{"id":"https://openalex.org/W4403594096","doi":"https://doi.org/10.1145/3664647.3680609","title":"Unleashing the Power of Generic Segmentation Model: A Simple Baseline for Infrared Small Target Detection","display_name":"Unleashing the Power of Generic Segmentation Model: A Simple Baseline for Infrared Small Target Detection","publication_year":2024,"publication_date":"2024-10-26","ids":{"openalex":"https://openalex.org/W4403594096","doi":"https://doi.org/10.1145/3664647.3680609"},"language":"en","primary_location":{"id":"doi:10.1145/3664647.3680609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680609","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/2409.04714","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101464703","display_name":"Mingjin Zhang","orcid":"https://orcid.org/0000-0002-1473-9784"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjin Zhang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-1473-9784","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Chi Zhang","orcid":"https://orcid.org/0000-0002-5574-9399"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chi Zhang","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-5574-9399","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100639013","display_name":"Qiming Zhang","orcid":"https://orcid.org/0000-0003-0060-0543"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Qiming Zhang","raw_affiliation_strings":["The University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0003-0060-0543","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5067798266","display_name":"Yunsong Li","orcid":"https://orcid.org/0000-0002-0234-6270"},"institutions":[{"id":"https://openalex.org/I149594827","display_name":"Xidian University","ror":"https://ror.org/05s92vm98","country_code":"CN","type":"education","lineage":["https://openalex.org/I149594827"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yunsong Li","raw_affiliation_strings":["Xidian University, Xi'an, China"],"raw_orcid":"https://orcid.org/0000-0002-0234-6270","affiliations":[{"raw_affiliation_string":"Xidian University, Xi'an, China","institution_ids":["https://openalex.org/I149594827"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101785348","display_name":"Xinbo Gao","orcid":"https://orcid.org/0000-0002-7985-0037"},"institutions":[{"id":"https://openalex.org/I10535382","display_name":"Chongqing University of Posts and Telecommunications","ror":"https://ror.org/03dgaqz26","country_code":"CN","type":"education","lineage":["https://openalex.org/I10535382"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xinbo Gao","raw_affiliation_strings":["Chongqing University of Post and Telecommunications, Chongqing, China"],"raw_orcid":"https://orcid.org/0000-0002-7985-0037","affiliations":[{"raw_affiliation_string":"Chongqing University of Post and Telecommunications, Chongqing, China","institution_ids":["https://openalex.org/I10535382"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100345321","display_name":"Jing Zhang","orcid":"https://orcid.org/0000-0001-6595-7661"},"institutions":[{"id":"https://openalex.org/I129604602","display_name":"The University of Sydney","ror":"https://ror.org/0384j8v12","country_code":"AU","type":"education","lineage":["https://openalex.org/I129604602"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Jing Zhang","raw_affiliation_strings":["The University of Sydney, Sydney, Australia"],"raw_orcid":"https://orcid.org/0000-0001-6595-7661","affiliations":[{"raw_affiliation_string":"The University of Sydney, Sydney, Australia","institution_ids":["https://openalex.org/I129604602"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":42.5849,"has_fulltext":true,"cited_by_count":26,"citation_normalized_percentile":{"value":0.99877016,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"10392","last_page":"10401"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12389","display_name":"Infrared Target Detection Methodologies","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/2202","display_name":"Aerospace 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/T10689","display_name":"Remote-Sensing Image Classification","score":0.9925000071525574,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9818000197410583,"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/computer-science","display_name":"Computer science","score":0.8100402355194092},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.7562923431396484},{"id":"https://openalex.org/keywords/code","display_name":"Code (set theory)","score":0.579552173614502},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.5659981369972229},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5535302758216858},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.5022602081298828},{"id":"https://openalex.org/keywords/market-segmentation","display_name":"Market segmentation","score":0.44450992345809937},{"id":"https://openalex.org/keywords/bridge","display_name":"Bridge (graph theory)","score":0.4403218924999237},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4246489405632019},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.4171752333641052},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.4155097007751465},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.39697232842445374}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8100402355194092},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.7562923431396484},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.579552173614502},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.5659981369972229},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5535302758216858},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.5022602081298828},{"id":"https://openalex.org/C125308379","wikidata":"https://www.wikidata.org/wiki/Q363057","display_name":"Market segmentation","level":2,"score":0.44450992345809937},{"id":"https://openalex.org/C100776233","wikidata":"https://www.wikidata.org/wiki/Q2532492","display_name":"Bridge (graph theory)","level":2,"score":0.4403218924999237},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4246489405632019},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.4171752333641052},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.4155097007751465},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.39697232842445374},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.0},{"id":"https://openalex.org/C162853370","wikidata":"https://www.wikidata.org/wiki/Q39809","display_name":"Marketing","level":1,"score":0.0},{"id":"https://openalex.org/C126322002","wikidata":"https://www.wikidata.org/wiki/Q11180","display_name":"Internal medicine","level":1,"score":0.0},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C144133560","wikidata":"https://www.wikidata.org/wiki/Q4830453","display_name":"Business","level":0,"score":0.0},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3664647.3680609","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3664647.3680609","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:2409.04714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.04714","pdf_url":"https://arxiv.org/pdf/2409.04714","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2409.04714","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2409.04714","pdf_url":"https://arxiv.org/pdf/2409.04714","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[{"score":0.75,"display_name":"Quality Education","id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1154562550","display_name":null,"funder_award_id":"2023YFA100860","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G1300971796","display_name":null,"funder_award_id":"2023YFA100860","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G1713521428","display_name":null,"funder_award_id":"2024KFKT001-1","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2022121445","display_name":null,"funder_award_id":"U21A20514","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G2124497053","display_name":"\u9762\u5411\u771f\u5b9e\u573a\u666f\u7684\u56fe\u50cf\u8d85\u5206\u8fa8\u91cd\u5efa\u7814\u7a76","funder_award_id":"62061047","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G4305211891","display_name":null,"funder_award_id":"2021QNRC001","funder_id":"https://openalex.org/F4320335777","funder_display_name":"National Key Research and Development Program of China"},{"id":"https://openalex.org/G6386153180","display_name":null,"funder_award_id":"2021QNRC001","funder_id":"https://openalex.org/F4320311778","funder_display_name":"China Association for Science and Technology"},{"id":"https://openalex.org/G6665774762","display_name":null,"funder_award_id":"2021QNRC001","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G6976320768","display_name":null,"funder_award_id":"62272363","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"},{"id":"https://openalex.org/G913836228","display_name":null,"funder_award_id":"62036007","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320311778","display_name":"China Association for Science and Technology","ror":"https://ror.org/035vmht26"},{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"},{"id":"https://openalex.org/F4320335777","display_name":"National Key Research and Development Program of