{"id":"https://openalex.org/W4393903914","doi":"https://doi.org/10.1145/3664647.3680571","title":"Deep Instruction Tuning for Segment Anything Model","display_name":"Deep Instruction Tuning for Segment Anything Model","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4393903914","doi":"https://doi.org/10.1145/3664647.3680571"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2404.00650","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Xiaorui Huang","orcid":"https://orcid.org/0009-0004-3168-1491"},"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":"Xiaorui Huang","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0004-3168-1491","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102997988","display_name":"Gen Luo","orcid":"https://orcid.org/0000-0001-5334-1843"},"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":"Gen Luo","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0001-5334-1843","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chaoyang Zhu","orcid":"https://orcid.org/0009-0005-7455-326X"},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]},{"id":"https://openalex.org/I889458895","display_name":"University of Hong Kong","ror":"https://ror.org/02zhqgq86","country_code":"HK","type":"education","lineage":["https://openalex.org/I889458895"]}],"countries":["HK"],"is_corresponding":false,"raw_author_name":"Chaoyang Zhu","raw_affiliation_strings":["The Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"],"raw_orcid":"https://orcid.org/0009-0005-7455-326X","affiliations":[{"raw_affiliation_string":"The Department of Computer Science and Engineering, The Hong Kong University of Science and Technology, Hong Kong, Hong Kong","institution_ids":["https://openalex.org/I200769079","https://openalex.org/I889458895"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Bo Tong","orcid":"https://orcid.org/0009-0006-3569-4278"},"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":"Bo Tong","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Minis, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0006-3569-4278","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Minis, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5091531008","display_name":"Yiyi Zhou","orcid":"https://orcid.org/0000-0002-5110-4526"},"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":"Yiyi Zhou","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Minis, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-5110-4526","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Minis, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059926864","display_name":"Xiaoshuai Sun","orcid":"https://orcid.org/0000-0003-3912-9306"},"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":"Xiaoshuai Sun","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Minis, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0003-3912-9306","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Minis, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016080094","display_name":"Rongrong Ji","orcid":"https://orcid.org/0000-0001-9163-2932"},"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":"Rongrong Ji","raw_affiliation_strings":["Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0001-9163-2932","affiliations":[{"raw_affiliation_string":"Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, Xiamen University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I191208505"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.04328734,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"905","last_page":"914"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.4307999908924103,"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/T10444","display_name":"Context-Aware Activity Recognition Systems","score":0.4307999908924103,"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/T12720","display_name":"Multimedia Communication and Technology","score":0.4307999908924103,"subfield":{"id":"https://openalex.org/subfields/3312","display_name":"Sociology and Political Science"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T10904","display_name":"Embedded Systems Design Techniques","score":0.3714999854564667,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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":0.5117856860160828},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3713454604148865},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.33517658710479736}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5117856860160828},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3713454604148865},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.33517658710479736}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3664647.3680571","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680571","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 32nd ACM International Conference on Multimedia","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2404.00650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.00650","pdf_url":"https://arxiv.org/pdf/2404.00650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"pmh:oai:repository.hkust.edu.hk:1783.1-148930","is_oa":false,"landing_page_url":"http://repository.hkust.edu.hk/ir/Record/1783.1-148930","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Conference paper"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2404.00650","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2404.00650","pdf_url":"https://arxiv.org/pdf/2404.00650","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1271955826","display_name":"\u57fa\u4e8e\u5f31\u76d1\u7763\u5b66\u4e60\u7684\u673a\u8f7d\u5730/\u6d77\u5c0f\u76ee\u6807\u68c0\u6d4b\u7814\u7a76","funder_award_id":"62072387","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1300220747","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1627692989","display_name":null,"funder_award_id":"2021J01002","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G1787173488","display_name":"\u9762\u5411\u6df1\u5ea6\u5b66\u4e60\u7684\u5bf9\u6297\u653b\u9632\u6280\u672f\u7814\u7a76","funder_award_id":"62072389","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G187639494","display_name":null,"funder_award_id":"No. 