{"id":"https://openalex.org/W3206780676","doi":"https://doi.org/10.14428/esann/2021.es2021-158","title":"Temperature as a Regularizer for Semantic Segmentation","display_name":"Temperature as a Regularizer for Semantic Segmentation","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3206780676","doi":"https://doi.org/10.14428/esann/2021.es2021-158","mag":"3206780676"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2021.es2021-158","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2021.es2021-158","pdf_url":"https://doi.org/10.14428/esann/2021.es2021-158","source":{"id":"https://openalex.org/S4306509709","display_name":"ESANN 2021 proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2021 proceedings","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.14428/esann/2021.es2021-158","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5066861225","display_name":"Chanho Kim","orcid":null},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Chanho Kim","raw_affiliation_strings":["University of Ottawa -School of Electrical Engineering and Computer Science (EECS) 800 King Edward Ave, Ottawa, ON -CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Ottawa -School of Electrical Engineering and Computer Science (EECS) 800 King Edward Ave, Ottawa, ON -CANADA","institution_ids":["https://openalex.org/I153718931"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5063382504","display_name":"Won\u2010Sook Lee","orcid":"https://orcid.org/0000-0003-3024-3081"},"institutions":[{"id":"https://openalex.org/I153718931","display_name":"University of Ottawa","ror":"https://ror.org/03c4mmv16","country_code":"CA","type":"education","lineage":["https://openalex.org/I153718931"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Won-Sook Lee","raw_affiliation_strings":["University of Ottawa -School of Electrical Engineering and Computer Science (EECS) 800 King Edward Ave, Ottawa, ON -CANADA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Ottawa -School of Electrical Engineering and Computer Science (EECS) 800 King Edward Ave, Ottawa, ON -CANADA","institution_ids":["https://openalex.org/I153718931"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I153718931"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.14110478,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"213","last_page":"218"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.35420000553131104,"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/T10320","display_name":"Neural Networks and Applications","score":0.35420000553131104,"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/T11948","display_name":"Machine Learning in Materials Science","score":0.3075999915599823,"subfield":{"id":"https://openalex.org/subfields/2505","display_name":"Materials Chemistry"},"field":{"id":"https://openalex.org/fields/25","display_name":"Materials Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10181","display_name":"Natural Language Processing Techniques","score":0.3068000078201294,"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":0.6783959865570068},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5625705718994141},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5623330473899841},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.44503673911094666},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4361182153224945},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.35805246233940125}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6783959865570068},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5625705718994141},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5623330473899841},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.44503673911094666},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4361182153224945},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.35805246233940125}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2021.es2021-158","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2021.es2021-158","pdf_url":"https://doi.org/10.14428/esann/2021.es2021-158","source":{"id":"https://openalex.org/S4306509709","display_name":"ESANN 2021 proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2021 proceedings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2021.es2021-158","is_oa":true,"landing_page_url":"http://doi.org/10.14428/esann/2021.es2021-158","pdf_url":"https://doi.org/10.14428/esann/2021.es2021-158","source":{"id":"https://openalex.org/S4306509709","display_name":"ESANN 2021 proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2021 proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3206780676.pdf","grobid_xml":"https://content.openalex.org/works/W3206780676.grobid-xml"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W4919037","https://openalex.org/W1686810756","https://openalex.org/W1821462560","https://openalex.org/W1903029394","https://openalex.org/W2095705004","https://openalex.org/W2108598243","https://openalex.org/W2144513243","https://openalex.org/W2144794286","https://openalex.org/W2163605009","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2593414223","https://openalex.org/W2739748921","https://openalex.org/W2787241931","https://openalex.org/W2902332991","https://openalex.org/W2921853515","https://openalex.org/W2948210185","https://openalex.org/W2952787292","https://openalex.org/W2963263347","https://openalex.org/W2963684088","https://openalex.org/W2963855133","https://openalex.org/W4295521014","https://openalex.org/W4298289240","https://openalex.org/W4308909683"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W4324315429","https://openalex.org/W2501551404","https://openalex.org/W4385583601","https://openalex.org/W4366829857","https://openalex.org/W4298131179","https://openalex.org/W2033914206","https://openalex.org/W2042327336","https://openalex.org/W1522196789"],"abstract_inverted_index":{"A":[0,13],"data-oriented":[1],"approach":[2],"including":[3],"all":[4],"deep":[5],"learning":[6],"methods":[7],"is":[8],"usually":[9],"suffered":[10],"by":[11,26],"overfitting.":[12],"regularizer":[14,50,85],"has":[15],"been,":[16],"from":[17],"the":[18,34,77],"beginning,":[19],"introduced":[20],"to":[21,37],"resolve":[22],"this":[23],"problem.":[24],"Inspired":[25],"Generative":[27],"Adversarial":[28],"Network":[29],"(GAN),":[30],"our":[31,66],"framework":[32],"generates":[33],"adversarial":[35],"loss":[36],"penalize":[38],"a":[39,43,49,60,63],"segmentation":[40],"model":[41],"like":[42],"regularizer.":[44],"We":[45],"introduce":[46],"temperature":[47,87],"as":[48],"when":[51],"calculating":[52],"Least-Square":[53],"losses.":[54],"Temperature":[55],"affects":[56],"losses":[57,73,80],"in":[58,65,93],"both":[59,92],"discriminator":[61],"and":[62,96],"generator":[64],"DCGAN":[67],"framework.":[68],"Our":[69],"experiment":[70],"suggests":[71],"L2":[72],"on":[74],"top":[75],"of":[76],"original":[78],"LSGAN":[79],"for":[81],"optimization.":[82],"This":[83],"new":[84],"using":[86],"improves":[88],"semantic":[89],"Segmentation":[90],"accuracy":[91,95],"Pixel":[94],"mean":[97],"Intersection-of":[98],"Union.":[99]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}