{"id":"https://openalex.org/W2963314614","doi":"https://doi.org/10.1109/cvpr.2018.00366","title":"Robust Classification with Convolutional Prototype Learning","display_name":"Robust Classification with Convolutional Prototype Learning","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2963314614","doi":"https://doi.org/10.1109/cvpr.2018.00366","mag":"2963314614"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2018.00366","doi":"https://doi.org/10.1109/cvpr.2018.00366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00366","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1805.03438","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112506595","display_name":"Hongming Yang","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hong-Ming Yang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082548671","display_name":"Xu-Yao Zhang","orcid":"https://orcid.org/0000-0001-9260-188X","observed_orcids":["https://orcid.org/0000-0001-9260-188X"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xu-Yao Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5039310938","display_name":"Fei Yin","orcid":"https://orcid.org/0000-0002-6412-9140","observed_orcids":["https://orcid.org/0000-0002-6412-9140"]},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fei Yin","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, P.R. China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100714202","display_name":"Cheng\u2010Lin Liu","orcid":"https://orcid.org/0000-0002-6743-4175","observed_orcids":["https://orcid.org/0000-0002-6743-4175"]},"institutions":[{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"government","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Cheng-Lin Liu","raw_affiliation_strings":["CAS Center for Excellence of Brain Science and Intelligence Technology, Beijing, P.R. China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"CAS Center for Excellence of Brain Science and Intelligence Technology, Beijing, P.R. China","institution_ids":["https://openalex.org/I19820366"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":6.885,"has_fulltext":true,"cited_by_count":506,"citation_normalized_percentile":{"value":0.97385954,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":96,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3474","last_page":"3482"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7544000148773193,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7544000148773193,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.1680999994277954,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.06239999830722809,"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/robust-classification","display_name":"robust classification","score":0.6980000138282776},{"id":"https://openalex.org/keywords/adversarial-robustness","display_name":"adversarial robustness","score":0.7799999713897705},{"id":"https://openalex.org/keywords/softmax-layer","display_name":"softmax layer","score":0.7260000109672546},{"id":"https://openalex.org/keywords/open-world-recognition","display_name":"open-world recognition","score":0.9049999713897705},{"id":"https://openalex.org/keywords/intra-class-compactness","display_name":"intra-class compactness","score":0.8299999833106995},{"id":"https://openalex.org/keywords/generative-models","display_name":"generative models","score":0.6299999952316284},{"id":"https://openalex.org/keywords/image-classification","display_name":"image classification","score":0.75}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8388726711273193},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.7876486778259277},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7649742364883423},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7342414259910583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6769818067550659},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5740317106246948},{"id":"https://openalex.org/C59404180","wikidata":"https://www.wikidata.org/wiki/Q17013334","display_name":"Feature learning","level":2,"score":0.5333141684532166},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5145813822746277},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4996812343597412},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.49127811193466187},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.42594239115715027},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.10143411159515381},{"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},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/cvpr.2018.00366","doi":"https://doi.org/10.1109/cvpr.2018.00366","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00366","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"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":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:1805.03438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.03438","pdf_url":"https://arxiv.org/pdf/1805.03438","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.1805.03438","doi":"https://doi.org/10.48550/arxiv.1805.03438","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1805.03438","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1805.03438","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