{"id":"https://openalex.org/W4408352759","doi":"https://doi.org/10.1109/icassp49660.2025.10889270","title":"U-SAM: Upgrade Segment Anything Model With Semantic-Aware and Memory-Efficient","display_name":"U-SAM: Upgrade Segment Anything Model With Semantic-Aware and Memory-Efficient","publication_year":2025,"publication_date":"2025-03-12","ids":{"openalex":"https://openalex.org/W4408352759","doi":"https://doi.org/10.1109/icassp49660.2025.10889270"},"language":"en","primary_location":{"id":"doi:10.1109/icassp49660.2025.10889270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5101468648","display_name":"Xiaofeng Jin","orcid":"https://orcid.org/0000-0003-3140-9389"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaofeng Jin","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101506745","display_name":"Jie Hu","orcid":"https://orcid.org/0000-0001-5311-5803"},"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":"Jie Hu","raw_affiliation_strings":["National University of Singapore,Learning and Vision Lab,Singapore"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National University of Singapore,Learning and Vision Lab,Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5069323421","display_name":"Jianghang Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianghang Lin","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5033991031","display_name":"Shengchuan Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengchuan Zhang","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014628588","display_name":"Liujuan Cao","orcid":"https://orcid.org/0000-0002-7645-9606"},"institutions":[{"id":"https://openalex.org/I191208505","display_name":"Xiamen University","ror":"https://ror.org/00mcjh785","country_code":"CN","type":"education","lineage":["https://openalex.org/I191208505"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liujuan Cao","raw_affiliation_strings":["Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China,P.R. China,361005","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"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":0.0354357,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12127","display_name":"Software System Performance and Reliability","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12127","display_name":"Software System Performance and Reliability","score":0.9951000213623047,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T14470","display_name":"Advanced Data Processing Techniques","score":0.9866999983787537,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"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/T10679","display_name":"Service-Oriented Architecture and Web Services","score":0.9821000099182129,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/computer-science","display_name":"Computer science","score":0.7791835069656372},{"id":"https://openalex.org/keywords/upgrade","display_name":"Upgrade","score":0.6530510187149048},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.42150765657424927},{"id":"https://openalex.org/keywords/computer-architecture","display_name":"Computer architecture","score":0.4185091555118561},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41069602966308594},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.29986509680747986}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7791835069656372},{"id":"https://openalex.org/C2780615140","wikidata":"https://www.wikidata.org/wiki/Q920419","display_name":"Upgrade","level":2,"score":0.6530510187149048},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.42150765657424927},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.4185091555118561},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41069602966308594},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.29986509680747986}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icassp49660.2025.10889270","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp49660.2025.10889270","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320321878","display_name":"Natural Science Foundation of Fujian Province","ror":null},{"id":"https://openalex.org/F4320329860","display_name":"National Science and Technology Major Project","ror":null},{"id":"https://openalex.org/F4320336125","display_name":"National Science Fund for Distinguished Young