{"id":"https://openalex.org/W2768489488","doi":"https://doi.org/10.1109/cvpr.2018.00377","title":"An Analysis of Scale Invariance in Object Detection - SNIP","display_name":"An Analysis of Scale Invariance in Object Detection - SNIP","publication_year":2018,"publication_date":"2018-06-01","ids":{"openalex":"https://openalex.org/W2768489488","doi":"https://doi.org/10.1109/cvpr.2018.00377","mag":"2768489488"},"language":"en","primary_location":{"id":"doi:10.1109/cvpr.2018.00377","doi":"https://doi.org/10.1109/cvpr.2018.00377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00377","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"},"volume":null,"type":"conference-paper","is_traditional":true,"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/A5101687172","display_name":"Bharat Singh","orcid":"https://orcid.org/0000-0003-4921-5996","observed_orcids":["https://orcid.org/0000-0003-4921-5996"]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Bharat Singh","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5111454036","display_name":"Larry Steven Davis","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I66946132","display_name":"University of Maryland, College Park","ror":"https://ror.org/047s2c258","country_code":"US","type":"education","lineage":["https://openalex.org/I66946132"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Larry S. Davis","raw_affiliation_strings":["University of Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Maryland","institution_ids":["https://openalex.org/I66946132"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I66946132"],"apc_list":null,"apc_paid":null,"fwci":31.8615,"has_fulltext":false,"cited_by_count":911,"citation_normalized_percentile":{"value":0.99686897,"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":"3578","last_page":"3587"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9940999746322632,"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":0.9940999746322632,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.0032999999821186066,"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/T11605","display_name":"Visual Attention and Saliency Detection","score":0.0008999999845400453,"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/scale-invariance","display_name":"scale invariance","score":0.8859999775886536},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.984000027179718},{"id":"https://openalex.org/keywords/image-pyramid","display_name":"image pyramid","score":0.7919999957084656},{"id":"https://openalex.org/keywords/small-object-recognition","display_name":"small object recognition","score":0.6449999809265137},{"id":"https://openalex.org/keywords/convolutional-neural-networks","display_name":"convolutional neural networks","score":0.6000000238418579}],"concepts":[{"id":"https://openalex.org/C136886441","wikidata":"https://www.wikidata.org/wiki/Q926129","display_name":"Normalization (sociology)","level":2,"score":0.7381467819213867},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7302541732788086},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.6486576199531555},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.606631338596344},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.5521036982536316},{"id":"https://openalex.org/C63584917","wikidata":"https://www.wikidata.org/wiki/Q333286","display_name":"Bounding overwatch","level":2,"score":0.48919442296028137},{"id":"https://openalex.org/C147037132","wikidata":"https://www.wikidata.org/wiki/Q6865426","display_name":"Minimum bounding box","level":3,"score":0.48599156737327576},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.4850572645664215},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.47421765327453613},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.4550425112247467},{"id":"https://openalex.org/C135593079","wikidata":"https://www.wikidata.org/wiki/Q1750766","display_name":"Scale invariance","level":2,"score":0.45329540967941284},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.45325830578804016},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.45028620958328247},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.423638254404068},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4135664403438568},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1367461085319519},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.08345615863800049},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.08108004927635193},{"id":"https://openalex.org/C58640448","wikidata":"https://www.wikidata.org/wiki/Q42515","display_name":"Cartography","level":1,"score":0.07473993301391602},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C19165224","wikidata":"https://www.wikidata.org/wiki/Q23404","display_name":"Anthropology","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/