{"id":"https://openalex.org/W7136848154","doi":"https://doi.org/10.1109/tpami.2026.3674640","title":"Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing","display_name":"Benchmarking Semantic Segmentation Models via Appearance and Geometry Attribute Editing","publication_year":2026,"publication_date":"2026-03-16","ids":{"openalex":"https://openalex.org/W7136848154","doi":"https://doi.org/10.1109/tpami.2026.3674640","pmid":"https://pubmed.ncbi.nlm.nih.gov/41838508"},"language":"en","primary_location":{"id":"doi:10.1109/tpami.2026.3674640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3674640","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/A5129465896","display_name":"Zijin Yin","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zijin Yin","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-8769-9533","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129423671","display_name":"Bing Li","orcid":null},"institutions":[{"id":"https://openalex.org/I185163786","display_name":"King Abdulaziz University","ror":"https://ror.org/02ma4wv74","country_code":"SA","type":"education","lineage":["https://openalex.org/I185163786"]},{"id":"https://openalex.org/I71920554","display_name":"King Abdullah University of Science and Technology","ror":"https://ror.org/01q3tbs38","country_code":"SA","type":"education","lineage":["https://openalex.org/I71920554"]}],"countries":["SA"],"is_corresponding":false,"raw_author_name":"Bing Li","raw_affiliation_strings":["Visual Computing Center, King Abdullah University of Science and Technology, Jeddah, Saudi Arabia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Visual Computing Center, King Abdullah University of Science and Technology, Jeddah, Saudi Arabia","institution_ids":["https://openalex.org/I185163786","https://openalex.org/I71920554"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077313814","display_name":"Kongming Liang","orcid":"https://orcid.org/0000-0002-4726-093X"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kongming Liang","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0002-4726-093X","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100700666","display_name":"Han Sun","orcid":"https://orcid.org/0009-0002-8186-2376"},"institutions":[{"id":"https://openalex.org/I4210100255","display_name":"Beijing Academy of Artificial Intelligence","ror":"https://ror.org/016a74861","country_code":"CN","type":"other","lineage":["https://openalex.org/I4210100255"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Hao Sun","raw_affiliation_strings":["China Telecom Artificial Intelligence Technology Company Ltd, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"China Telecom Artificial Intelligence Technology Company Ltd, Beijing, China","institution_ids":["https://openalex.org/I4210100255"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5129456727","display_name":"Zhongjiang He","orcid":null},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhongjiang He","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Zhanyu Ma","orcid":"https://orcid.org/0000-0003-2950-2488"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhanyu Ma","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0003-2950-2488","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]},{"author_position":"last","author":{"id":null,"display_name":"Jun Guo","orcid":"https://orcid.org/0000-0001-9045-1339"},"institutions":[{"id":"https://openalex.org/I139759216","display_name":"Beijing University of Posts and Telecommunications","ror":"https://ror.org/04w9fbh59","country_code":"CN","type":"education","lineage":["https://openalex.org/I139759216"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jun Guo","raw_affiliation_strings":["School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China"],"raw_orcid":"https://orcid.org/0000-0001-9045-1339","affiliations":[{"raw_affiliation_string":"School of Artificial Intelligence, Beijing Key Laboratory of Multimodal Data Intelligent Perception and Governance, Beijing University of Posts and Telecommunications, Beijing, China","institution_ids":["https://openalex.org/I139759216"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"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":0.32430483,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"48","issue":"7","first_page":"8661","last_page":"8677"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11448","display_name":"Face recognition and analysis","score":0.5145000219345093,"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/T11448","display_name":"Face recognition and analysis","score":0.5145000219345093,"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/T10719","display_name":"3D Shape Modeling and Analysis","score":0.1467999964952469,"subfield":{"id":"https://openalex.org/subfields/2206","display_name":"Computational Mechanics"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.03889999911189079,"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/segmentation","display_name":"Segmentation","score":0.6108999848365784},{"id":"https://openalex.org/keywords/benchmarking","display_name":"Benchmarking","score":0.5455999970436096},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5329999923706055},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43779999017715454},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.40549999475479126},{"id":"https://openalex.org/keywords/semantics","display_name":"Semantics (computer