{"id":"https://openalex.org/W4415743508","doi":"https://doi.org/10.1109/tpami.2025.3626757","title":"SED++: A Simple Encoder-Decoder for Improved Open-Vocabulary Semantic Segmentation","display_name":"SED++: A Simple Encoder-Decoder for Improved Open-Vocabulary Semantic Segmentation","publication_year":2025,"publication_date":"2025-10-31","ids":{"openalex":"https://openalex.org/W4415743508","doi":"https://doi.org/10.1109/tpami.2025.3626757","pmid":"https://pubmed.ncbi.nlm.nih.gov/41171658"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2025.3626757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3626757","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","pubmed"],"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/A5100301546","display_name":"Wenqi Zhu","orcid":"https://orcid.org/0009-0008-0357-441X"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wenqi Zhu","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114125058","display_name":"Bin Xie","orcid":"https://orcid.org/0000-0002-3962-5644"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bin Xie","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037129512","display_name":"Jiale Cao","orcid":"https://orcid.org/0000-0002-5160-6841"},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiale Cao","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100733501","display_name":"Jin Xie","orcid":"https://orcid.org/0000-0002-1268-1363"},"institutions":[{"id":"https://openalex.org/I158842170","display_name":"Chongqing University","ror":"https://ror.org/023rhb549","country_code":"CN","type":"education","lineage":["https://openalex.org/I158842170"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jin Xie","raw_affiliation_strings":["School of Big Data and Software Engineering, Chongqing University, Chongqing, China"],"affiliations":[{"raw_affiliation_string":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China","institution_ids":["https://openalex.org/I158842170"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100760570","display_name":"Fahad Shahbaz Khan","orcid":"https://orcid.org/0000-0002-4263-3143"},"institutions":[{"id":"https://openalex.org/I4210113480","display_name":"Mohamed bin Zayed University of Artificial Intelligence","ror":"https://ror.org/0258gkt32","country_code":"AE","type":"education","lineage":["https://openalex.org/I4210113480"]}],"countries":["AE"],"is_corresponding":false,"raw_author_name":"Fahad Shahbaz Khan","raw_affiliation_strings":["Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","Mohamed bin Zayed University of Artificial Intelligence, UAE"],"affiliations":[{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE","institution_ids":["https://openalex.org/I4210113480"]},{"raw_affiliation_string":"Mohamed bin Zayed University of Artificial Intelligence, UAE","institution_ids":["https://openalex.org/I4210113480"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009590084","display_name":"Yanwei Pang","orcid":null},"institutions":[{"id":"https://openalex.org/I162868743","display_name":"Tianjin University","ror":"https://ror.org/012tb2g32","country_code":"CN","type":"education","lineage":["https://openalex.org/I162868743"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanwei Pang","raw_affiliation_strings":["School of Electrical and Information Engineering, Tianjin University, Tianjin, China"],"affiliations":[{"raw_affiliation_string":"School of Electrical and Information Engineering, Tianjin University, Tianjin, China","institution_ids":["https://openalex.org/I162868743"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5100301546"],"corresponding_institution_ids":["https://openalex.org/I162868743"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.32264517,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"3","first_page":"2528","last_page":"2543"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6549000144004822,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.6549000144004822,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.14890000224113464,"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":0.029400000348687172,"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":0.6338000297546387},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.6098999977111816},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.588100016117096},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5623999834060669},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.5314000248908997},{"id":"https://openalex.org/keywords/embedding","display_name":"Embedding","score":0.4828999936580658},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.43619999289512634},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.39879998564720154}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7569000124931335},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7081999778747559},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6338000297546387},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.6098999977111816},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.588100016117096},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5623999834060669},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5314000248908997},{"id":"https://openalex.org/C41608201","wikidata":"https://www.wikidata.org/wiki/Q980509","display_name":"Embedding","level":2,"score":0.4828999936580658},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.43619999289512634},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.39879998564720154},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.3903000056743622},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.38929998874664307},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.37689998745918274},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.35569998621940613},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.2842000126838684},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.2718999981880188},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.26739999651908875},{"id":"https://openalex.org/C173414695","wikidata":"https://www.wikidata.org/wiki/Q5510276","display_name":"Fusion