{"id":"https://openalex.org/W4413222003","doi":"https://doi.org/10.1145/3758090","title":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","display_name":"Transformers in Small Object Detection: A Benchmark and Survey of State-of-the-Art","publication_year":2025,"publication_date":"2025-08-11","ids":{"openalex":"https://openalex.org/W4413222003","doi":"https://doi.org/10.1145/3758090"},"language":"en","primary_location":{"id":"doi:10.1145/3758090","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3758090","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"hybrid","oa_url":"https://doi.org/10.1145/3758090","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5079424927","display_name":"Aref Miri Rekavandi","orcid":"https://orcid.org/0000-0001-9542-759X"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Aref Miri Rekavandi","raw_affiliation_strings":["The University of Western Australia","The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0001-9542-759X","affiliations":[{"raw_affiliation_string":"The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022342785","display_name":"Shima Rashidi","orcid":"https://orcid.org/0000-0002-6862-750X"},"institutions":[{"id":"https://openalex.org/I4210095297","display_name":"MIT University","ror":"https://ror.org/00v140q16","country_code":"MK","type":"education","lineage":["https://openalex.org/I4210095297"]},{"id":"https://openalex.org/I82951845","display_name":"RMIT University","ror":"https://ror.org/04ttjf776","country_code":"AU","type":"education","lineage":["https://openalex.org/I82951845"]}],"countries":["AU","MK"],"is_corresponding":false,"raw_author_name":"Shima Rashidi","raw_affiliation_strings":["RMIT University","RMIT University, Melbourne, Australia"],"raw_orcid":"https://orcid.org/0000-0001-5154-2385","affiliations":[{"raw_affiliation_string":"RMIT University","institution_ids":["https://openalex.org/I4210095297","https://openalex.org/I82951845"]},{"raw_affiliation_string":"RMIT University, Melbourne, Australia","institution_ids":["https://openalex.org/I82951845"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5014216530","display_name":"Farid Boussa\u00efd","orcid":"https://orcid.org/0000-0001-7250-7407"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Farid Boussaid","raw_affiliation_strings":["The University of Western Australia","The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0001-7250-7407","affiliations":[{"raw_affiliation_string":"The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5077184240","display_name":"Stephen Hoefs","orcid":null},"institutions":[{"id":"https://openalex.org/I1303474014","display_name":"Defence Science and Technology Group","ror":"https://ror.org/05ddrvt52","country_code":"AU","type":"government","lineage":["https://openalex.org/I1303474014","https://openalex.org/I2801453606","https://openalex.org/I3139952251"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Stephen Hoefs","raw_affiliation_strings":["Defence Science and Technology Group","Defence Science and Technology Group, Perth, Australia"],"raw_orcid":"https://orcid.org/0009-0000-5181-3042","affiliations":[{"raw_affiliation_string":"Defence Science and Technology Group","institution_ids":["https://openalex.org/I1303474014"]},{"raw_affiliation_string":"Defence Science and Technology Group, Perth, Australia","institution_ids":["https://openalex.org/I1303474014"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076398399","display_name":"Emre Akba\u015f","orcid":"https://orcid.org/0000-0002-3760-6722"},"institutions":[{"id":"https://openalex.org/I201799495","display_name":"Middle East Technical University","ror":"https://ror.org/014weej12","country_code":"TR","type":"education","lineage":["https://openalex.org/I201799495"]},{"id":"https://openalex.org/I2802821144","display_name":"Center for Environmental Health","ror":"https://ror.org/03k84rm07","country_code":"US","type":"facility","lineage":["https://openalex.org/I2802821144"]},{"id":"https://openalex.org/I3018134672","display_name":"Helmholtz Zentrum M\u00fcnchen","ror":"https://ror.org/00cfam450","country_code":"DE","type":"facility","lineage":["https://openalex.org/I1305996414","https://openalex.org/I3018134672"]}],"countries":["DE","TR","US"],"is_corresponding":false,"raw_author_name":"Emre Akbas","raw_affiliation_strings":["Helmholtz Center Munich German Research Center for Environmental Health","Middle East Technical University","Middle East Technical University, Ankara, Turkey and Helmholtz Center Munich German Research Center for Environmental Health, Neuherberg, Germany"],"raw_orcid":"https://orcid.org/0000-0002-3760-6722","affiliations":[{"raw_affiliation_string":"Helmholtz Center Munich German Research Center for Environmental Health","institution_ids":["https://openalex.org/I2802821144","https://openalex.org/I3018134672"]},{"raw_affiliation_string":"Middle East Technical University","institution_ids":["https://openalex.org/I201799495"]},{"raw_affiliation_string":"Middle East Technical University, Ankara, Turkey and Helmholtz Center Munich German Research Center for Environmental Health, Neuherberg, Germany","institution_ids":["https://openalex.org/I201799495","https://openalex.org/I3018134672"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5009750573","display_name":"Mohammed Bennamoun","orcid":"https://orcid.org/0000-0002-6603-3257"},"institutions":[{"id":"https://openalex.org/I177877127","display_name":"The University of Western