{"id":"https://openalex.org/W3184357819","doi":"https://doi.org/10.1109/siu53274.2021.9477825","title":"Effect of Loss Functions on Domain Adaptation in Semantic Segmentation","display_name":"Effect of Loss Functions on Domain Adaptation in Semantic Segmentation","publication_year":2021,"publication_date":"2021-06-09","ids":{"openalex":"https://openalex.org/W3184357819","doi":"https://doi.org/10.1109/siu53274.2021.9477825","mag":"3184357819"},"language":"en","primary_location":{"id":"doi:10.1109/siu53274.2021.9477825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu53274.2021.9477825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","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/A5028626788","display_name":"Kirman Serdar","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Kirman Serdar","raw_affiliation_strings":["Elektrik Elektronik Mühendisliği, Eskişehir Teknik Üniversitesi,Eskişehir"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Elektrik Elektronik Mühendisliği, Eskişehir Teknik Üniversitesi,Eskişehir","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5031295241","display_name":"H Emre Guven","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hilmi G\u00fcven","raw_affiliation_strings":["Elektrik Elektronik Mühendisliği, Eskişehir Teknik Üniversitesi,Eskişehir"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Elektrik Elektronik Mühendisliği, Eskişehir Teknik Üniversitesi,Eskişehir","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5070786755","display_name":"Cihan Topal","orcid":"https://orcid.org/0000-0002-6329-5251"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cihan Topal","raw_affiliation_strings":["Elektrik Elektronik Mühendisliği, Eskişehir Teknik Üniversitesi,Eskişehir"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Elektrik Elektronik Mühendisliği, Eskişehir Teknik Üniversitesi,Eskişehir","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.08346818,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.996999979019165,"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9958000183105469,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/softmax-function","display_name":"Softmax function","score":0.8259444236755371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7764154076576233},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7307214736938477},{"id":"https://openalex.org/keywords/domain-adaptation","display_name":"Domain adaptation","score":0.6844057440757751},{"id":"https://openalex.org/keywords/dice","display_name":"Dice","score":0.6563754677772522},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5962701439857483},{"id":"https://openalex.org/keywords/s\u00f8rensen\u2013dice-coefficient","display_name":"S\u00f8rensen\u2013Dice coefficient","score":0.565524160861969},{"id":"https://openalex.org/keywords/adaptation","display_name":"Adaptation (eye)","score":0.5179449915885925},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5020277500152588},{"id":"https://openalex.org/keywords/intersection","display_name":"Intersection (aeronautics)","score":0.44894739985466003},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.42136508226394653},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.35739976167678833},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.24851283431053162},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.11062279343605042},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.10542476177215576},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09281948208808899}],"concepts":[{"id":"https://openalex.org/C188441871","wikidata":"https://www.wikidata.org/wiki/Q7554146","display_name":"Softmax function","level":3,"score":0.8259444236755371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7764154076576233},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7307214736938477},{"id":"https://openalex.org/C2776434776","wikidata":"https://www.wikidata.org/wiki/Q19246213","display_name":"Domain adaptation","level":3,"score":0.6844057440757751},{"id":"https://openalex.org/C22029948","wikidata":"https://www.wikidata.org/wiki/Q45089","display_name":"Dice","level":2,"score":0.6563754677772522},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5962701439857483},{"id":"https://openalex.org/C163892561","wikidata":"https://www.wikidata.org/wiki/Q2613728","display_name":"S\u00f8rensen\u2013Dice coefficient","level":4,"score":0.565524160861969},{"id":"https://openalex.org/C139807058","wikidata":"https://www.wikidata.org/wiki/Q352374","display_name":"Adaptation (eye)","level":2,"score":0.5179449915885925},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5020277500152588},{"id":"https://openalex.org/C64543145","wikidata":"https://www.wikidata.org/wiki/Q162942","display_name":"Intersection (aeronautics)","level":2,"score":0.44894739985466003},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.42136508226394653},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35739976167678833},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.24851283431053162},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.11062279343605042},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10542476177215576},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09281948208808899},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/siu53274.2021.9477825","is_oa":false,"landing_page_url":"https://doi.org/10.1109/siu53274.2021.9477825","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 29th Signal Processing and Communications Applications Conference (SIU)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W2031489346","https://openalex.org/W2090923791","https://openalex.org/W2128053425","https://openalex.org/W2150066425","https://openalex.org/W2159291411","https://openalex.org/W2340897893","https://openalex.org/W2397830550","https://openalex.org/W2412782625","https://openalex.org/W2560023338","https://openalex.org/W2962976523","https://openalex.org/W2963826681","https://openalex.org/W2963840672","https://openalex.org/W2964098128"],"related_works":["https://openalex.org/W2999580839","https://openalex.org/W2973136608","https://openalex.org/W3152950745","https://openalex.org/W2897195263","https://openalex.org/W4372049117","https://openalex.org/W3116883888","https://openalex.org/W3105697449","https://openalex.org/W4360850309","https://openalex.org/W4317639945","https://openalex.org/W2630229246"],"abstract_inverted_index":{"In":[0,47,100],"this":[1,90,101],"paper,":[2],"it":[3,103,148],"is":[4,24,81,104,149,155],"analyzed":[5],"how":[6],"different":[7,73],"loss":[8],"functions":[9,120],"affect":[10],"the":[11,17,72,107,145,152],"performance":[12],"of":[13,19,29,34,75,109],"domain":[14,122],"adaptation":[15,87,123],"in":[16,42,66,84,124],"field":[18],"semantic":[20,125],"segmentation.":[21,126],"Semantic":[22],"segmentation":[23],"a":[25,58,82],"pixel-wise":[26],"classification":[27],"problem":[28,91],"an":[30],"image.":[31],"Large":[32],"amounts":[33],"annotated":[35,65],"data":[36],"are":[37,57,63,135],"required":[38],"to":[39,71],"train":[40],"successfully":[41],"multi-parameter":[43],"deep":[44],"learning":[45],"architectures.":[46],"recent":[48],"years,":[49],"several":[50],"works":[51],"have":[52],"demonstrated":[53],"that":[54,106,151],"synthetic":[55,140],"datasets":[56,134],"good":[59],"alternative":[60],"since":[61],"they":[62],"automatically":[64],"virtual":[67],"environments.":[68],"However,":[69],"due":[70],"distribution":[74],"source":[76,96],"and":[77,97,116,131,139],"target":[78,98],"datasets,":[79],"there":[80],"decrease":[83],"performance.":[85],"Domain":[86],"methods":[88],"address":[89],"by":[92],"decreasing":[93],"gap":[94],"between":[95],"data.":[99],"study,":[102,129],"investigated":[105],"effect":[108],"Cross-":[110],"Entropy,":[111],"Lovasz-Softmax,":[112],"Dice":[113,153],"Coefficient,":[114],"Tversky":[115],"mean":[117],"Intersection-over-Union":[118],"Loss":[119],"on":[121],"For":[127],"our":[128],"KITTI":[130,133],"Virtual":[132],"used":[136],"for":[137],"real":[138],"images":[141],"respectively.":[142],"By":[143],"evaluating":[144],"quantitative":[146],"results,":[147],"observed":[150],"Coefficient":[154],"relatively":[156],"more":[157],"successful.":[158]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}