{"id":"https://openalex.org/W4313001491","doi":"https://doi.org/10.1109/cvpr52688.2022.01400","title":"Propagation Regularizer for Semi-supervised Learning with Extremely Scarce Labeled Samples","display_name":"Propagation Regularizer for Semi-supervised Learning with Extremely Scarce Labeled Samples","publication_year":2022,"publication_date":"2022-06-01","ids":{"openalex":"https://openalex.org/W4313001491","doi":"https://doi.org/10.1109/cvpr52688.2022.01400"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr52688.2022.01400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01400","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085873189","display_name":"Noo-ri Kim","orcid":"https://orcid.org/0000-0002-7887-8396"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Noo-ri Kim","raw_affiliation_strings":["Sungkyunkwan University,Department of Electrical and Computer Engineering,Gyeonggi-do,Republic of Korea,16419"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University,Department of Electrical and Computer Engineering,Gyeonggi-do,Republic of Korea,16419","institution_ids":["https://openalex.org/I848706"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067651075","display_name":"Jee-Hyong Lee","orcid":"https://orcid.org/0000-0001-7242-7677"},"institutions":[{"id":"https://openalex.org/I848706","display_name":"Sungkyunkwan University","ror":"https://ror.org/04q78tk20","country_code":"KR","type":"education","lineage":["https://openalex.org/I848706"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jee-Hyong Lee","raw_affiliation_strings":["Sungkyunkwan University,Department of Electrical and Computer Engineering,Gyeonggi-do,Republic of Korea,16419"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Sungkyunkwan University,Department of Electrical and Computer Engineering,Gyeonggi-do,Republic of Korea,16419","institution_ids":["https://openalex.org/I848706"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I848706"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"14381","last_page":"14390"},"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":0.9889000058174133,"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":0.9889000058174133,"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/T12676","display_name":"Machine Learning and ELM","score":0.9750999808311462,"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":0.8132157921791077},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.7082255482673645},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6290912628173828},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.6236215829849243},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.6150605082511902},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.5676637291908264},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5010297298431396},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.42891162633895874},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.41488218307495117},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.06215527653694153}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8132157921791077},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.7082255482673645},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6290912628173828},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.6236215829849243},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.6150605082511902},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.5676637291908264},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5010297298431396},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.42891162633895874},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.41488218307495117},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.06215527653694153},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr52688.2022.01400","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr52688.2022.01400","pdf_url":null,"source":{"id":"https://openalex.org/S4363607701","display_name":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","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":"2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2012531322","https://openalex.org/W2402761219","https://openalex.org/W2785900585","https://openalex.org/W2353730437","https://openalex.org/W2490303674","https://openalex.org/W2609066826","https://openalex.org/W2810752900","https://openalex.org/W2365677836","https://openalex.org/W2531295127","https://openalex.org/W2346511343"],"abstract_inverted_index":{"Semi-supervised":[0],"learning":[1,105],"(SSL)":[2],"is":[3],"a":[4,11,21,29,60,96,132,183],"method":[5,135],"to":[6,50,92,167,170],"make":[7],"better":[8],"models":[9],"using":[10],"large":[12],"number":[13,23],"of":[14,24,33,44,62,88,125],"easily":[15],"accessible":[16],"unlabeled":[17],"data":[18,26],"along":[19],"with":[20,73,106,155],"small":[22],"labeled":[25,45,52,76,82,109,158],"obtained":[27],"at":[28],"high":[30],"cost.":[31,64],"Most":[32],"existing":[34,89,172],"SSL":[35,71],"studies":[36],"focus":[37,69],"on":[38,70,137,150,182],"the":[39,118,123,126,171],"cases":[40],"where":[41,86],"sufficient":[42],"amount":[43],"samples":[46,53,83,110],"are":[47,163],"available,":[48],"tens":[49],"hundreds":[51],"for":[54,117],"each":[55],"class,":[56,85,161],"which":[57,99,162],"still":[58],"requires":[59],"lot":[61],"labeling":[63],"In":[65,115],"this":[66],"paper,":[67],"we":[68,129],"environment":[72],"extremely":[74,107],"scarce":[75,108],"samples,":[77],"only":[78],"1":[79],"or":[80],"2":[81],"per":[84,160],"most":[87],"methods":[90,143,177],"fail":[91],"learn.":[93],"We":[94],"propose":[95,131],"propagation":[97,139],"regularizer":[98],"can":[100],"achieve":[101],"efficient":[102],"and":[103,147],"effective":[104],"by":[111,165],"suppressing":[112],"confirmation":[113],"bias.":[114],"addition,":[116],"realistic":[119],"model":[120,133],"selection":[121,134],"in":[122],"absence":[124],"validation":[127],"dataset,":[128,186],"also":[130,178],"based":[136],"our":[138,175],"regularizer.":[140],"The":[141],"proposed":[142,176],"show":[144,179],"70.9%,":[145],"30.3%,":[146],"78.9%":[148],"accuracy":[149],"CIFAR-10,":[151],"CIFAR-100,":[152],"SVHN":[153],"dataset":[154],"just":[156],"one":[157],"sample":[159],"improved":[164],"8.9%":[166],"120.2%":[168],"compared":[169],"approaches.":[173],"And":[174],"good":[180],"performance":[181],"higher":[184],"resolution":[185],"STL-10.":[187]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}