{"id":"https://openalex.org/W4410602189","doi":"https://doi.org/10.3390/jimaging11060172","title":"Unsupervised Class Generation to Expand Semantic Segmentation Datasets","display_name":"Unsupervised Class Generation to Expand Semantic Segmentation Datasets","publication_year":2025,"publication_date":"2025-05-22","ids":{"openalex":"https://openalex.org/W4410602189","doi":"https://doi.org/10.3390/jimaging11060172","pmid":"https://pubmed.ncbi.nlm.nih.gov/40558771"},"language":"en","primary_location":{"id":"doi:10.3390/jimaging11060172","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11060172","pdf_url":"https://www.mdpi.com/2313-433X/11/6/172/pdf?version=1747894740","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj","pubmed"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/2313-433X/11/6/172/pdf?version=1747894740","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5056547152","display_name":"Javier Montalvo","orcid":"https://orcid.org/0000-0001-6610-1566"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":true,"raw_author_name":"Javier Montalvo","raw_affiliation_strings":["Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0001-6610-1566","affiliations":[{"raw_affiliation_string":"Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015024907","display_name":"\u00c1lvaro Garc\u00eda\u2010Mart\u00edn","orcid":"https://orcid.org/0000-0002-1705-3972"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"\u00c1lvaro Garc\u00eda-Mart\u00edn","raw_affiliation_strings":["Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-1705-3972","affiliations":[{"raw_affiliation_string":"Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014470144","display_name":"Pablo Carballeira","orcid":"https://orcid.org/0000-0002-7199-698X"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Pablo Carballeira","raw_affiliation_strings":["Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-7199-698X","affiliations":[{"raw_affiliation_string":"Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5025958097","display_name":"Juan C. SanMiguel","orcid":"https://orcid.org/0000-0002-4999-2851"},"institutions":[{"id":"https://openalex.org/I63634437","display_name":"Universidad Aut\u00f3noma de Madrid","ror":"https://ror.org/01cby8j38","country_code":"ES","type":"education","lineage":["https://openalex.org/I63634437"]}],"countries":["ES"],"is_corresponding":false,"raw_author_name":"Juan C. SanMiguel","raw_affiliation_strings":["Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain"],"raw_orcid":"https://orcid.org/0000-0002-4999-2851","affiliations":[{"raw_affiliation_string":"Video Processing and Understanding Lab, Escuela Polit\u00e9cnica Superior, Universidad Aut\u00f3noma de Madrid, 28049 Madrid, Spain","institution_ids":["https://openalex.org/I63634437"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5056547152"],"corresponding_institution_ids":["https://openalex.org/I63634437"],"apc_list":{"value":1600,"currency":"CHF","value_usd":1782},"apc_paid":{"value":1600,"currency":"CHF","value_usd":1782},"fwci":1.0951,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75872068,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":97},"biblio":{"volume":"11","issue":"6","first_page":"172","last_page":"172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9991999864578247,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9987000226974487,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9980999827384949,"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/computer-science","display_name":"Computer science","score":0.8290762901306152},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6925587058067322},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.675392746925354},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6181109547615051},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.4942207634449005},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.41838058829307556},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3920769989490509}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8290762901306152},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6925587058067322},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.675392746925354},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6181109547615051},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.4942207634449005},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.41838058829307556},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3920769989490509}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.3390/jimaging11060172","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11060172","pdf_url":"https://www.mdpi.com/2313-433X/11/6/172/pdf?version=1747894740","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},{"id":"pmid:40558771","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/40558771","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of imaging","raw_type":null},{"id":"pmh:oai:doaj.org/article:3015d78efe21424d95d08e85538d1d88","is_oa":true,"landing_page_url":"https://doaj.org/article/3015d78efe21424d95d08e85538d1d88","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Journal of Imaging, Vol 11, Iss 6, p 172 (2025)","raw_type":"article"},{"id":"pmh:oai:pubmedcentral.nih.gov:12194140","is_oa":true,"landing_page_url":"https://www.ncbi.nlm.nih.gov/pmc/articles/12194140","pdf_url":null,"source":{"id":"https://openalex.org/S2764455111","display_name":"PubMed Central","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"J Imaging","raw_type":"Text"}],"best_oa_location":{"id":"doi:10.3390/jimaging11060172","is_oa":true,"landing_page_url":"https://doi.org/10.3390/jimaging11060172","pdf_url":"https://www.mdpi.com/2313-433X/11/6/172/pdf?version=1747894740","source":{"id":"https://openalex.org/S2736465063","display_name":"Journal