/1805.03438","pdf_url":"https://arxiv.org/pdf/1805.03438","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"study_designs":[],"awards":[{"id":"https://openalex.org/G6431871145","display_name":null,"funder_award_id":"61721004","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7010190359","display_name":"\u6df1\u5ea6\u8ba4\u77e5\u795e\u7ecf\u7f51\u7edc\u7406\u8bba\u4e0e\u65b9\u6cd5\u7814\u7a76","funder_award_id":"61633021","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320309480","display_name":"Nvidia","ror":"https://ror.org/03jdj4y14"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2963314614.pdf","grobid_xml":"https://content.openalex.org/works/W2963314614.grobid-xml"},"referenced_works_count":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1673923490","https://openalex.org/W1677182931","https://openalex.org/W1686810756","https://openalex.org/W1946293154","https://openalex.org/W1978482254","https://openalex.org/W1978964824","https://openalex.org/W1988418786","https://openalex.org/W1990863955","https://openalex.org/W1999567757","https://openalex.org/W2012672587","https://openalex.org/W2023935830","https://openalex.org/W2046079134","https://openalex.org/W2054564221","https://openalex.org/W2063500021","https://openalex.org/W2063541597","https://openalex.org/W2096733369","https://openalex.org/W2097000478","https://openalex.org/W2097216480","https://openalex.org/W2112796928","https://openalex.org/W2123045220","https://openalex.org/W2123749980","https://openalex.org/W2127839699","https://openalex.org/W2134969019","https://openalex.org/W2138621090","https://openalex.org/W2144172034","https://openalex.org/W2154579312","https://openalex.org/W2156338447","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2261268509","https://openalex.org/W2294059674","https://openalex.org/W2407521645","https://openalex.org/W2520774990","https://openalex.org/W2594407953","https://openalex.org/W2604735854","https://openalex.org/W2962779710","https://openalex.org/W2963150697","https://openalex.org/W2963466847","https://openalex.org/W2964153729","https://openalex.org/W3037950864","https://openalex.org/W3118608800","https://openalex.org/W6674599109","https://openalex.org/W7099244549"],"related_works":["https://openalex.org/W3113047382","https://openalex.org/W4310413889","https://openalex.org/W4206824656","https://openalex.org/W4210456479","https://openalex.org/W2774226989","https://openalex.org/W4414455593","https://openalex.org/W4367402037","https://openalex.org/W4402352269","https://openalex.org/W3099308814","https://openalex.org/W2180290696"],"abstract_inverted_index":{"Convolutional":[0],"neural":[1],"networks":[2],"(CNNs)":[3],"have":[4],"been":[5,17],"widely":[6],"used":[7],"for":[8,34,47,187],"image":[9],"classification.":[10,36],"Despite":[11],"its":[12],"high":[13],"accuracies,":[14],"CNN":[15,29,48],"has":[16],"shown":[18],"to":[19,122,136],"be":[20,147],"easily":[21],"fooled":[22],"by":[23,51],"some":[24],"adversarial":[25],"examples,":[26],"indicating":[27],"that":[28,42,97,166],"is":[30,49,56,96,131],"not":[31],"robust":[32],"enough":[33],"pattern":[35],"In":[37],"this":[38],"paper,":[39],"we":[40,80,117],"argue":[41],"the":[43,52,64,78,102,110,113,124,138,142,155,180,189],"lack":[44],"of":[45,66,74,93,115,141,158],"robustness":[46,181],"caused":[50],"softmax":[53],"layer,":[54],"which":[55,145],"a":[57,71,82,127,134,150],"totally":[58],"discriminative":[59],"model":[60,152],"and":[61,107,178,191],"based":[62,153],"on":[63,154,162],"assumption":[65,157],"closed":[67],"world":[68,104],"(i.e.,":[69],"with":[70],"fixed":[72],"number":[73],"categories).":[75],"To":[76],"improve":[77,109,137],"robustness,":[79],"propose":[81],"novel":[83],"learning":[84,89,194],"framework":[85,114],"called":[86],"convolutional":[87],"prototype":[88,128],"(CPL).":[90],"The":[91],"advantage":[92],"using":[94],"prototypes":[95],"it":[98],"can":[99,146,168],"well":[100],"handle":[101],"open":[103],"recognition":[105],"problem":[106],"therefore":[108],"robustness.":[111],"Under":[112],"CPL,":[116],"design":[118],"multiple":[119],"classification":[120],"criteria":[121],"train":[123],"network.":[125],"Moreover,":[126],"loss":[129],"(PL)":[130],"proposed":[132],"as":[133,149],"regularization":[135],"intra-class":[139],"compactness":[140],"feature":[143],"representation,":[144],"viewed":[148],"generative":[151],"Gaussian":[156],"different":[159],"classes.":[160],"Experiments":[161],"several":[163],"datasets":[164],"demonstrate":[165],"CPL":[167,183],"achieve":[169],"comparable":[170],"or":[171],"even":[172],"better":[173],"results":[174],"than":[175],"traditional":[176],"CNN,":[177],"from":[179],"perspective,":[182],"shows":[184],"great":[185],"advantages":[186],"both":[188],"rejection":[190],"incremental":[192],"category":[193],"tasks.":[195]},"counts_by_year":[{"year":2026,"cited_by_count":52},{"year":2025,"cited_by_count":106},{"year":2024,"cited_by_count":100},{"year":2023,"cited_by_count":89},{"year":2022,"cited_by_count":65},{"year":2021,"cited_by_count":52},{"year":2020,"cited_by_count":28},{"year":2019,"cited_by_count":11},{"year":2018,"cited_by_count":3}],"updated_date":"2026-11-10T11:39:43.021295","created_date":"2019-07-30T00:00:00"}