{"id":"https://openalex.org/W2920240795","doi":"https://doi.org/10.1609/aaai.v33i01.33013396","title":"Utilizing Class Information for Deep Network Representation Shaping","display_name":"Utilizing Class Information for Deep Network Representation Shaping","publication_year":2019,"publication_date":"2019-07-17","ids":{"openalex":"https://openalex.org/W2920240795","doi":"https://doi.org/10.1609/aaai.v33i01.33013396","mag":"2920240795"},"language":"en","primary_location":{"id":"doi:10.1609/aaai.v33i01.33013396","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013396","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.1609/aaai.v33i01.33013396","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101854638","display_name":"Daeyoung Choi","orcid":"https://orcid.org/0000-0001-6323-4478"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Daeyoung Choi","raw_affiliation_strings":["Seoul National University","Seoul National Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5056032525","display_name":"Wonjong Rhee","orcid":"https://orcid.org/0000-0002-2590-8774"},"institutions":[{"id":"https://openalex.org/I139264467","display_name":"Seoul National University","ror":"https://ror.org/04h9pn542","country_code":"KR","type":"education","lineage":["https://openalex.org/I139264467"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wonjong Rhee","raw_affiliation_strings":["Seoul National University","Seoul National Univ.#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Seoul National University","institution_ids":["https://openalex.org/I139264467"]},{"raw_affiliation_string":"Seoul National Univ.#TAB#","institution_ids":["https://openalex.org/I139264467"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I139264467"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":"01","first_page":"3396","last_page":"3403"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9998999834060669,"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":0.9976999759674072,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9962999820709229,"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/interpretability","display_name":"Interpretability","score":0.8281903862953186},{"id":"https://openalex.org/keywords/covariance","display_name":"Covariance","score":0.7548267245292664},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.689498782157898},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5953673124313354},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5783640146255493},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5698262453079224},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5101128220558167},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5064204931259155},{"id":"https://openalex.org/keywords/regularization","display_name":"Regularization (linguistics)","score":0.5061742663383484},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4722149968147278},{"id":"https://openalex.org/keywords/variance","display_name":"Variance (accounting)","score":0.46645301580429077},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.465880811214447},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.24696356058120728},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.1648121476173401}],"concepts":[{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.8281903862953186},{"id":"https://openalex.org/C178650346","wikidata":"https://www.wikidata.org/wiki/Q201984","display_name":"Covariance","level":2,"score":0.7548267245292664},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.689498782157898},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5953673124313354},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5783640146255493},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5698262453079224},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5101128220558167},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5064204931259155},{"id":"https://openalex.org/C2776135515","wikidata":"https://www.wikidata.org/wiki/Q17143721","display_name":"Regularization (linguistics)","level":2,"score":0.5061742663383484},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4722149968147278},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.46645301580429077},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.465880811214447},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.24696356058120728},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.1648121476173401},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C121955636","wikidata":"https://www.wikidata.org/wiki/Q4116214","display_name":"Accounting","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1609/aaai.v33i01.33013396","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013396","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1809.09307","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1809.09307","pdf_url":"https://arxiv.org/pdf/1809.09307","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"","raw_type":"text"},{"id":"mag:2920240795","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/1809.09307","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.1809.09307","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.1809.09307","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.1609/aaai.v33i01.33013396","is_oa":true,"landing_page_url":"https://doi.org/10.1609/aaai.v33i01.33013396","pdf_url":null,"source":{"id":"https://openalex.org/S4210191458","display_name":"Proceedings