{"id":"https://openalex.org/W4409640704","doi":"https://doi.org/10.1109/lsp.2025.3562821","title":"Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation","display_name":"Exploring Token-Level Augmentation in Vision Transformer for Semi-Supervised Semantic Segmentation","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409640704","doi":"https://doi.org/10.1109/lsp.2025.3562821"},"language":"en","primary_location":{"id":"doi:10.1109/lsp.2025.3562821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3562821","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"},"type":"article","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/A5030715932","display_name":"D H Zhang","orcid":"https://orcid.org/0009-0001-2941-0084"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Dengke Zhang","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033579560","display_name":"Quan Tang","orcid":"https://orcid.org/0000-0003-4011-6166"},"institutions":[{"id":"https://openalex.org/I4210136793","display_name":"Peng Cheng Laboratory","ror":"https://ror.org/03qdqbt06","country_code":"CN","type":"facility","lineage":["https://openalex.org/I4210136793"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Quan Tang","raw_affiliation_strings":["Department of New Network, Pengcheng Laboratory, Shenzhen, China"],"affiliations":[{"raw_affiliation_string":"Department of New Network, Pengcheng Laboratory, Shenzhen, China","institution_ids":["https://openalex.org/I4210136793"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5005463262","display_name":"Fagui Liu","orcid":"https://orcid.org/0000-0003-1135-4982"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Fagui Liu","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5104111457","display_name":"Haiqing Mei","orcid":null},"institutions":[{"id":"https://openalex.org/I2800556661","display_name":"China Tobacco","ror":"https://ror.org/030d08e08","country_code":"CN","type":"government","lineage":["https://openalex.org/I2800556661"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haiqing Mei","raw_affiliation_strings":["China Tobacco Guangdong Industrial Corporation, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"China Tobacco Guangdong Industrial Corporation, Guangzhou, China","institution_ids":["https://openalex.org/I2800556661"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100643265","display_name":"C. L. Philip Chen","orcid":"https://orcid.org/0000-0001-5451-7230"},"institutions":[{"id":"https://openalex.org/I90610280","display_name":"South China University of Technology","ror":"https://ror.org/0530pts50","country_code":"CN","type":"education","lineage":["https://openalex.org/I90610280"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"C. L. Philip Chen","raw_affiliation_strings":["School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"],"affiliations":[{"raw_affiliation_string":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China","institution_ids":["https://openalex.org/I90610280"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5030715932"],"corresponding_institution_ids":["https://openalex.org/I90610280"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.12929869,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":null,"first_page":"1885","last_page":"1889"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9485999941825867,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9485999941825867,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9340999722480774,"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":0.7183048129081726},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6138800978660583},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5980572700500488},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.57120281457901},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5434092283248901},{"id":"https://openalex.org/keywords/security-token","display_name":"Security token","score":0.5155684947967529},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.4747493863105774},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.37948280572891235},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.3337589204311371},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11705002188682556},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.08787888288497925}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183048129081726},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6138800978660583},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5980572700500488},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.57120281457901},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5434092283248901},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.5155684947967529},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.4747493863105774},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.37948280572891235},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.3337589204311371},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11705002188682556},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.08787888288497925},{"id":"https://openalex.org/C119599485","wikidata":"https://www.wikidata.org/wiki/Q43035","display_name":"Electrical engineering","level":1,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/lsp.2025.3562821","is_oa":false,"landing_page_url":"https://doi.org/10.1109/lsp.2025.3562821","pdf_url":null,"source":{"id":"https://openalex.org/S120629676","display_name":"IEEE Signal Processing Letters","issn_l":"1070-9908","issn":["1070-9908","1558-2361"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Signal Processing Letters","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1903029394","https://openalex.org/W2037227137","https://openalex.org/W2144794286","https://openalex.org/W2340897893","https://openalex.org/W2787091153","https://openalex.org/W2991453722","https://openalex.org/W2992308087","https://openalex.org/W3094502228","https://openalex.org/W3096609285","https://openalex.org/W3120562181","https://openalex.org/W3138516171","https://openalex.org/W3151130473","https://openalex.org/W3204140421","https://openalex.org/W4214893857","https://openalex.org/W4214899942","https://openalex.org/W4312310512","https://openalex.org/W4312922277","https://openalex.org/W4313118352","https://openalex.org/W4386065584","https://openalex.org/W4386071949","https://openalex.org/W4386075981","https://openalex.org/W4389403397","https://openalex.org/W4390873032","https://openalex.org/W4402716414","https://openalex.org/W4402727005","https://openalex.org/W4402727392","https://openalex.org/W4402753905","https://openalex.org/W4407097610","https://openalex.org/W6684191040","https://openalex.org/W6733814495","https://openalex.org/W6797399245","https://openalex.org/W6857979729","https://openalex.org/W6869023556"],"related_works":["https://openalex.org/W4388335561","https://openalex.org/W2970530566","https://openalex.org/W4288261899","https://openalex.org/W4307309205","https://openalex.org/W2967478618","https://openalex.org/W4385009901","https://openalex.org/W4385572700","https://openalex.org/W2997152889","https://openalex.org/W4304700937","https://openalex.org/W1522196789"],"abstract_inverted_index":{"Semi-supervised":[0],"semantic":[1,47],"segmentation":[2,48],"has":[3],"witnessed":[4],"remarkable":[5],"advancements":[6],"in":[7],"recent":[8],"years.":[9],"However,":[10],"existing":[11],"algorithms":[12,142],"are":[13],"based":[14],"on":[15],"convolutional":[16],"neural":[17],"networks,":[18],"and":[19,77,88,112,132],"directly":[20],"applying":[21],"them":[22],"to":[23,30,91,98,115],"Vision":[24,50],"Transformers":[25],"poses":[26],"certain":[27],"limitations":[28],"due":[29],"conceptual":[31],"disparities.":[32],"To":[33],"this":[34],"end,":[35],"we":[36,102],"propose":[37,103],"TokenSwap,":[38],"a":[39,104],"data":[40],"augmentation":[41,87,90,114],"technique":[42],"designed":[43],"explicitly":[44],"for":[45,71],"semi-supervised":[46],"with":[49,55,143],"Transformers.":[51],"TokenSwap":[52],"aligns":[53],"well":[54],"the":[56,64,68,78,93,116,137],"global":[57],"attention":[58],"mechanism":[59],"by":[60],"mixing":[61],"images":[62],"at":[63],"token":[65],"level,":[66],"enhancing":[67],"learning":[69],"capability":[70],"contextual":[72],"information":[73],"among":[74],"image":[75,86,111],"patches":[76],"utilization":[79],"of":[80,95],"unlabeled":[81],"data.":[82],"We":[83,119],"further":[84],"incorporate":[85],"feature":[89,113],"promote":[92],"diversity":[94],"augmentation.":[96],"Moreover,":[97],"enhance":[99],"consistency":[100],"regularization,":[101],"dual-branch":[105],"framework":[106],"where":[107],"each":[108],"branch":[109],"applies":[110],"input":[117],"image.":[118],"conduct":[120],"extensive":[121],"experiments":[122],"across":[123],"multiple":[124],"benchmark":[125],"datasets,":[126],"including":[127],"Pascal":[128],"VOC":[129],"2012,":[130],"Cityscapes,":[131],"COCO.":[133],"Results":[134],"suggest":[135],"that":[136],"proposed":[138],"method":[139],"outperforms":[140],"state-of-the-art":[141],"notably":[144],"observed":[145],"accuracy":[146],"improvement,":[147],"especially":[148],"under":[149],"limited":[150],"fine":[151],"annotations.":[152]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}