Australia","ror":"https://ror.org/047272k79","country_code":"AU","type":"education","lineage":["https://openalex.org/I177877127"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Mohammed Bennamoun","raw_affiliation_strings":["School of Computer Science and Software Engineering, The University of Western Australia","School of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia"],"raw_orcid":"https://orcid.org/0000-0002-6603-3257","affiliations":[{"raw_affiliation_string":"School of Computer Science and Software Engineering, The University of Western Australia","institution_ids":["https://openalex.org/I177877127"]},{"raw_affiliation_string":"School of Computer Science and Software Engineering, The University of Western Australia, Perth, Australia","institution_ids":["https://openalex.org/I177877127"]}]}],"institutions":[],"countries_distinct_count":5,"institutions_distinct_count":7,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.6887,"has_fulltext":false,"cited_by_count":25,"citation_normalized_percentile":{"value":0.9927859,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":99,"max":100},"biblio":{"volume":"58","issue":"3","first_page":"1","last_page":"33"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998999834060669,"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":0.9998999834060669,"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/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/2209","display_name":"Industrial and Manufacturing 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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9919000267982483,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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":0.8523613214492798},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.6193593144416809},{"id":"https://openalex.org/keywords/transformer","display_name":"Transformer","score":0.58221435546875},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.54393470287323},{"id":"https://openalex.org/keywords/image-stitching","display_name":"Image stitching","score":0.4405277967453003},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.44018983840942383},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.41176119446754456},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3407970666885376},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.2774617075920105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8523613214492798},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6193593144416809},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.58221435546875},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.54393470287323},{"id":"https://openalex.org/C29081049","wikidata":"https://www.wikidata.org/wiki/Q1364242","display_name":"Image stitching","level":2,"score":0.4405277967453003},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.44018983840942383},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.41176119446754456},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3407970666885376},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.2774617075920105},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C165801399","wikidata":"https://www.wikidata.org/wiki/Q25428","display_name":"Voltage","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/3758090","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3758090","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:openaire/8327181e-eed6-42af-87f4-755c1b04d1e8","is_oa":true,"landing_page_url":"https://research-repository.uwa.edu.au/en/publications/8327181e-eed6-42af-87f4-755c1b04d1e8","pdf_url":null,"source":{"id":"https://openalex.org/S4306402523","display_name":"UWA Profiles and Research Repository (University of Western Australia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I177877127","host_organization_name":"The University of Western Australia","host_organization_lineage":["https://openalex.org/I177877127"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Miri Rekavandi, A, Rashidi, S, Boussaid, F, Hoefs, S, Akbas, E & Bennamoun, M 2025, 'Transformers in Small Object Detection : A Benchmark and Survey of State-of-the-Art', ACM Computing Surveys, vol. 58, no. 3, 64. https://doi.org/10.1145/3758090","raw_type":"info:eu-repo/semantics/article"},{"id":"pmh:oai:https://open.metu.edu.tr:11511/117269","is_oa":false,"landing_page_url":"https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=105021924275&origin=inward","pdf_url":null,"source":{"id":"https://openalex.org/S4306402495","display_name":"OpenMETU (Middle East Technical University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I201799495","host_organization_name":"Middle East Technical University","host_organization_lineage":["https://openalex.org/I201799495"],"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":"Journal Article"}],"best_oa_location":{"id":"doi:10.1145/3758090","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3758090","pdf_url":null,"source":{"id":"https://openalex.org/S157921468","display_name":"ACM Computing Surveys","issn_l":"0360-0300","issn":["0360-0300","1557-7341"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Computing Surveys","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G2222343817","display_name":null,"funder_award_id":"ARC DP210101682, DP210102674","funder_id":"https://openalex.org/F4320334704","funder_display_name":"Australian Research Council"}],"funders":[{"id":"https://openalex.org/F4320334704","display_name":"Australian Research