{"id":"https://openalex.org/W7128296970","doi":"https://doi.org/10.1145/3795886","title":"Improving Test-Time Efficiency in Source-Free Semantic Segmentation via Multi-Stage Self-Training","display_name":"Improving Test-Time Efficiency in Source-Free Semantic Segmentation via Multi-Stage Self-Training","publication_year":2026,"publication_date":"2026-02-07","ids":{"openalex":"https://openalex.org/W7128296970","doi":"https://doi.org/10.1145/3795886"},"language":"en","primary_location":{"id":"doi:10.1145/3795886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3795886","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","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/A5082962427","display_name":"Yifang Yin","orcid":"https://orcid.org/0000-0002-6525-6133"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Yifang Yin","raw_affiliation_strings":["Institute for Infocomm Research (IR), A*STAR, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-6525-6133","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (IR), A*STAR, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125339157","display_name":"Jinming Cao","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Jinming Cao","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-8614-7366","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhenguang Liu","orcid":"https://orcid.org/0000-0002-7981-9873"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhenguang Liu","raw_affiliation_strings":["Zhejiang University, Hangzhou, China"],"raw_orcid":"https://orcid.org/0000-0002-7981-9873","affiliations":[{"raw_affiliation_string":"Zhejiang University, Hangzhou, China","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5125335839","display_name":"Guanfeng Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I4210146998","display_name":"MOH Holdings","ror":"https://ror.org/052jm1735","country_code":"SG","type":"healthcare","lineage":["https://openalex.org/I4210146998"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Guanfeng Wang","raw_affiliation_strings":["Grabtaxi Holdings Limited, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-4224-1449","affiliations":[{"raw_affiliation_string":"Grabtaxi Holdings Limited, Singapore, Singapore","institution_ids":["https://openalex.org/I4210146998"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5068002105","display_name":"Shili Xiang","orcid":"https://orcid.org/0000-0001-6598-2904"},"institutions":[{"id":"https://openalex.org/I3005327000","display_name":"Institute for Infocomm Research","ror":"https://ror.org/053rfa017","country_code":"SG","type":"facility","lineage":["https://openalex.org/I115228651","https://openalex.org/I3005327000","https://openalex.org/I91275662"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Shili Xiang","raw_affiliation_strings":["Institute for Infocomm Research (IR), A*STAR, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0001-6598-2904","affiliations":[{"raw_affiliation_string":"Institute for Infocomm Research (IR), A*STAR, Singapore, Singapore","institution_ids":["https://openalex.org/I3005327000"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5125340052","display_name":"Roger Zimmermann","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Roger Zimmermann","raw_affiliation_strings":["National University of Singapore, Singapore, Singapore"],"raw_orcid":"https://orcid.org/0000-0002-7410-2590","affiliations":[{"raw_affiliation_string":"National University of Singapore, Singapore, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"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":0.16918481,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"22","issue":"4","first_page":"1","last_page":"20"},"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":0.9754999876022339,"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":0.9754999876022339,"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":0.00570000009611249,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0031999999191612005,"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/segmentation","display_name":"Segmentation","score":0.8364999890327454},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.5371999740600586},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.47600001096725464},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4287000000476837},{"id":"https://openalex.org/keywords/component","display_name":"Component (thermodynamics)","score":0.4203999936580658},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"Noise reduction","score":0.3878999948501587},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.38589999079704285}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9085000157356262},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8364999890327454},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5720999836921692},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.5371999740600586},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.47600001096725464},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45419999957084656},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4287000000476837},{"id":"https://openalex.org/C168167062","wikidata":"https://www.wikidata.org/wiki/Q1117970","display_name":"Component (thermodynamics)","level":2,"score":0.4203999936580658},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.3878999948501587},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.38589999079704285},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.3847000002861023},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.37779998779296875},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3158999979496002},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.30709999799728394},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.26820001006126404},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.2648000121116638},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.25679999589920044},{"id":"https://openalex.org/C207685749","wikidata":"https://www.wikidata.org/wiki/Q2088941","display_name":"Domain