{"id":"https://openalex.org/W3131576537","doi":"https://doi.org/10.5220/0010246001130122","title":"Feature Map Upscaling to Improve Scale Invariance in Convolutional Neural Networks","display_name":"Feature Map Upscaling to Improve Scale Invariance in Convolutional Neural Networks","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3131576537","doi":"https://doi.org/10.5220/0010246001130122","mag":"3131576537"},"language":"en","primary_location":{"id":"doi:10.5220/0010246001130122","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010246001130122","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.5220/0010246001130122","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5032772753","display_name":"Dinesh Kumar","orcid":"https://orcid.org/0000-0003-4693-0097"},"institutions":[{"id":"https://openalex.org/I44666525","display_name":"University of the South Pacific","ror":"https://ror.org/008stv805","country_code":"FJ","type":"education","lineage":["https://openalex.org/I44666525"]}],"countries":["FJ"],"is_corresponding":true,"raw_author_name":"Dinesh Kumar","raw_affiliation_strings":["Faculty of Science & Technology, University of the South Pacific, Laucala Bay Road, Suva, Fiji, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Faculty of Science & Technology, University of the South Pacific, Laucala Bay Road, Suva, Fiji, --- Select a Country ---","institution_ids":["https://openalex.org/I44666525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5087977913","display_name":"Dharmendra Sharma","orcid":"https://orcid.org/0000-0002-9856-4685"},"institutions":[{"id":"https://openalex.org/I188329596","display_name":"University of Canberra","ror":"https://ror.org/04s1nv328","country_code":"AU","type":"education","lineage":["https://openalex.org/I188329596"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dharmendra Sharma","raw_affiliation_strings":["Faculty of Science & Technology, University of Canberra, 11 Kirinari Street, Canberra, ACT 2617, Australia, --- Select a Country ---"],"affiliations":[{"raw_affiliation_string":"Faculty of Science & Technology, University of Canberra, 11 Kirinari Street, Canberra, ACT 2617, Australia, --- Select a Country ---","institution_ids":["https://openalex.org/I188329596"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5032772753"],"corresponding_institution_ids":["https://openalex.org/I44666525"],"apc_list":null,"apc_paid":null,"fwci":0.2526,"has_fulltext":true,"cited_by_count":3,"citation_normalized_percentile":{"value":0.55840067,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"113","last_page":"122"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9976999759674072,"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"}},"topics":[{"id":"https://openalex.org/T13114","display_name":"Image Processing Techniques and Applications","score":0.9976999759674072,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9955999851226807,"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/T11019","display_name":"Image Enhancement Techniques","score":0.9948999881744385,"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/artificial-intelligence","display_name":"Artificial intelligence","score":0.7634838819503784},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7598552703857422},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7262673377990723},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.6335061192512512},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.5860870480537415},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5723428130149841},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5544608235359192},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5157318711280823},{"id":"https://openalex.org/keywords/pyramid","display_name":"Pyramid (geometry)","score":0.46196526288986206},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.45434969663619995},{"id":"https://openalex.org/keywords/invariant","display_name":"Invariant (physics)","score":0.4440385103225708},{"id":"https://openalex.org/keywords/cognitive-neuroscience-of-visual-object-recognition","display_name":"Cognitive neuroscience of visual object recognition","score":0.4329257309436798},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.4326710104942322},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.403571218252182},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3740394711494446},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11714103817939758}],"concepts":[{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7634838819503784},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7598552703857422},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7262673377990723},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.6335061192512512},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.5860870480537415},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5723428130149841},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5544608235359192},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5157318711280823},{"id":"https://openalex.org/C142575187","wikidata":"https://www.wikidata.org/wiki/Q3358290","display_name":"Pyramid (geometry)","level":2,"score":0.46196526288986206},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.45434969663619995},{"id":"https://openalex.org/C190470478","wikidata":"https://www.wikidata.org/wiki/Q2370229","display_name":"Invariant (physics)","level":2,"score":0.4440385103225708},{"id":"https://openalex.org/C64876066","wikidata":"https://www.wikidata.org/wiki/Q5141226","display_name":"Cognitive