{"id":"https://openalex.org/W7125954627","doi":"https://doi.org/10.1109/smc58881.2025.11342798","title":"Multi-Scale Token Pruning in Mask2Former for Semantic Segmentation","display_name":"Multi-Scale Token Pruning in Mask2Former for Semantic Segmentation","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125954627","doi":"https://doi.org/10.1109/smc58881.2025.11342798"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11342798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-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/A5053005436","display_name":"Ryuto Ishibashi","orcid":"https://orcid.org/0009-0000-3161-2200"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Ryuto Ishibashi","raw_affiliation_strings":["Ritsumeikan University,Graduate School of Science and Engineering,Japan,525-8577"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Graduate School of Science and Engineering,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057095798","display_name":"Lin Meng","orcid":"https://orcid.org/0000-0001-9787-9936"},"institutions":[{"id":"https://openalex.org/I135768898","display_name":"Ritsumeikan University","ror":"https://ror.org/0197nmd03","country_code":"JP","type":"education","lineage":["https://openalex.org/I135768898","https://openalex.org/I4390039241"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Lin Meng","raw_affiliation_strings":["Ritsumeikan University,Graduate School of Science and Engineering,Japan,525-8577"],"affiliations":[{"raw_affiliation_string":"Ritsumeikan University,Graduate School of Science and Engineering,Japan,525-8577","institution_ids":["https://openalex.org/I135768898"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5085355268","display_name":"Mingcong Deng","orcid":"https://orcid.org/0000-0001-7411-6602"},"institutions":[{"id":"https://openalex.org/I92614990","display_name":"Tokyo University of Agriculture and Technology","ror":"https://ror.org/00qg0kr10","country_code":"JP","type":"education","lineage":["https://openalex.org/I92614990"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Mingcong Deng","raw_affiliation_strings":["Tokyo University of Agriculture and Technology,Department of Electrical and Electronic Engineering,Tokyo,Japan,184-8588"],"affiliations":[{"raw_affiliation_string":"Tokyo University of Agriculture and Technology,Department of Electrical and Electronic Engineering,Tokyo,Japan,184-8588","institution_ids":["https://openalex.org/I92614990"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053005436"],"corresponding_institution_ids":["https://openalex.org/I135768898"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.71936431,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3833","last_page":"3838"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.7264999747276306,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.7264999747276306,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.11230000108480453,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05180000141263008,"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/security-token","display_name":"Security token","score":0.6930000185966492},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6201000213623047},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.5145999789237976},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.49380001425743103},{"id":"https://openalex.org/keywords/computational-complexity-theory","display_name":"Computational complexity theory","score":0.4788999855518341},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.46799999475479126},{"id":"https://openalex.org/keywords/pairwise-comparison","display_name":"Pairwise comparison","score":0.3691999912261963},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.36169999837875366}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7688999772071838},{"id":"https://openalex.org/C48145219","wikidata":"https://www.wikidata.org/wiki/Q1335365","display_name":"Security token","level":2,"score":0.6930000185966492},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6358000040054321},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6201000213623047},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.49380001425743103},{"id":"https://openalex.org/C179799912","wikidata":"https://www.wikidata.org/wiki/Q205084","display_name":"Computational complexity theory","level":2,"score":0.4788999855518341},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.46799999475479126},{"id":"https://openalex.org/C184898388","wikidata":"https://www.wikidata.org/wiki/Q1435712","display_name":"Pairwise comparison","level":2,"score":0.3691999912261963},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.36169999837875366},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.33869999647140503},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3244999945163727},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32100000977516174},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.3156999945640564},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31139999628067017},{"id":"https://openalex.org/C152124472","wikidata":"https://www.wikidata.org/wiki/Q1204361","display_name":"Redundancy (engineering)","level":2,"score":0.30959999561309814},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C2780186347","wikidata":"https://www.wikidata.org/wiki/Q11414","display_name":"Subnetwork","level":2,"score":0.29440000653266907},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.289000004529953},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.2678000032901764}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11342798","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11342798","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W2194775991","https://openalex.org/W2340897893","https://openalex.org/W2737258237","https://openalex.org/W2781228439","https://openalex.org/W2884822772","https://openalex.org/W3138516171","https://openalex.org/W3170841864","https://openalex.org/W3211490618","https://openalex.org/W4214588794","https://openalex.org/W4214893857","https://openalex.org/W4312815172","https://openalex.org/W4385245566","https://openalex.org/W4386066311","https://openalex.org/W4386076222","https://openalex.org/W4403919210","https://openalex.org/W4406505715"],"related_works":[],"abstract_inverted_index":{"Although":[0],"Transformer":[1],"has":[2],"been":[3],"successfully":[4],"applied":[5],"to":[6,20,28,38,44,113],"Vision":[7],"tasks":[8,148],"in":[9,145],"various":[10,74],"fields,":[11],"its":[12],"large":[13,115,151],"computational":[14,46,123],"cost":[15,47],"and":[16,48,68,116,133],"performance":[17],"degradation":[18],"due":[19],"divergence":[21],"from":[22],"the":[23,62,88,98,114,122],"language":[24],"task":[25],"are":[26,140],"issues":[27],"be":[29,70],"addressed.":[30],"In":[31,125],"this":[32,106],"paper,":[33],"we":[34],"introduce":[35],"token":[36,76],"pruning":[37,77],"Mask2Former,":[39],"a":[40,150],"state-of-the-art":[41],"segmentation":[42],"method,":[43],"reduce":[45],"improve":[49],"recognition":[50],"accuracy":[51],"without":[52],"additional":[53],"training.":[54],"Multi-Scale":[55],"Token":[56],"Pruning":[57],"(MSTP)":[58],"works":[59],"effectively":[60],"on":[61,97],"multi-scale":[63],"feature":[64],"tokens":[65],"of":[66,90,121,153],"Mask2Former":[67,89],"can":[69,109],"universally":[71],"implemented":[72],"with":[73,101,119,149],"conventional":[75],"methods.":[78],"Experimental":[79],"results":[80],"show":[81],"that":[82],"introducing":[83],"Top-K":[84],"(norm+rand)":[85],"MSTP":[86],"into":[87],"Swin-L":[91],"backbone":[92],"achieves":[93],"+0.28":[94],"(56.31)":[95],"mIoU":[96,111,136],"ADE20K":[99],"benchmark":[100],"+5.7%":[102],"speed":[103],"up.":[104],"With":[105],"improvement,":[107],"Mask2Former+MSTP":[108],"achieve":[110],"equivalent":[112],"powerful":[117],"BEiT-UperNet":[118],"1/4":[120],"complexity.":[124],"addition,":[126],"+0.04":[127],"(57.86)":[128],"PQ":[129],"for":[130,137],"COCO":[131],"panoptic":[132],"+0.19":[134],"(63.36)":[135],"Mapillary":[138],"Vistas":[139],"achieved,":[141],"showing":[142],"particular":[143],"usefulness":[144],"complex":[146],"semantic":[147],"number":[152],"categories.":[154]},"counts_by_year":[],"updated_date":"2026-01-29T23:17:01.242718","created_date":"2026-01-29T00:00:00"}