Council","ror":"https://ror.org/05mmh0f86"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":70,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W2005926822","https://openalex.org/W2109255472","https://openalex.org/W2117539524","https://openalex.org/W2186222003","https://openalex.org/W2512351403","https://openalex.org/W2518876086","https://openalex.org/W2558687840","https://openalex.org/W2570343428","https://openalex.org/W2602856279","https://openalex.org/W2883683269","https://openalex.org/W2890968433","https://openalex.org/W2914353073","https://openalex.org/W2935079508","https://openalex.org/W2943659362","https://openalex.org/W2950800384","https://openalex.org/W2962721361","https://openalex.org/W2989676862","https://openalex.org/W2992240579","https://openalex.org/W3011722050","https://openalex.org/W3042930119","https://openalex.org/W3096609285","https://openalex.org/W3097055324","https://openalex.org/W3101430149","https://openalex.org/W3107867277","https://openalex.org/W3122239467","https://openalex.org/W3122799380","https://openalex.org/W3158364670","https://openalex.org/W3170778815","https://openalex.org/W3217153199","https://openalex.org/W4200047081","https://openalex.org/W4213200979","https://openalex.org/W4213281551","https://openalex.org/W4214540501","https://openalex.org/W4220726952","https://openalex.org/W4221166276","https://openalex.org/W4224079585","https://openalex.org/W4236965008","https://openalex.org/W4281263827","https://openalex.org/W4283029931","https://openalex.org/W4285110782","https://openalex.org/W4286974534","https://openalex.org/W4289890839","https://openalex.org/W4292387403","https://openalex.org/W4294167341","https://openalex.org/W4294805043","https://openalex.org/W4295927775","https://openalex.org/W4296281486","https://openalex.org/W4297093526","https://openalex.org/W4299296451","https://openalex.org/W4306955484","https://openalex.org/W4307494192","https://openalex.org/W4312335509","https://openalex.org/W4312713936","https://openalex.org/W4312785838","https://openalex.org/W4313555051","https://openalex.org/W4313591362","https://openalex.org/W4313827729","https://openalex.org/W4315641800","https://openalex.org/W4315881624","https://openalex.org/W4317938492","https://openalex.org/W4319990398","https://openalex.org/W4320009770","https://openalex.org/W4321094182","https://openalex.org/W4382568144","https://openalex.org/W4385245566","https://openalex.org/W4385877222","https://openalex.org/W4389665201","https://openalex.org/W4407574876","https://openalex.org/W4409887807"],"related_works":["https://openalex.org/W68020613","https://openalex.org/W1973382465","https://openalex.org/W4255291540","https://openalex.org/W3134240150","https://openalex.org/W2091466534","https://openalex.org/W4387591196","https://openalex.org/W4392793652","https://openalex.org/W4399199700","https://openalex.org/W172825421","https://openalex.org/W2944699522"],"abstract_inverted_index":{"Transformers":[0],"have":[1,42],"rapidly":[2],"gained":[3],"popularity":[4],"in":[5,9,33,53,97,133,164],"computer":[6],"vision,":[7],"especially":[8],"the":[10,17,48,66,113,118,169,172],"field":[11],"of":[12,19,47,104,115,128,154,171,190,196],"object":[13,21,51],"detection.":[14],"Upon":[15],"examining":[16],"outcomes":[18],"state-of-the-art":[20],"detection":[22,54,129],"methods,":[23],"we":[24],"noticed":[25],"that":[26,91,161],"transformers":[27,111],"consistently":[28],"outperformed":[29],"well-established":[30],"CNN-based":[31],"detectors":[32],"almost":[34],"every":[35],"video":[36],"or":[37],"image":[38],"dataset.":[39],"Small":[40,80],"objects":[41],"been":[43],"identified":[44],"as":[45,179],"one":[46],"most":[49],"challenging":[50],"types":[52],"frameworks":[55],"due":[56],"to":[57,64,87,121],"their":[58,79],"low":[59],"visibility.":[60],"This":[61,99],"article":[62],"aims":[63],"explore":[65],"performance":[67,96,170],"benefits":[68],"offered":[69],"by":[70],"such":[71,178],"extensive":[72],"networks":[73],"and":[74,145,150,167,188],"identify":[75],"potential":[76,89],"reasons":[77],"for":[78,112,159],"Object":[81],"Detection":[82],"(SOD)":[83],"superiority.":[84],"We":[85,147],"aim":[86],"investigate":[88],"strategies":[90],"could":[92],"further":[93],"enhance":[94],"transformers\u2019":[95],"SOD.":[98],"survey":[100],"presents":[101],"a":[102,126,152],"taxonomy":[103],"over":[105],"60":[106],"research":[107],"studies":[108,124,166,174,198],"on":[109,199],"developed":[110],"task":[114],"SOD,":[116],"spanning":[117],"years":[119],"2020":[120],"2023.":[122],"These":[123],"encompass":[125],"variety":[127],"applications,":[130],"including":[131],"SOD":[132,160],"generic":[134],"images,":[135,137,139,142,144],"aerial":[136],"medical":[138],"active":[140],"millimeter":[141],"underwater":[143],"videos.":[146],"also":[148],"compile":[149],"present":[151],"list":[153],"12":[155],"large-scale":[156],"datasets":[157],"suitable":[158],"were":[162],"overlooked":[163],"previous":[165],"compare":[168],"reviewed":[173],"using":[175],"popular":[176],"metrics":[177],"mean":[180],"Average":[181],"Precision":[182],"(mAP),":[183],"Frames":[184],"Per":[185],"Second":[186],"(FPS),":[187],"number":[189],"parameters.":[191],"Researchers":[192],"can":[193],"keep":[194],"track":[195],"newer":[197],"our":[200],"web":[201],"page,":[202],"which":[203],"is":[204],"available":[205],"at:":[206],"https://github.com/arekavandi/Transformer-SOD.":[207]},"counts_by_year":[{"year":2026,"cited_by_count":14},{"year":2025,"cited_by_count":11}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2025-08-17T00:00:00"}