{"id":"https://openalex.org/W7131118200","doi":"https://doi.org/10.1109/access.2026.3665511","title":"Multi-Level Online Group Pruning for Deep Semantic Segmentation: Balancing Efficiency and Class Fairness","display_name":"Multi-Level Online Group Pruning for Deep Semantic Segmentation: Balancing Efficiency and Class Fairness","publication_year":2026,"publication_date":"2026-01-01","ids":{"openalex":"https://openalex.org/W7131118200","doi":"https://doi.org/10.1109/access.2026.3665511"},"language":null,"primary_location":{"id":"doi:10.1109/access.2026.3665511","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3665511","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2026.3665511","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101554660","display_name":"Fei Yan","orcid":"https://orcid.org/0000-0001-5177-4493"},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yan Fei","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126607168","display_name":"Yaocheng Zhong","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yaocheng Zhong","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0009-0004-7618-5600","affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126588865","display_name":"Jiayu Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiayu Wang","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126590187","display_name":"Huang Shita","orcid":null},"institutions":[{"id":"https://openalex.org/I4210149256","display_name":"Zhangzhou Vocational and Technical College","ror":"https://ror.org/03myvh511","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210149256"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Huang Shita","raw_affiliation_strings":["Antai Technology Company Ltd., Zhangzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Antai Technology Company Ltd., Zhangzhou, China","institution_ids":["https://openalex.org/I4210149256"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5122892426","display_name":"Xiaodong Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I75867142","display_name":"Xiamen University of Technology","ror":"https://ror.org/01285e189","country_code":"CN","type":"education","lineage":["https://openalex.org/I75867142"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaodong Wang","raw_affiliation_strings":["Xiamen University of Technology, Xiamen, China"],"raw_orcid":"https://orcid.org/0000-0002-9153-1928","affiliations":[{"raw_affiliation_string":"Xiamen University of Technology, Xiamen, China","institution_ids":["https://openalex.org/I75867142"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.23689947,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"14","issue":null,"first_page":"28898","last_page":"28910"},"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":0.17839999496936798,"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":0.17839999496936798,"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.16699999570846558,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/T11273","display_name":"Advanced Graph Neural Networks","score":0.11089999973773956,"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/pruning","display_name":"Pruning","score":0.7580999732017517},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6678000092506409},{"id":"https://openalex.org/keywords/discriminative-model","display_name":"Discriminative model","score":0.5859000086784363},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5533000230789185},{"id":"https://openalex.org/keywords/rendering","display_name":"Rendering (computer graphics)","score":0.4438000023365021},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.42809998989105225},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3953999876976013},{"id":"https://openalex.org/keywords/contextual-image-classification","display_name":"Contextual image classification","score":0.3813999891281128}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7865999937057495},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.7580999732017517},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6678000092506409},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5889000296592712},{"id":"https://openalex.org/C97931131","wikidata":"https://www.wikidata.org/wiki/Q5282087","display_name":"Discriminative model","level":2,"score":0.5859000086784363},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5533000230789185},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45089998841285706},{"id":"https://openalex.org/C205711294","wikidata":"https://www.wikidata.org/wiki/Q176953","display_name":"Rendering (computer graphics)","level":2,"score":0.4438000023365021},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.42809998989105225},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3953999876976013},{"id":"https://openalex.org/C75294576","wikidata":"https://www.wikidata.org/wiki/Q5165192","display_name":"Contextual image