of Imaging","issn_l":"2313-433X","issn":["2313-433X"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Imaging","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G4582345598","display_name":null,"funder_award_id":"TEC-2024/COM-322","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"},{"id":"https://openalex.org/G8284237729","display_name":null,"funder_award_id":"PID2021-125051OB-I00","funder_id":"https://openalex.org/F4320315062","funder_display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades"},{"id":"https://openalex.org/G8701379388","display_name":null,"funder_award_id":"PID2021-125051OB-I00","funder_id":"https://openalex.org/F4320322930","funder_display_name":"Ministerio de Ciencia e Innovaci\u00f3n"}],"funders":[{"id":"https://openalex.org/F4320315062","display_name":"Ministerio de Ciencia, Innovaci\u00f3n y Universidades","ror":null},{"id":"https://openalex.org/F4320322930","display_name":"Ministerio de Ciencia e Innovaci\u00f3n","ror":"https://ror.org/034900433"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4410602189.pdf","grobid_xml":"https://content.openalex.org/works/W4410602189.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W2031489346","https://openalex.org/W2132927647","https://openalex.org/W2161236525","https://openalex.org/W2340897893","https://openalex.org/W2431874326","https://openalex.org/W2487365028","https://openalex.org/W2601484520","https://openalex.org/W2605102758","https://openalex.org/W2615547864","https://openalex.org/W2963073217","https://openalex.org/W2963107255","https://openalex.org/W2964285681","https://openalex.org/W2984957018","https://openalex.org/W3117590843","https://openalex.org/W3120804725","https://openalex.org/W3183166151","https://openalex.org/W3206360173","https://openalex.org/W3216568609","https://openalex.org/W3217147624","https://openalex.org/W4285139519","https://openalex.org/W4295832130","https://openalex.org/W4312768455","https://openalex.org/W4312933868","https://openalex.org/W4362631127","https://openalex.org/W4380053223","https://openalex.org/W4385569875","https://openalex.org/W4385825654","https://openalex.org/W4386047746","https://openalex.org/W4386066047","https://openalex.org/W4386918902","https://openalex.org/W4390874575","https://openalex.org/W4398226180","https://openalex.org/W4402772505","https://openalex.org/W4403049104","https://openalex.org/W6680210483","https://openalex.org/W6735859743","https://openalex.org/W6745935785","https://openalex.org/W6855239411"],"related_works":["https://openalex.org/W4379231730","https://openalex.org/W4389858081","https://openalex.org/W2501551404","https://openalex.org/W4298131179","https://openalex.org/W2113201962","https://openalex.org/W4385583601","https://openalex.org/W4395685956","https://openalex.org/W3159516372","https://openalex.org/W4398146871","https://openalex.org/W4387803165"],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,25,147,161],"is":[2,9,26,78,94],"a":[3,37,69,150,233],"computer":[4],"vision":[5],"task":[6],"where":[7],"classification":[8],"performed":[10],"at":[11],"the":[12,18,40,87,107,113,173,185,191],"pixel":[13],"level.":[14],"Due":[15],"to":[16,61,73,81,90,140,152,171,190,207],"this,":[17],"process":[19],"of":[20,42,109,115,175,215],"labeling":[21],"images":[22,117],"for":[23,156,220,227],"semantic":[24,160],"time-consuming":[27],"and":[28,136,149],"expensive.":[29],"To":[30],"mitigate":[31],"this":[32,125],"cost":[33],"there":[34],"has":[35],"been":[36],"surge":[38],"in":[39,51,159],"use":[41],"synthetically":[43],"generated":[44,154],"data-usually":[45],"created":[46],"using":[47],"simulators":[48],"or":[49],"videogames-which,":[50],"combination":[52],"with":[53,106,144,164,211],"domain":[54,177],"adaptation":[55,178],"methods,":[56,196],"can":[57,201],"effectively":[58,204],"learn":[59,205],"how":[60,199,206],"segment":[62,208],"real":[63],"data.":[64],"Still,":[65],"these":[66],"datasets":[67],"have":[68,101],"particular":[70],"limitation:":[71],"due":[72],"their":[74],"closed-set":[75],"nature,":[76],"it":[77],"not":[79,96,202],"possible":[80],"include":[82],"novel":[83,157,182,209,221],"classes":[84,158],"without":[85,121,188],"modifying":[86],"tool":[88],"used":[89],"generate":[91,141],"them,":[92],"which":[93],"often":[95],"public.":[97],"Concurrently,":[98],"generative":[99],"models":[100,200],"made":[102],"remarkable":[103],"progress,":[104],"particularly":[105],"introduction":[108],"diffusion":[110],"models,":[111],"enabling":[112],"creation":[114],"high-quality":[116],"from":[118],"text":[119],"prompts":[120],"additional":[122],"supervision.":[123],"In":[124],"work,":[126],"we":[127,197],"propose":[128],"an":[129,145,212],"unsupervised":[130,176],"pipeline":[131],"that":[132],"leverages":[133],"Stable":[134],"Diffusion":[135],"Segment":[137],"Anything":[138],"Module":[139],"class":[142],"examples":[143],"associated":[146],"mask,":[148],"method":[151],"integrate":[153],"cutouts":[155],"datasets,":[162],"all":[163],"minimal":[165],"user":[166],"input.":[167],"Our":[168],"approach":[169],"aims":[170],"improve":[172],"performance":[174,214,235],"methods":[179],"by":[180],"introducing":[181],"samples":[183],"into":[184],"training":[186],"data":[187],"modifications":[189],"underlying":[192],"algorithms.":[193],"With":[194],"our":[195],"show":[198],"only":[203],"classes,":[210,222,231],"average":[213],"51%":[216],"intersection":[217],"over":[218],"union":[219],"but":[223],"also":[224],"reduce":[225],"errors":[226],"other,":[228],"already":[229],"existing":[230],"reaching":[232],"higher":[234],"level":[236],"overall.":[237]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-10-10T00:00:00"}