62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G2564228358","display_name":null,"funder_award_id":"No. 62025603","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2785666877","display_name":null,"funder_award_id":"62002305","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3181244293","display_name":null,"funder_award_id":"2022J06001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G3568142893","display_name":null,"funder_award_id":"62272401","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G390962370","display_name":null,"funder_award_id":"2021J01002","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G5284885812","display_name":null,"funder_award_id":"62176222","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6075090814","display_name":null,"funder_award_id":"62025603","funder_id":"https://openalex.org/F4320336125","funder_display_name":"National Science Fund for Distinguished Young Scholars"},{"id":"https://openalex.org/G6727647225","display_name":null,"funder_award_id":"62176226","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G717600273","display_name":null,"funder_award_id":"U22B2051","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7220565969","display_name":null,"funder_award_id":"2022J06001","funder_id":"https://openalex.org/F4320321878","funder_display_name":"Natural Science Foundation of Fujian Province"},{"id":"https://openalex.org/G7272499820","display_name":null,"funder_award_id":"U21B2037","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G7779606772","display_name":null,"funder_award_id":"62176223","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G8406165135","display_name":"\u9762\u5411\u56fe\u654f\u611f\u6df1\u5ea6\u5b66\u4e60\u7684\u7ed3\u6784\u5316\u8d85\u56fe\u7814\u7a76","funder_award_id":"62072386","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/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":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4393903914.pdf"},"referenced_works_count":25,"referenced_works":["https://openalex.org/W1903029394","https://openalex.org/W2277195237","https://openalex.org/W2876852810","https://openalex.org/W2964284374","https://openalex.org/W2999219213","https://openalex.org/W3034325957","https://openalex.org/W3035097537","https://openalex.org/W3093025045","https://openalex.org/W3106546328","https://openalex.org/W3138516171","https://openalex.org/W3169998662","https://openalex.org/W3172522282","https://openalex.org/W3187664142","https://openalex.org/W3206209177","https://openalex.org/W4312956471","https://openalex.org/W4382240193","https://openalex.org/W4386065815","https://openalex.org/W4386075493","https://openalex.org/W4387968216","https://openalex.org/W4387969771","https://openalex.org/W4390873429","https://openalex.org/W4390874575","https://openalex.org/W4391948963","https://openalex.org/W4393160910","https://openalex.org/W4402660119"],"related_works":["https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2478288626","https://openalex.org/W4391913857","https://openalex.org/W2350741829","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Recently,":[0],"Segment":[1],"Anything":[2],"Model":[3],"(SAM)":[4],"has":[5],"become":[6],"a":[7,127,159,167],"research":[8],"hotspot":[9],"in":[10,83,131],"the":[11,79,110,121,140,171,177],"fields":[12],"of":[13,37,124,142,155],"multimedia":[14],"and":[15,46,109,185],"computer":[16],"vision,":[17],"which":[18],"exhibits":[19],"powerful":[20],"yet":[21,97],"versatile":[22],"capabilities":[23],"on":[24,53,149],"various":[25],"(un)":[26],"conditional":[27],"image":[28,58,122],"segmentation":[29,38,59,145],"tasks.":[30],"Although":[31],"SAM":[32,125,165],"can":[33,118,163,174],"support":[34],"different":[35],"types":[36],"prompts,":[39],"we":[40,64,93],"note":[41],"that,":[42],"compared":[43],"to":[44,73,133,179],"point-":[45],"box-guided":[47],"segmentations,":[48],"it":[49],"performs":[50],"much":[51,182],"worse":[52],"text-instructed":[54],"tasks,":[55],"e.g.,":[56],"referring":[57],"(RIS).":[60],"In":[61],"this":[62,91],"paper,":[63],"argue":[65],"that":[66,158],"deep":[67,99,136],"text":[68],"instruction":[69,100],"tuning":[70,101],"is":[71,107,112,190],"key":[72],"mitigate":[74],"such":[75],"shortcoming":[76],"caused":[77],"by":[78,166],"shallow":[80],"fusion":[81,137],"scheme":[82],"its":[84,143],"default":[85],"light-weight":[86],"mask":[87],"decoder.":[88],"To":[89],"address":[90],"issue,":[92],"propose":[94],"two":[95],"simple":[96,160],"effective":[98],"(DIT)":[102],"methods":[103],"for":[104],"SAM,":[105],"one":[106],"end-to-end":[108,161],"other":[111],"layer-wise.":[113],"With":[114],"minimal":[115],"modifications,":[116],"DITs":[117],"directly":[119],"transform":[120],"encoder":[123],"as":[126],"stand-alone":[128],"vision-language":[129],"learner":[130],"contrast":[132],"building":[134],"another":[135],"branch,":[138],"maximizing":[139],"benefit":[141],"superior":[144],"capability.":[146],"Extensive":[147],"experiments":[148],"three":[150],"highly":[151],"competitive":[152],"benchmark":[153],"datasets":[154],"RIS":[156],"show":[157],"DIT":[162,173],"improve":[164],"large":[168],"margin,":[169],"while":[170],"layer-wise":[172],"further":[175],"boost":[176],"performance":[178],"state-of-the-art":[180],"with":[181],"less":[183],"data":[184],"training":[186],"expenditures.":[187],"Our":[188],"code":[189],"released":[191],"at:":[192],"https://github.com/wysnzzzz/DIT.":[193]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}