{"id":"https://openalex.org/W4307411363","doi":"https://doi.org/10.1109/icip46576.2022.9897990","title":"Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection","display_name":"Slicing Aided Hyper Inference and Fine-Tuning for Small Object Detection","publication_year":2022,"publication_date":"2022-10-16","ids":{"openalex":"https://openalex.org/W4307411363","doi":"https://doi.org/10.1109/icip46576.2022.9897990"},"language":"en","primary_location":{"id":"doi:10.1109/icip46576.2022.9897990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897990","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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/A5005084622","display_name":"Fatih \u00c7a\u011fatay Aky\u00f6n","orcid":"https://orcid.org/0000-0001-7098-3944"},"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/I4210147190","display_name":"Turkish Aerospace Industries (Turkey)","ror":"https://ror.org/03jjbp459","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210147190"]}],"countries":["TR"],"is_corresponding":true,"raw_author_name":"Fatih Cagatay Akyon","raw_affiliation_strings":["OBSS AI,Ankara,Turkey","OBSS AI, Ankara, Turkey","Graduate School of Informatics, Middle East Technical University, Ankara, Turkey"],"affiliations":[{"raw_affiliation_string":"OBSS AI,Ankara,Turkey","institution_ids":["https://openalex.org/I4210147190"]},{"raw_affiliation_string":"OBSS AI, Ankara, Turkey","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Informatics, Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034124601","display_name":"Sinan Onur Altinuc","orcid":"https://orcid.org/0000-0001-5119-160X"},"institutions":[{"id":"https://openalex.org/I4210147190","display_name":"Turkish Aerospace Industries (Turkey)","ror":"https://ror.org/03jjbp459","country_code":"TR","type":"company","lineage":["https://openalex.org/I4210147190"]},{"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"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Sinan Onur Altinuc","raw_affiliation_strings":["OBSS AI,Ankara,Turkey","OBSS AI, Ankara, Turkey","Graduate School of Informatics, Middle East Technical University, Ankara, Turkey"],"affiliations":[{"raw_affiliation_string":"OBSS AI,Ankara,Turkey","institution_ids":["https://openalex.org/I4210147190"]},{"raw_affiliation_string":"OBSS AI, Ankara, Turkey","institution_ids":[]},{"raw_affiliation_string":"Graduate School of Informatics, Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5003028527","display_name":"Alptekin Temizel","orcid":"https://orcid.org/0000-0001-6082-2573"},"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"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Alptekin Temizel","raw_affiliation_strings":["Middle East Technical University,Graduate School of Informatics,Ankara,Turkey","Graduate School of Informatics, Middle East Technical University, Ankara, Turkey"],"affiliations":[{"raw_affiliation_string":"Middle East Technical University,Graduate School of Informatics,Ankara,Turkey","institution_ids":["https://openalex.org/I201799495"]},{"raw_affiliation_string":"Graduate School of Informatics, Middle East Technical University, Ankara, Turkey","institution_ids":["https://openalex.org/I201799495"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5005084622"],"corresponding_institution_ids":["https://openalex.org/I201799495","https://openalex.org/I4210147190"],"apc_list":null,"apc_paid":null,"fwci":25.1886,"has_fulltext":false,"cited_by_count":462,"citation_normalized_percentile":{"value":0.99588361,"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":"966","last_page":"970"},"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9940000176429749,"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"}},{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9934999942779541,"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/slicing","display_name":"Slicing","score":0.8688206672668457},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7949973344802856},{"id":"https://openalex.org/keywords/object-detection","display_name":"Object detection","score":0.7924270629882812},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.7499605417251587},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.6501250267028809},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6231777667999268},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5719010829925537},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.5565789341926575},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.5414353609085083},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.5309958457946777},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.38047343492507935},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.14185777306556702}],"concepts":[{"id":"https://openalex.org/C2776190703","wikidata":"https://www.wikidata.org/wiki/Q488148","display_name":"Slicing","level":2,"score":0.8688206672668457},