China","ror":null}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4403594096.pdf","grobid_xml":"https://content.openalex.org/works/W4403594096.grobid-xml"},"referenced_works_count":62,"referenced_works":["https://openalex.org/W1861492603","https://openalex.org/W1901129140","https://openalex.org/W1972868773","https://openalex.org/W1974872009","https://openalex.org/W2006273284","https://openalex.org/W2035159765","https://openalex.org/W2041560658","https://openalex.org/W2041646550","https://openalex.org/W2067173181","https://openalex.org/W2094153102","https://openalex.org/W2099244020","https://openalex.org/W2104408738","https://openalex.org/W2117539524","https://openalex.org/W2129500293","https://openalex.org/W2133643452","https://openalex.org/W2150815919","https://openalex.org/W2344310038","https://openalex.org/W2348142746","https://openalex.org/W2544366167","https://openalex.org/W2565639579","https://openalex.org/W2744362103","https://openalex.org/W2798769484","https://openalex.org/W2900678331","https://openalex.org/W2921709033","https://openalex.org/W2952787292","https://openalex.org/W2962914239","https://openalex.org/W2982242214","https://openalex.org/W2983943451","https://openalex.org/W2986015886","https://openalex.org/W3001427728","https://openalex.org/W3010079414","https://openalex.org/W3023890832","https://openalex.org/W3035358681","https://openalex.org/W3096609285","https://openalex.org/W3118249006","https://openalex.org/W3118934234","https://openalex.org/W3138516171","https://openalex.org/W3171950886","https://openalex.org/W3177349073","https://openalex.org/W3217157240","https://openalex.org/W4212863773","https://openalex.org/W4214524539","https://openalex.org/W4295308583","https://openalex.org/W4301516520","https://openalex.org/W4304084055","https://openalex.org/W4304092528","https://openalex.org/W4312322023","https://openalex.org/W4312348652","https://openalex.org/W4312980183","https://openalex.org/W4313065862","https://openalex.org/W4313506322","https://openalex.org/W4386066126","https://openalex.org/W4386071509","https://openalex.org/W4386072286","https://openalex.org/W4386076367","https://openalex.org/W4390190100","https://openalex.org/W4390874466","https://openalex.org/W4390874575","https://openalex.org/W4391109864","https://openalex.org/W4393148032","https://openalex.org/W4393159543","https://openalex.org/W6797153837"],"related_works":["https://openalex.org/W2383111961","https://openalex.org/W2365952365","https://openalex.org/W2352448290","https://openalex.org/W2380820513","https://openalex.org/W2913146933","https://openalex.org/W2372385138","https://openalex.org/W4296359239","https://openalex.org/W2101155126","https://openalex.org/W2043093291","https://openalex.org/W2363545964"],"abstract_inverted_index":{"Recent":[0],"advancements":[1],"in":[2,32,99,174],"deep":[3],"learning":[4],"have":[5],"greatly":[6],"advanced":[7],"the":[8,41,46,63,71,141],"field":[9],"of":[10,49,65],"infrared":[11,50,118],"small":[12,117],"object":[13],"detection":[14],"(IRSTD).":[15],"Despite":[16],"their":[17,96],"remarkable":[18],"success,":[19],"a":[20,108,146],"notable":[21],"gap":[22,37],"persists":[23],"between":[24],"these":[25],"IRSTD":[26,77,93,100,166],"methods":[27],"and":[28,45,152,177,185,193,201],"generic":[29,66,84],"segmentation":[30,67,85],"approaches":[31],"natural":[33],"image":[34],"domains.":[35],"This":[36],"primarily":[38],"arises":[39],"from":[40],"significant":[42],"modality":[43],"differences":[44],"limited":[47],"availability":[48],"data.":[51],"In":[52],"this":[53,59],"study,":[54],"we":[55,106,124,139],"aim":[56],"to":[57,76,91,129,155,180],"bridge":[58],"divergence":[60],"by":[61,144,187],"investigating":[62],"adaptation":[64],"models,":[68],"such":[69],"as":[70],"Segment":[72],"Anything":[73],"Model":[74],"(SAM),":[75],"tasks.":[78],"Our":[79],"investigation":[80],"reveals":[81],"that":[82],"many":[83],"models":[86,128,202],"can":[87],"achieve":[88],"comparable":[89],"performance":[90,143,173],"state-of-the-art":[92,131],"methods.":[94],"However,":[95],"full":[97],"potential":[98],"remains":[101],"untapped.":[102],"To":[103],"address":[104],"this,":[105],"propose":[107],"simple,":[109],"lightweight,":[110],"yet":[111],"effective":[112],"baseline":[113],"model":[114,169],"for":[115],"segmenting":[116],"objects.":[119],"Through":[120,160],"appropriate":[121],"distillation":[122],"strategies,":[123],"empower":[125],"smaller":[126],"student":[127],"outperform":[130],"methods,":[132],"even":[133],"surpassing":[134,183],"fine-tuned":[135],"teacher":[136],"results.":[137],"Furthermore,":[138],"enhance":[140],"model's":[142],"introducing":[145],"novel":[147],"query":[148],"design":[149],"comprising":[150],"dense":[151],"sparse":[153],"queries":[154],"effectively":[156],"encode":[157],"multi-scale":[158],"features.":[159],"extensive":[161],"experimentation":[162],"across":[163],"four":[164],"popular":[165],"datasets,":[167],"our":[168],"demonstrates":[170],"significantly":[171],"improved":[172],"both":[175],"accuracy":[176],"throughput":[178],"compared":[179],"existing":[181],"approaches,":[182],"SAM":[184],"Semantic-SAM":[186],"over":[188],"14":[189],"IoU":[190,195],"on":[191,196],"NUDT":[192],"4":[194],"IRSTD1k.":[197],"The":[198],"source":[199],"code":[200],"will":[203],"be":[204],"released":[205],"at":[206],"https://github.com/O937-blip/SimIR.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":5},{"year":2025,"cited_by_count":21}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2024-10-22T00:00:00"}