756052017212},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.657050371170044},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5829684734344482},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5354245901107788},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5075544118881226},{"id":"https://openalex.org/C146849305","wikidata":"https://www.wikidata.org/wiki/Q370766","display_name":"Ground truth","level":2,"score":0.5024333000183105},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.47944942116737366},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.46387067437171936},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4516262114048004},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4366699159145355},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp43922.2022.9747470","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp43922.2022.9747470","pdf_url":null,"source":{"id":"https://openalex.org/S4363607702","display_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","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":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"No poverty","id":"https://metadata.un.org/sdg/1","score":0.6700000166893005}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1921293667","https://openalex.org/W2095705004","https://openalex.org/W2121056381","https://openalex.org/W2158751697","https://openalex.org/W2162139029","https://openalex.org/W2163605009","https://openalex.org/W2167460663","https://openalex.org/W2194775991","https://openalex.org/W2566079294","https://openalex.org/W2620998106","https://openalex.org/W2682189153","https://openalex.org/W2743200750","https://openalex.org/W2885593519","https://openalex.org/W2963096987","https://openalex.org/W2963703197","https://openalex.org/W2963735582","https://openalex.org/W2964274690","https://openalex.org/W2964292098","https://openalex.org/W2967052791","https://openalex.org/W2970038028","https://openalex.org/W2996108195","https://openalex.org/W3019093950","https://openalex.org/W3034185248","https://openalex.org/W3089415123","https://openalex.org/W4214748882","https://openalex.org/W4287124576","https://openalex.org/W6640298173","https://openalex.org/W6674330103","https://openalex.org/W6678280073","https://openalex.org/W6683245480","https://openalex.org/W6684191040","https://openalex.org/W6742511895","https://openalex.org/W6751037545","https://openalex.org/W6751647823","https://openalex.org/W6753772092","https://openalex.org/W6766952621","https://openalex.org/W6771630921","https://openalex.org/W6784243975","https://openalex.org/W6796353777"],"related_works":["https://openalex.org/W1574414179","https://openalex.org/W4362597605","https://openalex.org/W3009056573","https://openalex.org/W2922073769","https://openalex.org/W4297676672","https://openalex.org/W4281702477","https://openalex.org/W4378510483","https://openalex.org/W4376166922","https://openalex.org/W2786764570","https://openalex.org/W4309960894"],"abstract_inverted_index":{"Large":[0],"training":[1,19,103],"datasets":[2,128],"almost":[3],"always":[4],"contain":[5],"examples":[6],"with":[7,82,129],"inaccurate":[8],"or":[9],"incorrect":[10],"labels.":[11],"Deep":[12],"Neural":[13],"Networks":[14],"(DNNs)":[15],"tend":[16],"to":[17,65],"overfit":[18],"label":[20,37,113],"noise,":[21,71],"resulting":[22],"in":[23,27],"poorer":[24],"model":[25],"performance":[26],"practice.":[28],"To":[29],"address":[30],"this":[31],"problem,":[32],"we":[33,97],"propose":[34],"a":[35],"robust":[36],"correction":[38,114],"framework":[39,73],"combining":[40],"the":[41,61,79,88,100,116,144],"ideas":[42],"of":[43,63,94,102],"small":[44,83],"loss":[45,84,90,93],"selection":[46],"and":[47,54,91,106,126,133,138],"noise":[48,131],"correction,":[49],"which":[50],"learns":[51],"network":[52],"parameters":[53],"reassigns":[55],"ground":[56],"truth":[57],"labels":[58],"iteratively.":[59],"Taking":[60],"expertise":[62],"DNNs":[64],"learn":[66],"meaningful":[67],"patterns":[68],"before":[69],"fitting":[70],"our":[72,121,141],"first":[74],"trains":[75],"two":[76,95],"networks":[77],"over":[78],"current":[80],"dataset":[81],"selection.":[85],"Based":[86],"on":[87,123],"classification":[89],"agreement":[92],"networks,":[96],"can":[98],"measure":[99],"confidence":[101],"data.":[104],"More":[105],"more":[107],"confident":[108],"samples":[109],"are":[110],"selected":[111],"for":[112],"during":[115],"learning":[117],"process.":[118],"We":[119],"demonstrate":[120],"method":[122,142],"both":[124],"synthetic":[125],"real-world":[127],"different":[130],"types":[132],"rates,":[134],"including":[135],"CIFAR-10,":[136],"CIFAR-100":[137],"Clothing1M,":[139],"where":[140],"outperforms":[143],"baseline":[145],"approaches.":[146]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}