{"id":"https://openalex.org/W4414360466","doi":"https://doi.org/10.24963/ijcai.2025/889","title":"DenseSAM: Semantic Enhance SAM for Efficient Dense Object Segmentation","display_name":"DenseSAM: Semantic Enhance SAM for Efficient Dense Object Segmentation","publication_year":2025,"publication_date":"2025-09-01","ids":{"openalex":"https://openalex.org/W4414360466","doi":"https://doi.org/10.24963/ijcai.2025/889"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2025/889","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","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/A5031728902","display_name":"Linyun Zhou","orcid":"https://orcid.org/0000-0001-8160-5623"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Linyun Zhou","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075445069","display_name":"Jiacong Hu","orcid":null},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jiacong Hu","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070429750","display_name":"Shengxuming Zhang","orcid":"https://orcid.org/0000-0002-8827-9012"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shengxuming Zhang","raw_affiliation_strings":["School of Software Technology, Zhejiang University","State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"School of Software Technology, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048922656","display_name":"Xiangtong Du","orcid":"https://orcid.org/0000-0002-3301-6717"},"institutions":[{"id":"https://openalex.org/I177388780","display_name":"Xuzhou Medical College","ror":"https://ror.org/04fe7hy80","country_code":"CN","type":"education","lineage":["https://openalex.org/I177388780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiangtong Du","raw_affiliation_strings":["Xuzhou Medical University"],"affiliations":[{"raw_affiliation_string":"Xuzhou Medical University","institution_ids":["https://openalex.org/I177388780"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026532752","display_name":"Mingli Song","orcid":"https://orcid.org/0000-0003-2621-6048"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingli Song","raw_affiliation_strings":["State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101980996","display_name":"Xiuming Zhang","orcid":"https://orcid.org/0000-0002-0457-5296"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiuming Zhang","raw_affiliation_strings":["The First Affiliated Hospital, College of Medicine, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"The First Affiliated Hospital, College of Medicine, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5043914348","display_name":"Zunlei Feng","orcid":"https://orcid.org/0000-0001-8640-8434"},"institutions":[{"id":"https://openalex.org/I76130692","display_name":"Zhejiang University","ror":"https://ror.org/00a2xv884","country_code":"CN","type":"education","lineage":["https://openalex.org/I76130692"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zunlei Feng","raw_affiliation_strings":["Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","School of Software Technology, Zhejiang University","State Key Laboratory of Blockchain and Data Security, Zhejiang University"],"affiliations":[{"raw_affiliation_string":"Hangzhou High-Tech Zone (Binjiang) Institute of Blockchain and Data Security","institution_ids":[]},{"raw_affiliation_string":"School of Software Technology, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]},{"raw_affiliation_string":"State Key Laboratory of Blockchain and Data Security, Zhejiang University","institution_ids":["https://openalex.org/I76130692"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":7,"corresponding_author_ids":["https://openalex.org/A5031728902"],"corresponding_institution_ids":["https://openalex.org/I76130692"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.26785696,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"7994","last_page":"8002"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.992900013923645,"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":0.992900013923645,"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/T12702","display_name":"Brain Tumor Detection and Classification","score":0.9663000106811523,"subfield":{"id":"https://openalex.org/subfields/2808","display_name":"Neurology"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9606999754905701,"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":0.8040000200271606},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5702000260353088},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5687000155448914},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5422000288963318},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5271000266075134},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.5235999822616577},{"id":"https://openalex.org/keywords/segmentation-based-object-categorization","display_name":"Segmentation-based object categorization","score":0.4934000074863434},{"id":"https://openalex.org/keywords/scale-space-segmentation","display_name":"Scale-space segmentation","score":0.49230000376701355},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.48579999804496765}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8237000107765198},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.8040000200271606},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7026000022888184},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5702000260353088},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5687000155448914},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5511000156402588},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5422000288963318},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5271000266075134},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.5235999822616577},{"id":"https://openalex.org/C25694479","wikidata":"https://www.wikidata.org/wiki/Q7446278","display_name":"Segmentation-based