knowledge","level":2,"score":0.25189998745918274}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3795886","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3795886","pdf_url":null,"source":{"id":"https://openalex.org/S19610489","display_name":"ACM Transactions on Multimedia Computing Communications and Applications","issn_l":"1551-6857","issn":["1551-6857","1551-6865"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Multimedia Computing, Communications, and Applications","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/11","display_name":"Sustainable cities and communities","score":0.5618529319763184}],"awards":[],"funders":[{"id":"https://openalex.org/F4320320696","display_name":"Agency for Science, Technology and Research","ror":"https://ror.org/036wvzt09"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":46,"referenced_works":["https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2412782625","https://openalex.org/W2431874326","https://openalex.org/W2487365028","https://openalex.org/W2887964057","https://openalex.org/W2963107255","https://openalex.org/W2963120918","https://openalex.org/W2969893028","https://openalex.org/W2981392058","https://openalex.org/W3021747502","https://openalex.org/W3048630682","https://openalex.org/W3096831136","https://openalex.org/W3102977943","https://openalex.org/W3107502112","https://openalex.org/W3108566666","https://openalex.org/W3164101295","https://openalex.org/W3175042385","https://openalex.org/W3175294391","https://openalex.org/W3175308890","https://openalex.org/W3175682855","https://openalex.org/W3202422321","https://openalex.org/W3205594649","https://openalex.org/W3206487064","https://openalex.org/W3214262346","https://openalex.org/W4293518937","https://openalex.org/W4312243476","https://openalex.org/W4382318762","https://openalex.org/W4384924694","https://openalex.org/W4386075995","https://openalex.org/W4386076503","https://openalex.org/W4387741718","https://openalex.org/W4390872135","https://openalex.org/W4390872291","https://openalex.org/W4390878797","https://openalex.org/W4392191951","https://openalex.org/W4392376875","https://openalex.org/W4400856224","https://openalex.org/W4402716161","https://openalex.org/W4402727160","https://openalex.org/W4402727575","https://openalex.org/W4403791260","https://openalex.org/W4403791750","https://openalex.org/W4408589729","https://openalex.org/W4408722897","https://openalex.org/W4411245000"],"related_works":[],"abstract_inverted_index":{"Source-free":[0],"domain":[1,14,18],"adaptive":[2],"semantic":[3],"segmentation":[4,112,146,176,186],"aims":[5],"at":[6,69],"adapting":[7],"a":[8,30,91],"model":[9,74],"trained":[10],"on":[11,78,189,226],"the":[12,16,23,45,70,141,190,200,209,227],"source":[13,24,167,210],"to":[15,22,33,43,130,171],"target":[17,169],"without":[19,39],"requiring":[20],"access":[21],"data.":[25],"Self-training":[26],"has":[27],"emerged":[28],"as":[29,208],"leading":[31],"approach":[32],"address":[34,60],"this":[35,61,86],"challenging":[36],"problem.":[37],"However,":[38],"robust":[40],"denoising":[41],"mechanisms":[42],"reduce":[44],"noise":[46],"in":[47,185],"pseudo":[48,102],"labels,":[49],"it":[50],"still":[51],"easily":[52],"fall":[53],"into":[54,133],"biased":[55],"estimates.":[56],"Most":[57],"existing":[58,135],"methods":[59],"issue":[62],"by":[63],"introducing":[64],"novel":[65],"architectures,":[66,177],"but":[67],"often":[68],"cost":[71],"of":[72,143,202,220],"increased":[73],"complexity":[75],"or":[76],"reliance":[77],"additional":[79],"input":[80],"modalities.":[81],"Different":[82],"from":[83,182],"previous":[84],"studies,":[85],"article":[87],"introduces":[88],"UniSFDA":[89,162,212],",":[90],"unified":[92],"multi-stage":[93],"self-training":[94,136],"framework":[95,119],"that":[96,161],"integrates":[97],"cross-model":[98],"transfer":[99],"learning,":[100],"uncertainty-aware":[101],"label":[103],"fusion,":[104],"and":[105,114,128,152,168,178,194,223],"intra-domain":[106],"style":[107],"augmentation,":[108],"thereby":[109],"enhancing":[110],"both":[111,166],"accuracy":[113],"test-time":[115],"efficiency.":[116],"Our":[117],"proposed":[118],"offers":[120],"exceptional":[121],"flexibility,":[122],"with":[123,174],"each":[124],"component":[125],"being":[126],"independent":[127],"ready":[129],"be":[131,172],"integrated":[132],"any":[134],"framework.":[137,156,204],"Additionally,":[138],"we":[139],"investigate":[140],"performance":[142],"various":[144],"representative":[145],"models,":[147],"including":[148],"DeepLabv2,":[149],"SegFormer,":[150],"DFormer,":[151],"ViT-Adapter,":[153],"within":[154],"our":[155,203],"It":[157],"is":[158,163],"worth":[159],"noting":[160],"model-agnostic,":[164],"allowing":[165],"networks":[170],"instantiated":[173],"arbitrary":[175],"thus":[179],"readily":[180],"benefiting":[181],"future":[183],"advances":[184],"models.":[187],"Experiments":[188],"GTA5":[191],"\\(\\rightarrow\\)":[192,196],"Cityscapes":[193,197],"SYNTHIA":[195],"benchmarks":[198],"demonstrate":[199],"effectiveness":[201],"With":[205],"DeepLabv2":[206],"(SegFormer)":[207],"model,":[211],"establishes":[213],"new":[214],"state-of-the-art":[215],"performance,":[216],"achieving":[217],"mIoU":[218],"scores":[219],"61.8%":[221],"(65.4%)":[222],"57.9%":[224],"(59.6%)":[225],"two":[228],"benchmarks,":[229],"respectively.":[230]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-08T00:00:00"}