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/cvpr.2018.00377","doi":"https://doi.org/10.1109/cvpr.2018.00377","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cvpr.2018.00377","pdf_url":null,"source":{"id":"https://openalex.org/S4210176548","display_name":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings","issn_l":"1063-6919","issn":["1063-6919","2332-564X","2575-7075"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-1"],"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":44,"referenced_works":["https://openalex.org/W639708223","https://openalex.org/W1536680647","https://openalex.org/W1861492603","https://openalex.org/W1932624639","https://openalex.org/W2108598243","https://openalex.org/W2109255472","https://openalex.org/W2112328181","https://openalex.org/W2117287331","https://openalex.org/W2133155955","https://openalex.org/W2145023731","https://openalex.org/W2150134853","https://openalex.org/W2151103935","https://openalex.org/W2162915993","https://openalex.org/W2163605009","https://openalex.org/W2179352600","https://openalex.org/W2194775991","https://openalex.org/W2286929393","https://openalex.org/W2288122362","https://openalex.org/W2294059674","https://openalex.org/W2322480645","https://openalex.org/W2339890635","https://openalex.org/W2407521645","https://openalex.org/W2412782625","https://openalex.org/W2474389331","https://openalex.org/W2490270993","https://openalex.org/W2530966705","https://openalex.org/W2557728737","https://openalex.org/W2565639579","https://openalex.org/W2572745118","https://openalex.org/W2579152745","https://openalex.org/W2601564443","https://openalex.org/W2743706233","https://openalex.org/W2747648373","https://openalex.org/W2752782242","https://openalex.org/W2884561390","https://openalex.org/W2963150697","https://openalex.org/W2963315052","https://openalex.org/W2963351448","https://openalex.org/W2963420686","https://openalex.org/W3106250896","https://openalex.org/W3118608800","https://openalex.org/W4394643157","https://openalex.org/W6732077511","https://openalex.org/W7099244549"],"related_works":["https://openalex.org/W2969519573","https://openalex.org/W3118578254","https://openalex.org/W3035139411","https://openalex.org/W3138977901","https://openalex.org/W2885641989","https://openalex.org/W2988452521","https://openalex.org/W2998315853","https://openalex.org/W1800922288","https://openalex.org/W7100780349","https://openalex.org/W2989294831"],"abstract_inverted_index":{"An":[0],"analysis":[1],"of":[2,22,32,39,75,111,114,120,137,143],"different":[3,30,40,115],"techniques":[4],"for":[5,43,102],"recognizing":[6],"and":[7,18,68,80,89,134,151],"detecting":[8],"objects":[9,46,82],"under":[10],"extreme":[11],"scale":[12,19],"variation":[13],"is":[14,132],"presented.":[15],"Scale":[16,100],"specific":[17],"invariant":[20],"design":[21],"detectors":[23,70],"are":[24,53,83],"compared":[25],"by":[26],"training":[27,97],"them":[28],"with":[29,154],"configurations":[31],"input":[33],"data.":[34],"By":[35],"evaluating":[36],"the":[37,72,109,121,125,161,166],"performance":[38,131],"network":[41],"architectures":[42],"classifying":[44],"small":[45,79],"on":[47,61,71],"ImageNet,":[48],"we":[49,64,93],"show":[50],"that":[51],"CNNs":[52],"not":[54],"robust":[55],"to":[56,66,85],"changes":[57],"in":[58,165],"scale.":[59,123],"Based":[60],"this":[62],"analysis,":[63],"propose":[65],"train":[67,153],"test":[69],"same":[73],"scales":[74,91],"an":[76,135,141],"image-pyramid.":[77],"Since":[78],"large":[81],"difficult":[84],"recognize":[86],"at":[87,175],"smaller":[88],"larger":[90],"respectively,":[92],"present":[94],"a":[95,118],"novel":[96],"scheme":[98],"called":[99],"Normalization":[101],"Image":[103],"Pyramids":[104],"(SNIP)":[105],"which":[106],"selectively":[107],"back-propagates":[108],"gradients":[110],"object":[112],"instances":[113],"sizes":[116],"as":[117],"function":[119],"image":[122],"On":[124],"COCO":[126,167],"dataset,":[127],"our":[128],"single":[129],"model":[130],"45.7%":[133],"ensemble":[136],"3":[138],"networks":[139],"obtains":[140],"mAP":[142],"48.3%.":[144],"We":[145],"use":[146],"off-the-shelf":[147],"ImageNet-1000":[148],"pre-trained":[149],"models":[150],"only":[152],"bounding":[155],"box":[156],"supervision.":[157],"Our":[158],"submission":[159],"won":[160],"Best":[162],"Student":[163],"Entry":[164],"2017":[168],"challenge.":[169],"Code":[170],"will":[171],"be":[172],"made":[173],"available":[174],"http://bit.ly/2yXVg4c.":[176]},"counts_by_year":[{"year":2026,"cited_by_count":51},{"year":2025,"cited_by_count":78},{"year":2024,"cited_by_count":81},{"year":2023,"cited_by_count":127},{"year":2022,"cited_by_count":139},{"year":2021,"cited_by_count":170},{"year":2020,"cited_by_count":137},{"year":2019,"cited_by_count":115},{"year":2018,"cited_by_count":13}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2017-12-04T00:00:00"}