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7949973344802856},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.7924270629882812},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.7499605417251587},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.6501250267028809},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6231777667999268},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5719010829925537},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.5565789341926575},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.5414353609085083},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.5309958457946777},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.38047343492507935},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.14185777306556702},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icip46576.2022.9897990","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icip46576.2022.9897990","pdf_url":null,"source":{"id":"https://openalex.org/S4363607719","display_name":"2022 IEEE International Conference on Image Processing (ICIP)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 IEEE International Conference on Image Processing (ICIP)","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":32,"referenced_works":["https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W2031489346","https://openalex.org/W2108598243","https://openalex.org/W2193145675","https://openalex.org/W2565639579","https://openalex.org/W2798748382","https://openalex.org/W2893811450","https://openalex.org/W2913979809","https://openalex.org/W2945786113","https://openalex.org/W2951232496","https://openalex.org/W2953106684","https://openalex.org/W2963351448","https://openalex.org/W2964241181","https://openalex.org/W2982770724","https://openalex.org/W2997408160","https://openalex.org/W3018757597","https://openalex.org/W3099116041","https://openalex.org/W3106250896","https://openalex.org/W3172087149","https://openalex.org/W3208645658","https://openalex.org/W3208826636","https://openalex.org/W4214507171","https://openalex.org/W4229895439","https://openalex.org/W4288325606","https://openalex.org/W4297670610","https://openalex.org/W6620707391","https://openalex.org/W6748130322","https://openalex.org/W6754988903","https://openalex.org/W6764322716","https://openalex.org/W6777046832","https://openalex.org/W6803118227"],"related_works":["https://openalex.org/W2337415362","https://openalex.org/W2007544051","https://openalex.org/W121273120","https://openalex.org/W2095705906","https://openalex.org/W2975200075","https://openalex.org/W4312857205","https://openalex.org/W2732308154","https://openalex.org/W1988485990","https://openalex.org/W3177406559","https://openalex.org/W2334336442"],"abstract_inverted_index":{"Detection":[0],"of":[1,25,85,149],"small":[2,23,67],"objects":[3,5,19],"and":[4,30,63,102,122,127,152,167,170],"far":[6],"away":[7],"in":[8,15,27,75,145,155],"the":[9,28,76,100,110,132,156],"scene":[10],"is":[11,54,73,172],"a":[12,58,140,146],"major":[13],"challenge":[14],"surveillance":[16],"applications.":[17],"Such":[18],"are":[20],"represented":[21],"by":[22,119],"number":[24],"pixels":[26],"image":[29],"lack":[31],"sufficient":[32],"details,":[33],"making":[34],"them":[35],"difficult":[36],"to":[37],"detect":[38],"using":[39,95],"conventional":[40],"detectors.":[41],"In":[42],"this":[43],"work,":[44],"an":[45],"open-source":[46],"framework":[47],"called":[48],"Slicing":[49],"Aided":[50],"Hyper":[51],"Inference":[52],"(SAHI)":[53],"proposed":[55,71,111],"that":[56,78,109],"provides":[57],"generic":[59,74],"slicing":[60,141],"aided":[61,142],"inference":[62,112],"fine-tuning":[64],"pipeline":[65],"for":[66,124],"object":[68,88,96,105,116],"detection.":[69],"The":[70],"technique":[72,160],"sense":[77],"it":[79,171],"can":[80,114,135],"be":[81,136],"applied":[82],"on":[83,99],"top":[84],"any":[86,91],"available":[87,174],"detector":[89],"without":[90],"fine-tuning.":[92],"Experimental":[93],"evaluations,":[94],"detection":[97,106,117,133],"baselines":[98],"Visdrone":[101],"xView":[103],"aerial":[104],"datasets":[107],"show":[108],"method":[113],"increase":[115,148],"AP":[118,154],"6.8%,":[120],"5.1%":[121],"5.3%":[123],"FCOS,":[125],"VFNet":[126],"TOOD":[128],"detectors,":[129],"respectively.":[130],"Moreover,":[131],"accuracy":[134],"further":[137],"increased":[138],"with":[139,164],"fine-tuning,":[143],"resulting":[144],"cumulative":[147],"12.7%,":[150],"13.4%":[151],"14.5%":[153],"same":[157],"order.":[158],"Proposed":[159],"has":[161],"been":[162],"integrated":[163],"Detectron2,":[165],"MMDetection":[166],"YOLOv5":[168],"models":[169],"publicly":[173],"at":[175],"https://github.com/obss/sahi.git":[176]},"counts_by_year":[{"year":2026,"cited_by_count":41},{"year":2025,"cited_by_count":190},{"year":2024,"cited_by_count":132},{"year":2023,"cited_by_count":79},{"year":2022,"cited_by_count":20}],"updated_date":"2026-04-06T07:47:59.780226","created_date":"2025-10-10T00:00:00"}