{"id":"https://openalex.org/W4408111570","doi":"https://doi.org/10.5220/0013222700003912","title":"Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator","display_name":"Accuracy Improvement of Semi-Supervised Segmentation Using Supervised ClassMix and Sup-Unsup Feature Discriminator","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4408111570","doi":"https://doi.org/10.5220/0013222700003912"},"language":"en","primary_location":{"id":"doi:10.5220/0013222700003912","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013222700003912","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0013222700003912","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062183293","display_name":"Takahiro Mano","orcid":null},"institutions":[{"id":"https://openalex.org/I96636082","display_name":"Meijo University","ror":"https://ror.org/04h42fc75","country_code":"JP","type":"education","lineage":["https://openalex.org/I96636082"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Mano","raw_affiliation_strings":["Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan","institution_ids":["https://openalex.org/I96636082"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Reiji Saito","orcid":null},"institutions":[{"id":"https://openalex.org/I96636082","display_name":"Meijo University","ror":"https://ror.org/04h42fc75","country_code":"JP","type":"education","lineage":["https://openalex.org/I96636082"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Reiji Saito","raw_affiliation_strings":["Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan","institution_ids":["https://openalex.org/I96636082"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5103163418","display_name":"Kazuhiro Hotta","orcid":"https://orcid.org/0000-0002-5675-8713"},"institutions":[{"id":"https://openalex.org/I96636082","display_name":"Meijo University","ror":"https://ror.org/04h42fc75","country_code":"JP","type":"education","lineage":["https://openalex.org/I96636082"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Kazuhiro Hotta","raw_affiliation_strings":["Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Meijo University, 1-501 Shiogamaguchi, Tempaku-ku, Nagoya 468-8502, Japan","institution_ids":["https://openalex.org/I96636082"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I96636082"],"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":null,"issue":null,"first_page":"592","last_page":"600"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10057","display_name":"Face and Expression Recognition","score":0.6858000159263611,"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/T10057","display_name":"Face and Expression Recognition","score":0.6858000159263611,"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/discriminator","display_name":"Discriminator","score":0.9547784328460693},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7342965006828308},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6998691558837891},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6834235787391663},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6461085677146912},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.6370993852615356},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5388028621673584},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.04728025197982788},{"id":"https://openalex.org/keywords/telecommunications","display_name":"Telecommunications","score":0.03737384080886841}],"concepts":[{"id":"https://openalex.org/C2779803651","wikidata":"https://www.wikidata.org/wiki/Q5282088","display_name":"Discriminator","level":3,"score":0.9547784328460693},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7342965006828308},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6998691558837891},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6834235787391663},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6461085677146912},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.6370993852615356},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5388028621673584},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.04728025197982788},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.03737384080886841},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0013222700003912","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013222700003912","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2604.07122","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2604.07122","pdf_url":"https://arxiv.org/pdf/2604.07122","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,"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.2604.07122","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2604.07122","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,"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:10.5220/0013222700003912","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0013222700003912","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities","score":0.7900000214576721}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2601157893","https://openalex.org/W2373006798","https://openalex.org/W2131735617","https://openalex.org/W2056912418","https://openalex.org/W2033213769","https://openalex.org/W4312376745","https://openalex.org/W2136016640","https://openalex.org/W2049538278","https://openalex.org/W2886173746","https://openalex.org/W4200043248"],"abstract_inverted_index":{"In":[0],"semantic":[1],"segmentation,":[2],"the":[3,33,89,111,131,148],"creation":[4],"of":[5,25,69,157],"pixel-level":[6],"labels":[7,46,105],"for":[8],"training":[9],"data":[10,79],"incurs":[11],"significant":[12],"costs.":[13],"To":[14],"address":[15],"this":[16],"problem,":[17],"semi-supervised":[18,40,164],"learning,":[19],"which":[20,86],"utilizes":[21],"a":[22,67,76,101,127],"small":[23],"number":[24],"labeled":[26,82,107,144],"images":[27,30,50,119,138],"alongside":[28],"unlabeled":[29,49,63,84,118,137],"to":[31,133,141,162],"enhance":[32],"performance,":[34],"has":[35],"gained":[36],"attention.":[37],"A":[38],"conventional":[39,163],"learning":[41,165],"method,":[42],"ClassMix,":[43],"pastes":[44],"class":[45,104],"predicted":[47],"from":[48,62,106],"onto":[51,117],"other":[52],"images.":[53,123,145],"However,":[54],"since":[55],"ClassMix":[56],"performs":[57],"operations":[58],"using":[59],"pseudo-labels":[60],"obtained":[61],"images,":[64,85,108],"there":[65,74],"is":[66,75],"risk":[68],"handling":[70],"inaccurate":[71],"labels.":[72],"Additionally,":[73],"gap":[77],"in":[78,159],"quality":[80],"between":[81],"and":[83,120,150],"can":[87],"impact":[88],"feature":[90],"maps.":[91],"This":[92],"study":[93],"addresses":[94],"these":[95],"two":[96],"issues.":[97],"First,":[98],"we":[99,125],"propose":[100],"method":[102,128],"where":[103],"along":[109],"with":[110],"corresponding":[112],"image":[113],"regions,":[114],"are":[115],"pasted":[116],"their":[121],"pseudo-labeled":[122],"Second,":[124],"introduce":[126],"that":[129],"trains":[130],"model":[132],"make":[134],"predictions":[135],"on":[136,143,147],"more":[139],"similar":[140],"those":[142],"Experiments":[146],"Chase":[149],"COVID-19":[151],"datasets":[152],"demonstrated":[153],"an":[154],"average":[155],"improvement":[156],"2.07%":[158],"mIoU":[160],"compared":[161],"methods.":[166]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}