Scholars","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":33,"referenced_works":["https://openalex.org/W845365781","https://openalex.org/W1861492603","https://openalex.org/W2110158442","https://openalex.org/W2340897893","https://openalex.org/W2531409750","https://openalex.org/W2948672349","https://openalex.org/W2962850830","https://openalex.org/W3035564946","https://openalex.org/W4312578992","https://openalex.org/W4312710812","https://openalex.org/W4312815172","https://openalex.org/W4313030842","https://openalex.org/W4385481295","https://openalex.org/W4386075633","https://openalex.org/W4390190100","https://openalex.org/W4390874575","https://openalex.org/W4391021462","https://openalex.org/W4393148942","https://openalex.org/W4394758452","https://openalex.org/W4402915908","https://openalex.org/W4403791674","https://openalex.org/W4404612589","https://openalex.org/W4404722477","https://openalex.org/W4409366851","https://openalex.org/W6757817989","https://openalex.org/W6800217721","https://openalex.org/W6851607685","https://openalex.org/W6852040150","https://openalex.org/W6853219587","https://openalex.org/W6854362512","https://openalex.org/W6858986087","https://openalex.org/W6859134941","https://openalex.org/W6861232000"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2368672678","https://openalex.org/W2370626080","https://openalex.org/W2965111880","https://openalex.org/W2368576029","https://openalex.org/W2377210208","https://openalex.org/W116478885","https://openalex.org/W2391279445"],"abstract_inverted_index":{"Segment":[0,101],"Anything":[1,102],"Model":[2,103],"(SAM)":[3],"has":[4],"achieved":[5],"remarkable":[6],"success":[7],"in":[8,37,199,215],"the":[9,45,99,132,205],"field":[10],"of":[11,68],"class-agnostic":[12],"image":[13,32,146],"segmentation":[14,33,41,62,91,109,118,147,181],"by":[15,130,165,210,225],"utilizing":[16],"points":[17],"or":[18],"boxes":[19],"as":[20],"prompts.":[21],"However,":[22],"we":[23,97],"identify":[24],"two":[25],"significant":[26],"limitations":[27],"when":[28],"compared":[29],"to":[30,47,84,112],"traditional":[31,57,117,145],"models:":[34],"(1)":[35],"Trained":[36],"a":[38,105,121,154,212],"category-agnostic":[39],"interactive":[40],"manner,":[42],"SAM":[43,129],"lacks":[44],"ability":[46],"discern":[48],"object":[49],"granularity":[50],"and":[51,60,72,78,89,107,116,123,179,191,220],"semantics,":[52],"rendering":[53],"it":[54],"ineffective":[55],"for":[56,80,143],"instance,":[58,82,177],"semantic,":[59,178],"panoptic":[61,180],"tasks.":[63,148],"(2)":[64],"SAM\u2019s":[65],"inefficient":[66],"use":[67],"instance-independent":[69],"visual":[70,168],"features":[71,77,142,169],"tokens":[73,79],"necessitates":[74],"maintaining":[75],"unique":[76],"each":[81],"leading":[83],"excessive":[85],"GPU":[86,162],"memory":[87,163,223],"consumption":[88],"diminished":[90],"efficiency.":[92],"To":[93],"address":[94],"these":[95],"issues,":[96],"propose":[98],"Universal":[100],"(U-SAM),":[104],"semantic-aware":[106],"memory-efficient":[108],"model":[110],"designed":[111],"perform":[113],"both":[114],"promptable":[115],"tasks":[119],"within":[120],"compact":[122],"unified":[124],"framework.":[125],"Specifically,":[126],"U-SAM":[127,150,187,203],"enhances":[128],"integrating":[131],"Multi-Scale":[133],"Semantic-Aware":[134],"Image":[135],"Encoder":[136],"(S2IE),":[137],"thus":[138],"providing":[139],"multi-scale":[140],"semantic":[141],"achieving":[144,211],"Additionally,":[149],"is":[151,188],"equipped":[152],"with":[153,170],"Twin":[155],"Token":[156],"Mask":[157],"Decoder":[158],"(T2MD)":[159],"which":[160],"reduces":[161],"overhead":[164],"substituting":[166],"replicated":[167,171],"tokens.":[172],"Extensive":[173],"experiments":[174],"across":[175],"interactive,":[176],"demonstrate":[182],"U-SAM\u2019s":[183],"promising":[184],"results.":[185],"Notably,":[186],"9\u00d7":[189],"smaller":[190],"10\u00d7":[192],"faster":[193],"than":[194],"SAM,":[195],"showing":[196],"strong":[197],"performance":[198],"zero-shot":[200],"segmentation.":[201],"Moreover,":[202],"surpasses":[204],"SOTA":[206],"object-prompter-based":[207],"model,":[208],"RSPrompter,":[209],"6.2%":[213],"increase":[214],"PQ,":[216],"operating":[217],"14\u00d7":[218],"faster,":[219],"cutting":[221],"training":[222],"usage":[224],"61%.":[226]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}