object categorization","level":5,"score":0.4934000074863434},{"id":"https://openalex.org/C65885262","wikidata":"https://www.wikidata.org/wiki/Q7429708","display_name":"Scale-space segmentation","level":4,"score":0.49230000376701355},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.48579999804496765},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.47839999198913574},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44339999556541443},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4426000118255615},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.40290001034736633},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.37529999017715454},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.3621000051498413},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3564000129699707},{"id":"https://openalex.org/C2776502983","wikidata":"https://www.wikidata.org/wiki/Q690182","display_name":"Contrast (vision)","level":2,"score":0.33379998803138733},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.3172000050544739},{"id":"https://openalex.org/C184337299","wikidata":"https://www.wikidata.org/wiki/Q1437428","display_name":"Semantics (computer science)","level":2,"score":0.3124000132083893},{"id":"https://openalex.org/C2775955345","wikidata":"https://www.wikidata.org/wiki/Q7449071","display_name":"Semantic mapping","level":2,"score":0.29919999837875366},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.29899999499320984},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.2971999943256378},{"id":"https://openalex.org/C183322885","wikidata":"https://www.wikidata.org/wiki/Q17007702","display_name":"Context model","level":3,"score":0.2782999873161316},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.2551000118255615},{"id":"https://openalex.org/C175154964","wikidata":"https://www.wikidata.org/wiki/Q380077","display_name":"Task analysis","level":3,"score":0.2526000142097473},{"id":"https://openalex.org/C64754055","wikidata":"https://www.wikidata.org/wiki/Q7574053","display_name":"Spatial contextual awareness","level":2,"score":0.25049999356269836}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2025/889","is_oa":false,"landing_page_url":"https://doi.org/10.24963/ijcai.2025/889","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Fourth International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Dense":[0],"object":[1,220],"segmentation":[2,67,139,221],"is":[3,84,114,225],"essential":[4,120],"for":[5,121,137,217],"various":[6,218],"applications,":[7],"particularly":[8],"in":[9,25,65,81,140],"pathology":[10,185],"image":[11,15],"and":[12,21,35,99,170,200],"remote":[13,206],"sensing":[14,207],"analysis.":[16],"However,":[17,75],"distinguishing":[18],"numerous":[19,77],"similar":[20],"densely":[22],"packed":[23],"objects":[24],"this":[26,88],"task":[27],"presents":[28],"significant":[29,63],"challenges.":[30],"Several":[31],"methods,":[32],"including":[33],"CNN-":[34],"ViT-based":[36],"approaches,":[37],"have":[38],"been":[39],"proposed":[40],"to":[41,148,158,176],"tackle":[42],"these":[43],"issues.":[44],"Yet,":[45],"models":[46],"trained":[47],"on":[48,71,184,205],"limited":[49,52],"datasets":[50],"exhibit":[51],"generalization":[53,104],"ability.":[54],"The":[55,223],"Segment":[56],"Anything":[57],"Model":[58],"(SAM)":[59],"has":[60],"recently":[61],"achieved":[62],"progress":[64],"zero-shot":[66],"but":[68],"relies":[69],"heavily":[70],"precise":[72],"positional":[73],"guidance.":[74],"providing":[76,197],"accurate":[78],"location":[79,118,132],"prompts":[80,119,133],"dense":[82,141,219],"scenarios":[83],"time-consuming.":[85],"To":[86],"overcome":[87],"limitation,":[89],"we":[90],"conducted":[91],"an":[92],"in-depth":[93],"exploration":[94],"of":[95,128,152],"the":[96,108,126,150,168],"SAM":[97],"mechanism":[98],"found":[100],"that":[101,188],"its":[102,211],"strong":[103],"ability":[105],"stems":[106],"from":[107],"encoder\u2019s":[109],"edge":[110],"detection":[111],"capability,":[112],"which":[113,130],"semantically":[115],"independent,":[116],"making":[117,214],"segmentation.":[122,181],"This":[123],"insight":[124],"inspired":[125],"development":[127],"DenseSAM,":[129],"replaces":[131],"with":[134,167,193],"semantic":[135,180],"guidance":[136],"automatic":[138,179],"scenarios.":[142],"Specifically,":[143],"it":[144],"uses":[145],"local":[146],"details":[147],"weaken":[149],"edges":[151],"background":[153],"objects,":[154],"leverages":[155],"global":[156],"context":[157],"enhance":[159],"intra-class":[160],"feature":[161],"similarity,":[162],"while":[163],"further":[164,209],"increasing":[165],"contrast":[166],"background,":[169],"integrates":[171],"a":[172,198],"dual-head":[173],"decoding":[174],"process":[175],"enable":[177],"lightweight":[178],"Extensive":[182],"experiments":[183,204],"images":[186,208],"demonstrate":[187],"DenseSAM":[189,215],"delivers":[190],"remarkable":[191],"performance":[192],"minimal":[194],"training":[195],"parameters,":[196],"cost-effective":[199],"efficient":[201],"solution.":[202],"Moreover,":[203],"validate":[210],"excellent":[212],"scalability,":[213],"suitable":[216],"domains.":[222],"code":[224],"available":[226],"at":[227],"https://github.com/imAzhou/DenseSAM.":[228]},"counts_by_year":[],"updated_date":"2026-03-07T16:01:11.037858","created_date":"2025-10-10T00:00:00"}