classification","level":3,"score":0.3813999891281128},{"id":"https://openalex.org/C174348530","wikidata":"https://www.wikidata.org/wiki/Q188635","display_name":"Bridging (networking)","level":2,"score":0.3792000114917755},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3698999881744385},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.3619999885559082},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.33340001106262207},{"id":"https://openalex.org/C151201525","wikidata":"https://www.wikidata.org/wiki/Q177239","display_name":"Limit (mathematics)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C2984842247","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep neural networks","level":3,"score":0.31130000948905945},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.27799999713897705},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27230000495910645},{"id":"https://openalex.org/C193415008","wikidata":"https://www.wikidata.org/wiki/Q639681","display_name":"Network architecture","level":2,"score":0.27059999108314514},{"id":"https://openalex.org/C774472","wikidata":"https://www.wikidata.org/wiki/Q6760393","display_name":"Margin (machine learning)","level":2,"score":0.2535000145435333}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/access.2026.3665511","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3665511","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.1109/access.2026.3665511","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2026.3665511","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G3288678757","display_name":null,"funder_award_id":"2025J011281","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G3572434684","display_name":null,"funder_award_id":"2023J011428","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G6569092586","display_name":null,"funder_award_id":"3502Z202473071","funder_id":"https://openalex.org/F4320316884","funder_display_name":"Natural Science Foundation of Xiamen City"},{"id":"https://openalex.org/G7390307896","display_name":null,"funder_award_id":"2022J011236","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G8958461235","display_name":null,"funder_award_id":"2022Y0077","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"}],"funders":[{"id":"https://openalex.org/F4320316884","display_name":"Natural Science Foundation of Xiamen City","ror":null},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"This":[0],"study":[1],"targets":[2],"Encoder-Decoder":[3,49,165],"architectures":[4],"acceleration":[5],"for":[6,58,116,173,179,185,201],"semantic":[7],"segmentation.":[8],"Although":[9],"deep":[10],"neural":[11],"networks":[12],"have":[13,44],"shown":[14],"superior":[15,199],"performance":[16,141,200],"in":[17,32,163],"image":[18,151],"segmentation":[19,72,140,152],"tasks,":[20,60],"their":[21,30],"substantial":[22],"model":[23,90],"size":[24],"and":[25,35,110,138,156,183],"high":[26],"computational":[27],"complexity":[28],"limit":[29],"application":[31],"real-time":[33],"processing":[34],"resource-constrained":[36],"devices.":[37],"To":[38,95],"tackle":[39],"this":[40,97],"issue,":[41,98],"pruning":[42,54,105,159,192],"techniques":[43],"been":[45],"developed":[46],"to":[47,64,84,92],"compact":[48],"networks.":[50],"However,":[51],"most":[52,113],"current":[53],"methods":[55,76],"are":[56],"designed":[57],"classification":[59],"rendering":[61],"them":[62],"challenging":[63],"achieve":[65],"satisfactory":[66],"results":[67],"on":[68,148,181,187],"fine-grained":[69],"demands":[70],"of":[71,161],"tasks.":[73],"Additionally,":[74],"these":[75,129],"only":[77],"consider":[78],"the":[79,112,122,174],"filters\u2019":[80],"global":[81],"average":[82],"contribution":[83],"each":[85],"class,":[86],"which":[87],"can":[88,125],"compromise":[89],"sensitivity":[91],"minority":[93,118,175],"classes.":[94,203],"solve":[96],"we":[99],"propose":[100],"a":[101,135],"multi-level":[102],"online":[103,191],"group":[104],"method.":[106],"Our":[107],"method":[108,147,168],"identifies":[109],"preserves":[111],"discriminative":[114],"filters":[115],"critical":[117],"classes,":[119,176],"ensuring":[120],"that":[121],"pruned":[123],"network":[124],"still":[126,195],"accurately":[127],"segment":[128],"underrepresented":[130],"categories.":[131],"Consequently,":[132],"it":[133],"fosters":[134],"more":[136],"balanced":[137],"fair":[139],"across":[142],"all":[143],"classes.We":[144],"evaluated":[145],"our":[146,167],"two":[149],"popular":[150],"datasets,":[153],"i.e.,":[154],"Camvid":[155,182],"Cityscapes.":[157],"After":[158],"93%":[160],"parameters":[162],"trendy":[164],"networks,":[166],"achieves":[169],"noteworthy":[170],"IoU":[171],"gains":[172],"e.g.,":[177],"6.5%":[178],"Pole":[180],"4.7%":[184],"Fence":[186],"Cityscapes,":[188],"over":[189],"state-of-the-art":[190],"methods,":[193],"while":[194],"maintaining":[196],"comparable":[197],"or":[198],"majority":[202]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-24T00:00:00"}