science)","score":0.35260000824928284},{"id":"https://openalex.org/keywords/visualization","display_name":"Visualization","score":0.3287000060081482}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6888999938964844},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6802999973297119},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6108999848365784},{"id":"https://openalex.org/C86251818","wikidata":"https://www.wikidata.org/wiki/Q816754","display_name":"Benchmarking","level":2,"score":0.5455999970436096},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5432999730110168},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5329999923706055},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43779999017715454},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.40549999475479126},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.35260000824928284},{"id":"https://openalex.org/C36464697","wikidata":"https://www.wikidata.org/wiki/Q451553","display_name":"Visualization","level":2,"score":0.3287000060081482},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.3093999922275543},{"id":"https://openalex.org/C29123130","wikidata":"https://www.wikidata.org/wiki/Q874709","display_name":"Computational geometry","level":2,"score":0.29429998993873596},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.2924000024795532},{"id":"https://openalex.org/C9417928","wikidata":"https://www.wikidata.org/wiki/Q1070689","display_name":"Image processing","level":3,"score":0.28949999809265137},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.27810001373291016},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.2732999920845032},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.25769999623298645},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.25429999828338623}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/tpami.2026.3674640","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tpami.2026.3674640","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:41838508","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/41838508","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":[{"id":"https://openalex.org/G172479822","display_name":null,"funder_award_id":"62225601","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5612663533","display_name":null,"funder_award_id":"62476029","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7101706402","display_name":null,"funder_award_id":"L242025","funder_id":"https://openalex.org/F4320322919","funder_display_name":"Natural Science Foundation of Beijing Municipality"},{"id":"https://openalex.org/G8677236040","display_name":null,"funder_award_id":"U23B2052","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320322919","display_name":"Natural Science Foundation of Beijing Municipality","ror":null},{"id":"https://openalex.org/F4320334978","display_name":"Beijing Nova Program","ror":"https://ror.org/034k14f91"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Semantic":[0],"segmentation":[1,19,51,135,171,256,274],"takes":[2],"a":[3,166,231],"pivotal":[4],"role":[5],"in":[6,21,30,35,77,216,268],"various":[7,55],"applications":[8],"such":[9,102,209],"as":[10,97,99,103,210,230,250],"autonomous":[11],"driving":[12],"and":[13,32,71,80,86,95,105,162,212,235,239,258,266,272],"medical":[14],"image":[15,87],"analysis.":[16],"When":[17],"deploying":[18],"models":[20,52,177,191,249],"practice,":[22],"it":[23],"is":[24],"critical":[25],"to":[26,48,112,178,198],"test":[27],"their":[28],"behaviors":[29],"varied":[31],"complex":[33],"scenes":[34],"advance.":[36],"In":[37,130],"this":[38,131],"paper,":[39],"we":[40,74,110,156,259],"construct":[41,157],"an":[42],"automatic":[43],"data":[44,206,232],"generation":[45,224],"pipeline":[46,225],"Gen4Seg":[47],"stress-test":[49],"semantic":[50,170],"by":[53,127],"generating":[54],"challenging":[56],"samples":[57],"with":[58,120],"different":[59],"attribute":[60],"changes.":[61],"Beyond":[62],"previous":[63],"evaluation":[64],"paradigms":[65],"focusing":[66],"solely":[67],"on":[68],"global":[69],"weather":[70,104],"style":[72],"transfer,":[73],"investigate":[75],"variations":[76,101],"both":[78,237],"appearance":[79,220],"geometry":[81],"attributes":[82,115],"at":[83],"the":[84,133,141,147,245],"object":[85,91],"level.":[88],"These":[89],"include":[90],"color,":[92],"material,":[93],"size,":[94],"position,":[96],"well":[98],"image-level":[100],"style.":[106],"To":[107],"achieve":[108],"this,":[109],"propose":[111],"edit":[113],"visual":[114],"of":[116,123,150,169,247],"existing":[117,134],"real":[118],"images":[119],"precise":[121],"control":[122],"structural":[124],"information,":[125],"empowered":[126],"diffusion":[128],"models.":[129,182,275],"way,":[132],"labels":[136],"can":[137,226],"be":[138,228],"reused":[139],"for":[140,253],"edited":[142],"images,":[143],"which":[144],"greatly":[145],"reduces":[146],"labor":[148],"costs":[149],"constructing":[151],"datasets.":[152],"Using":[153],"our":[154,223,261],"pipeline,":[155],"two":[158],"new":[159],"benchmarks,":[160],"Pascal-EA":[161],"COCO-EA.":[163],"We":[164,183],"benchmark":[165],"broad":[167],"variety":[168],"models,":[172,257],"spanning":[173],"from":[174],"conventional":[175],"close-set":[176],"recent":[179],"open-vocabulary":[180,190],"large":[181],"have":[184],"several":[185],"key":[186],"findings:":[187],"1)":[188],"advanced":[189],"do":[192],"not":[193],"exhibit":[194],"greater":[195],"robustness":[196,218],"compared":[197],"closed-set":[199],"methods":[200],"under":[201],"geometric":[202],"variations;":[203,221],"2)":[204],"traditional":[205],"augmentation":[207,233],"techniques,":[208],"CutOut":[211],"CutMix,":[213],"are":[214],"limited":[215],"enhancing":[217],"against":[219],"3)":[222],"also":[227],"employed":[229],"tool":[234],"improve":[236],"in-distribution":[238],"out-of-distribution":[240],"performances.":[241],"Our":[242],"work":[243],"suggests":[244],"potential":[246],"generative":[248],"effective":[251],"tools":[252],"automatically":[254],"analyzing":[255],"hope":[260],"findings":[262],"will":[263],"assist":[264],"practitioners":[265],"researchers":[267],"developing":[269],"more":[270],"robust":[271],"reliable":[273]},"counts_by_year":[],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2026-03-17T00:00:00"}