{"id":"https://openalex.org/W4390479119","doi":"https://doi.org/10.1145/3595916.3626435","title":"Multi-head Siamese Prototype Learning against both Data and Label Corruption","display_name":"Multi-head Siamese Prototype Learning against both Data and Label Corruption","publication_year":2023,"publication_date":"2023-12-06","ids":{"openalex":"https://openalex.org/W4390479119","doi":"https://doi.org/10.1145/3595916.3626435"},"language":"en","primary_location":{"id":"doi:10.1145/3595916.3626435","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626435","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626435","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626435","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100354128","display_name":"Peng-Fei Zhang","orcid":"https://orcid.org/0000-0002-6790-2098"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Peng-Fei Zhang","raw_affiliation_strings":["University of Queensland, AU"],"raw_orcid":"https://orcid.org/0000-0002-6790-2098","affiliations":[{"raw_affiliation_string":"University of Queensland, AU","institution_ids":["https://openalex.org/I165143802"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078170935","display_name":"Zi Huang","orcid":"https://orcid.org/0000-0002-9738-4949"},"institutions":[{"id":"https://openalex.org/I165143802","display_name":"The University of Queensland","ror":"https://ror.org/00rqy9422","country_code":"AU","type":"education","lineage":["https://openalex.org/I165143802"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Zi Helen Huang","raw_affiliation_strings":["University of Queensland, AU"],"raw_orcid":"https://orcid.org/0000-0002-9738-4949","affiliations":[{"raw_affiliation_string":"University of Queensland, AU","institution_ids":["https://openalex.org/I165143802"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I165143802"],"apc_list":null,"apc_paid":null,"fwci":0.2175,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.49898164,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9878000020980835,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9850999712944031,"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/computer-science","display_name":"Computer science","score":0.789262056350708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6670883893966675},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6529780626296997},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5676854848861694},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5430890321731567},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.4488624632358551},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4466962218284607},{"id":"https://openalex.org/keywords/consistency","display_name":"Consistency (knowledge bases)","score":0.43348371982574463},{"id":"https://openalex.org/keywords/adversarial-system","display_name":"Adversarial system","score":0.4258626401424408},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.4172193109989166},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3721969723701477},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.15669235587120056},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09893026947975159}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.789262056350708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6670883893966675},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6529780626296997},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5676854848861694},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5430890321731567},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.4488624632358551},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4466962218284607},{"id":"https://openalex.org/C2776436953","wikidata":"https://www.wikidata.org/wiki/Q5163215","display_name":"Consistency (knowledge bases)","level":2,"score":0.43348371982574463},{"id":"https://openalex.org/C37736160","wikidata":"https://www.wikidata.org/wiki/Q1801315","display_name":"Adversarial system","level":2,"score":0.4258626401424408},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.4172193109989166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3721969723701477},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.15669235587120056},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09893026947975159},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3595916.3626435","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626435","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626435","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3595916.3626435","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3595916.3626435","pdf_url":"https://dl.acm.org/doi/pdf/10.1145/3595916.3626435","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Multimedia Asia 2023","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","score":0.7300000190734863,"display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390479119.pdf","grobid_xml":"https://content.openalex.org/works/W4390479119.grobid-xml"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2566079294","https://openalex.org/W2907508577","https://openalex.org/W2912083425","https://openalex.org/W2914393402","https://openalex.org/W2964292098","https://openalex.org/W3042609801","https://openalex.org/W3081788389","https://openalex.org/W3118471355","https://openalex.org/W3122091215","https://openalex.org/W3135808071","https://openalex.org/W3155471926","https://openalex.org/W3173423020","https://openalex.org/W3208049411","https://openalex.org/W3211393740","https://openalex.org/W4206455036","https://openalex.org/W4206513838","https://openalex.org/W4236965008","https://openalex.org/W4247200422","https://openalex.org/W4286865884","https://openalex.org/W4301409532","https://openalex.org/W4312601326","https://openalex.org/W6740005241","https://openalex.org/W6782074319","https://openalex.org/W6797172672"],"related_works":["https://openalex.org/W2502115930","https://openalex.org/W2482350142","https://openalex.org/W4246396837","https://openalex.org/W3126451824","https://openalex.org/W1561927205","https://openalex.org/W3191453585","https://openalex.org/W4297672492","https://openalex.org/W4389116644","https://openalex.org/W4310988119","https://openalex.org/W4385544042"],"abstract_inverted_index":{"The":[0],"training":[1],"of":[2,36,40,50,107,209],"the":[3,16,34,48,98,105,108,122,125,133,141,164,182,185,207,210,214],"Deep":[4],"Neural":[5],"Network":[6],"(DNN)":[7],"has":[8],"been":[9],"seriously":[10],"challenged":[11],"by":[12,74,162],"insidious":[13],"noise":[14,19],"in":[15,20,25,77,83,167,213],"dataset,":[17],"including":[18],"raw":[21],"data":[22,138,188,190,196,198],"and":[23,71,79,170,194],"errors":[24],"annotations.":[26],"Existing":[27],"methods":[28],"usually":[29],"limit":[30],"their":[31],"efforts":[32],"to":[33,67,103,110,120,144,157,180],"defense":[35],"one":[37],"particular":[38],"kind":[39],"noise,":[41,148],"which":[42],"would":[43],"be":[44],"powerless":[45],"when":[46],"facing":[47],"coexistence":[49],"various":[51],"noise.":[52,111,139],"To":[53],"deal":[54,145],"with":[55,97,124,146,184,191,199],"it,":[56],"we":[57],"propose":[58],"a":[59,87],"novel":[60],"Multi-head":[61],"Siamese":[62,89],"Prototype":[63],"Learning":[64],"(MSPL)":[65],"method":[66,212],"promote":[68],"discriminative":[69],"features":[70],"representative":[72],"prototypes":[73],"modeling":[75],"invariance":[76],"samples":[78],"sieving":[80],"out":[81,159],"incorrectness":[82],"labels.":[84],"More":[85],"specifically,":[86],"multi-head":[88],"network":[90],"structure":[91],"is":[92,101,118,155,177],"constructed,":[93],"where":[94],"prototype":[95],"learning":[96,117,176,217],"multi-consistency":[99],"constraint":[100],"performed":[102,119],"improve":[104],"resilience":[106],"model":[109,123,183],"Under":[112],"this":[113],"regime,":[114],"adversarial":[115,129],"contrastive":[116],"train":[121,181],"dynamically":[126],"generated":[127],"vicious":[128],"examples,":[130],"further":[131],"enhancing":[132],"invariant":[134],"predictive":[135],"ability":[136],"against":[137],"At":[140],"same":[142],"time,":[143],"label":[147],"an":[149],"effective":[150],"multi-granularity":[151],"sample":[152],"selection":[153],"strategy":[154],"designed":[156],"filter":[158],"noisy":[160,200,216],"labels":[161],"measuring":[163],"error":[165],"distribution":[166],"both":[168],"global":[169],"local":[171],"(i.e.,":[172,189,197],"class-specific)":[173],"perspectives.":[174],"Semi-supervised":[175],"accordingly":[178],"conducted":[179],"resulting":[186],"labelled":[187],"clean":[192],"labels)":[193],"unlabelled":[195],"labels).":[201],"Extensive":[202],"experiments":[203],"on":[204],"benchmarks":[205],"demonstrate":[206],"effectiveness":[208],"proposed":[211],"extremely":[215],"environment.":[218]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-30T17:31:21.811387","created_date":"2025-10-10T00:00:00"}