mechanism","level":4,"score":0.25609999895095825},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.25029999017715454}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2025.3626757","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2025.3626757","pdf_url":null,"source":{"id":"https://openalex.org/S199944782","display_name":"IEEE Transactions on Pattern Analysis and Machine Intelligence","issn_l":"0162-8828","issn":["0162-8828","1939-3539","2160-9292"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320439","host_organization_name":"IEEE Computer Society","host_organization_lineage":["https://openalex.org/P4310320439","https://openalex.org/P4310319808"],"host_organization_lineage_names":["IEEE Computer Society","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 Transactions on Pattern Analysis and Machine Intelligence","raw_type":"journal-article"},{"id":"pmid:41171658","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41171658","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":"IEEE transactions on pattern analysis and machine intelligence","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2031489346","https://openalex.org/W2125215748","https://openalex.org/W2250384498","https://openalex.org/W2412782625","https://openalex.org/W2507296351","https://openalex.org/W2561196672","https://openalex.org/W2565639579","https://openalex.org/W2598666589","https://openalex.org/W2604254608","https://openalex.org/W2799213142","https://openalex.org/W2886641317","https://openalex.org/W2894299524","https://openalex.org/W2924485953","https://openalex.org/W2955058313","https://openalex.org/W2963728677","https://openalex.org/W2963881378","https://openalex.org/W2970231061","https://openalex.org/W2981689412","https://openalex.org/W2999219213","https://openalex.org/W3090449556","https://openalex.org/W3094502228","https://openalex.org/W3095670406","https://openalex.org/W3122412340","https://openalex.org/W3169367294","https://openalex.org/W3170841864","https://openalex.org/W4214893857","https://openalex.org/W4312443924","https://openalex.org/W4312458986","https://openalex.org/W4312726009","https://openalex.org/W4312815172","https://openalex.org/W4312912313","https://openalex.org/W4312935996","https://openalex.org/W4312956471","https://openalex.org/W4312960937","https://openalex.org/W4312980231","https://openalex.org/W4386065512","https://openalex.org/W4386065874","https://openalex.org/W4386075561","https://openalex.org/W4386075588","https://openalex.org/W4386075819","https://openalex.org/W4386076046","https://openalex.org/W4386076397","https://openalex.org/W4386415485","https://openalex.org/W4390871743","https://openalex.org/W4390872930","https://openalex.org/W4390874070","https://openalex.org/W4390874575","https://openalex.org/W4394677290","https://openalex.org/W4401070841","https://openalex.org/W4402703011","https://openalex.org/W4402715795","https://openalex.org/W4402716400","https://openalex.org/W4402754004","https://openalex.org/W4402773761","https://openalex.org/W4402961794","https://openalex.org/W4403726492","https://openalex.org/W4403759200","https://openalex.org/W4404544982","https://openalex.org/W4404612913","https://openalex.org/W4408609670","https://openalex.org/W4409129306","https://openalex.org/W4413145015","https://openalex.org/W4413145574","https://openalex.org/W4413145825","https://openalex.org/W4413157437","https://openalex.org/W4415797178","https://openalex.org/W4416310693"],"related_works":[],"abstract_inverted_index":{"Open-vocabulary":[0],"semantic":[1,10,47,190],"segmentation":[2,48,91,247],"aims":[3],"to":[4,28,89,95,114,125,146],"partition":[5],"an":[6,14,211,225,240],"image":[7,58,70,104,232],"into":[8],"distinct":[9],"regions":[11],"based":[12],"on":[13,23,159,194,215,233,245],"open":[15],"set":[16],"of":[17,55,202,213,228,243],"categories.":[18],"Existing":[19],"approaches":[20],"primarily":[21],"rely":[22],"image-level":[24],"pre-trained":[25,50],"vision-language":[26,51],"models":[27],"perform":[29],"this":[30,34],"pixel-level":[31],"task.":[32],"In":[33,93],"paper,":[35],"we":[36,161,179],"propose":[37],"SED,":[38,160],"a":[39,56,60,64,77,96,122,135,234],"simple":[40],"yet":[41],"effective":[42],"encoder-decoder":[43],"architecture":[44],"for":[45,187],"open-vocabulary":[46,188],"leveraging":[49],"models.":[52],"SED":[53],"consists":[54],"hierarchical":[57,69,100],"encoder,":[59,62,98],"text":[61,73,168],"and":[63,72,170,200,238],"gradual":[65,86,118,143],"fusion":[66,87,119,144],"decoder.":[67],"The":[68,117],"encoder":[71,74,101],"collaboratively":[75],"generate":[76],"cost":[78,132],"volume,":[79],"which":[80],"is":[81,140],"progressively":[82,126],"decoded":[83],"by":[84],"the":[85,99,131,176,198,216],"decoder":[88,120,145,185],"produce":[90],"results.":[92],"contrast":[94],"plain":[97],"better":[102],"captures":[103],"detail":[105],"information":[106],"while":[107],"maintaining":[108],"linear":[109],"computational":[110],"complexity":[111],"with":[112,130,183,219],"respect":[113],"input":[115],"size.":[116],"adopts":[121],"top-down":[123],"structure":[124],"integrate":[127],"high-resolution":[128],"features":[129],"volume.":[133],"Furthermore,":[134],"category":[136,172],"early":[137,173],"rejection":[138,174],"strategy":[139],"introduced":[141],"in":[142,175],"filter":[147],"out":[148],"non-existent":[149],"categories":[150],"at":[151,224],"different":[152],"layers,":[153],"significantly":[154],"improving":[155],"inference":[156,226],"efficiency.":[157],"Based":[158],"further":[162],"introduce":[163],"two":[164],"modules,":[165],"including":[166],"non-label":[167],"embedding":[169],"additional":[171],"encoder.":[177],"Moreover,":[178],"extend":[180],"our":[181,203,208],"method":[182,209],"minimal":[184],"modification":[186],"video":[189,246],"segmentation.":[191],"Extensive":[192],"experiments":[193],"multiple":[195],"datasets":[196],"validate":[197],"effectiveness":[199],"efficiency":[201],"proposed":[204],"method.":[205],"With":[206],"ConvNeXt-B,":[207],"achieves":[210],"mIoU":[212,241],"34.9%":[214],"ADE20":[217],"K":[218],"150":[220],"classes":[221],"(i.e.,":[222],"A-150)":[223],"speed":[227],"69":[229],"ms":[230],"per":[231],"single":[235],"A6000":[236],"GPU,":[237],"has":[239],"score":[242],"40.2%":[244],"dataset":[248],"VSPW.":[249]},"counts_by_year":[],"updated_date":"2026-03-27T05:58:40.876381","created_date":"2025-10-31T00:00:00"}