of the AAAI Conference on Artificial Intelligence","issn_l":"2159-5399","issn":["2159-5399","2374-3468"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320058","host_organization_name":"Association for the Advancement of Artificial Intelligence","host_organization_lineage":["https://openalex.org/P4310320058"],"host_organization_lineage_names":["Association for the Advancement of Artificial Intelligence"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the AAAI Conference on Artificial Intelligence","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2385274007","display_name":null,"funder_award_id":"NRF-2017R1E1A1A03070560","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":26,"referenced_works":["https://openalex.org/W1836465849","https://openalex.org/W1915328033","https://openalex.org/W2047028564","https://openalex.org/W2084716923","https://openalex.org/W2095705004","https://openalex.org/W2135046866","https://openalex.org/W2156387975","https://openalex.org/W2194775991","https://openalex.org/W2284050935","https://openalex.org/W2520774990","https://openalex.org/W2560977758","https://openalex.org/W2753553146","https://openalex.org/W2799262739","https://openalex.org/W2900130267","https://openalex.org/W2962684187","https://openalex.org/W2962840515","https://openalex.org/W2963000224","https://openalex.org/W2963314614","https://openalex.org/W2963685250","https://openalex.org/W3137695714","https://openalex.org/W6662903892","https://openalex.org/W6682889407","https://openalex.org/W6687483927","https://openalex.org/W6709037320","https://openalex.org/W6725543821","https://openalex.org/W6730178624"],"related_works":["https://openalex.org/W2965106929","https://openalex.org/W2951748910","https://openalex.org/W2895608766","https://openalex.org/W3207580420","https://openalex.org/W2971894349","https://openalex.org/W3159223334","https://openalex.org/W3207631527","https://openalex.org/W2549726308","https://openalex.org/W2931956500","https://openalex.org/W3127682739","https://openalex.org/W3207315294","https://openalex.org/W3209616103","https://openalex.org/W3011461004","https://openalex.org/W3082883578","https://openalex.org/W2562540632","https://openalex.org/W3198923159","https://openalex.org/W2892611525","https://openalex.org/W3007541474","https://openalex.org/W2793374993","https://openalex.org/W1495279923"],"abstract_inverted_index":{"Statistical":[0],"characteristics":[1],"of":[2,21,109,127,138,180,198],"deep":[3,22],"network":[4],"representations,":[5],"such":[6,44,72],"as":[7],"sparsity":[8],"and":[9,19,37,98,149,162,166,188],"correlation,":[10],"are":[11,153,159],"known":[12],"to":[13,16,48,65,105,131],"be":[14,35,63,77],"relevant":[15],"the":[17,40,67,82,107,113,136,167,171,186,209],"performance":[18,211],"interpretability":[20],"learning.":[23],"When":[24],"a":[25,45,50],"statistical":[26,51],"characteristic":[27,52,69],"is":[28,122,129],"desired,":[29],"often":[30],"an":[31],"adequate":[32],"regularizer":[33,46],"can":[34,76],"designed":[36],"applied":[38],"during":[39],"training":[41],"phase.":[42],"Typically,":[43],"aims":[47],"manipulate":[49],"over":[53,185,201],"all":[54],"classes":[55,75],"together.":[56,155],"For":[57,135],"classification":[58,181],"tasks,":[59],"however,":[60],"it":[61],"might":[62],"advantageous":[64],"enforce":[66],"desired":[68],"per":[70],"class":[71,92,115,144],"that":[73,89,170],"different":[74],"better":[78],"distinguished.":[79],"Motivated":[80],"by":[81],"idea,":[83],"we":[84],"design":[85],"two":[86],"class-wise":[87,94],"regularizers":[88,158,172],"explicitly":[90],"utilize":[91],"information:":[93],"Covariance":[95,146],"Regularizer":[96,101,147,151],"(cw-CR)":[97],"classwise":[99],"Variance":[100,150],"(cw-VR).":[102],"cw-CR":[103],"targets":[104],"reduce":[106],"covariance":[108,128],"representations":[110],"calculated":[111],"from":[112],"same":[114],"samples":[116],"for":[117,195,212],"encouraging":[118],"feature":[119,133],"independence.":[120],"cw-VR":[121,207],"similar,":[123],"but":[124],"variance":[125],"instead":[126],"targeted":[130],"improve":[132],"compactness.":[134],"sake":[137],"completeness,":[139],"their":[140],"counterparts":[141],"without":[142],"using":[143],"information,":[145],"(CR)":[148],"(VR),":[152],"considered":[154],"The":[156],"four":[157],"conceptually":[160],"simple":[161],"computationally":[163],"very":[164],"efficient,":[165],"visualization":[168],"shows":[169],"indeed":[173],"perform":[174],"distinct":[175],"representation":[176],"shaping.":[177],"In":[178,205],"terms":[179],"performance,":[182],"significant":[183],"improvements":[184],"baseline":[187],"L1/L2":[189],"weight":[190],"regularization":[191],"methods":[192],"were":[193],"found":[194],"21":[196],"out":[197],"22":[199],"tasks":[200,214],"popular":[202],"benchmark":[203],"datasets.":[204],"particular,":[206],"achieved":[208],"best":[210],"13":[213],"including":[215],"ResNet-32/110.":[216]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}