neuroscience of visual object recognition","level":3,"score":0.4329257309436798},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4326710104942322},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.403571218252182},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3740394711494446},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11714103817939758},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.5220/0010246001130122","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010246001130122","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},{"id":"pmh:oai:generic.eprints.org:12663","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402186","display_name":"University of the South Pacific Electronic Research Repository (The University of the South Pacific)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I44666525","host_organization_name":"University of the South Pacific","host_organization_lineage":["https://openalex.org/I44666525"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"acceptedVersion","is_accepted":true,"is_published":false,"raw_source_name":"","raw_type":"Conference Proceedings"},{"id":"pmh:oai:generic.eprints.org:13824","is_oa":true,"landing_page_url":"http://repository.usp.ac.fj/13824/","pdf_url":"http://journalarticle.ukm.my/13824/1/352-Article%20Text-1318-1-10-20191214.pdf","source":{"id":"https://openalex.org/S4306401736","display_name":"UKM Journal Article Repository (Universiti Kebangsaan Malaysia)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I885383172","host_organization_name":"National University of Malaysia","host_organization_lineage":["https://openalex.org/I885383172"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Journal Article"}],"best_oa_location":{"id":"doi:10.5220/0010246001130122","is_oa":true,"landing_page_url":"https://doi.org/10.5220/0010246001130122","pdf_url":null,"source":null,"license":"cc-by-nc-nd","license_id":"https://openalex.org/licenses/cc-by-nc-nd","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W252252322","https://openalex.org/W603908379","https://openalex.org/W1800922288","https://openalex.org/W1912570122","https://openalex.org/W2112796928","https://openalex.org/W2119077463","https://openalex.org/W2246461641","https://openalex.org/W2560788656","https://openalex.org/W2565639579","https://openalex.org/W2598666589","https://openalex.org/W2748436136","https://openalex.org/W2899607431","https://openalex.org/W2902039355","https://openalex.org/W2962797416","https://openalex.org/W3011856129","https://openalex.org/W3118608800"],"related_works":["https://openalex.org/W4249847449","https://openalex.org/W44395729","https://openalex.org/W2765338038","https://openalex.org/W1496225612","https://openalex.org/W1523500768","https://openalex.org/W1566843515","https://openalex.org/W4292850564","https://openalex.org/W2181660907","https://openalex.org/W2100099236","https://openalex.org/W1575585820"],"abstract_inverted_index":{"Efforts":[0],"made":[1],"by":[2,158,199],"computer":[3],"scientists":[4],"to":[5,30,52,97,111,123,131],"model":[6,117,228],"the":[7,17,22,28,42,54,61,74,91,139,178,201,208],"visual":[8,44,62,75],"system":[9,63,76],"has":[10,20],"resulted":[11],"in":[12,34,68,102,233],"various":[13,35],"techniques":[14],"from":[15,81,134],"which":[16,186],"most":[18],"notable":[19],"been":[21],"Convolutional":[23],"Neural":[24],"Network":[25],"(CNN).":[26],"Whilst":[27],"ability":[29],"recognise":[31],"an":[32,175],"object":[33],"scales":[36,185],"is":[37,73],"a":[38,48,78,82,113,144,160,164,205],"trivial":[39],"task":[40],"for":[41,50,84,93],"human":[43],"system,":[45],"it":[46],"remains":[47],"challenge":[49],"CNNs":[51],"achieve":[53,156],"same":[55],"behaviour.":[56],"Recent":[57],"physiological":[58],"studies":[59],"reveal":[60],"uses":[64],"global-first":[65,114],"response":[66],"strategy":[67],"its":[69,85],"recognition":[70,86],"function,":[71],"that":[72,198],"processes":[77],"wider":[79],"area":[80],"scene":[83],"function.":[87],"This":[88],"theory":[89,110],"provides":[90],"potential":[92,224],"using":[94,220],"global":[95,193],"features":[96,133],"solve":[98],"transformation":[99],"invariance":[100,232],"problems":[101],"CNNs.":[103],"In":[104,129],"this":[105,109,157],"paper,":[106],"we":[107,142],"use":[108],"propose":[112],"feature":[115,146,181],"extraction":[116,147],"called":[118,149],"Stacked":[119,150],"Filter":[120,151],"CNN":[121,206,212,234],"(SFCNN)":[122],"improve":[124],"scale-invariant":[125],"classification":[126,214],"of":[127,138,166,169,183,215,226],"images.":[128,218],"SFCNN,":[130],"extract":[132],"spatially":[135],"larger":[136],"areas":[137],"target":[140],"image,":[141],"develop":[143],"trainable":[145],"layer":[148,162,203],"Convolut":[152],"ions":[153],"(SFC).":[154],"We":[155],"creating":[159],"convolution":[161],"with":[163,174],"pyramid":[165],"stacked":[167],"filters":[168],"different":[170,184],"sizes.":[171],"When":[172],"convolved":[173],"input":[176],"image":[177],"outputs":[179],"are":[180,187],"maps":[182],"then":[188],"upsampled":[189],"and":[190],"used":[191],"as":[192],"features.":[194],"Our":[195],"results":[196],"show":[197],"integrating":[200],"SFC":[202],"within":[204],"structure,":[207],"network":[209],"outperforms":[210],"traditional":[211],"on":[213],"scaled":[216],"color":[217],"Experiments":[219],"benchmark":[221],"datasets":[222],"indicate":[223],"effectiveness":[225],"our":[227],"towards":[229],"improving":[230],"scale":[231],"networks.":[235]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}