{"id":"https://openalex.org/W4402351582","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650403","title":"How image distortions affect inference accuracy","display_name":"How image distortions affect inference accuracy","publication_year":2024,"publication_date":"2024-06-30","ids":{"openalex":"https://openalex.org/W4402351582","doi":"https://doi.org/10.1109/ijcnn60899.2024.10650403"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn60899.2024.10650403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5085391982","display_name":"Petr Dvo\u0159\u00e1\u010dek","orcid":"https://orcid.org/0000-0002-5525-7706"},"institutions":[{"id":"https://openalex.org/I187293425","display_name":"University of Ostrava","ror":"https://ror.org/00pyqav47","country_code":"CZ","type":"education","lineage":["https://openalex.org/I187293425"]}],"countries":["CZ"],"is_corresponding":true,"raw_author_name":"Petr Dvo\u0159\u00e1\u010dek","raw_affiliation_strings":["University of Ostrava,Centre of Excellence IT4Innovations, Institute for Research and Applications of Fuzzy Modeling,Ostrava,Czech Republic"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Ostrava,Centre of Excellence IT4Innovations, Institute for Research and Applications of Fuzzy Modeling,Ostrava,Czech Republic","institution_ids":["https://openalex.org/I187293425"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5085391982"],"corresponding_institution_ids":["https://openalex.org/I187293425"],"apc_list":null,"apc_paid":null,"fwci":1.5353,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.82091979,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":95,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9973000288009644,"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"}},"topics":[{"id":"https://openalex.org/T12111","display_name":"Industrial Vision Systems and Defect Detection","score":0.9973000288009644,"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/T13114","display_name":"Image Processing Techniques and Applications","score":0.9947999715805054,"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":0.9898999929428101,"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/inference","display_name":"Inference","score":0.7016697525978088},{"id":"https://openalex.org/keywords/affect","display_name":"Affect (linguistics)","score":0.6646704077720642},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6265442371368408},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5565603375434875},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.4803089499473572},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.4743990898132324},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.12954115867614746}],"concepts":[{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7016697525978088},{"id":"https://openalex.org/C2776035688","wikidata":"https://www.wikidata.org/wiki/Q1606558","display_name":"Affect (linguistics)","level":2,"score":0.6646704077720642},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6265442371368408},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5565603375434875},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.4803089499473572},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.4743990898132324},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.12954115867614746},{"id":"https://openalex.org/C46312422","wikidata":"https://www.wikidata.org/wiki/Q11024","display_name":"Communication","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ijcnn60899.2024.10650403","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn60899.2024.10650403","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":39,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1673923490","https://openalex.org/W2095705004","https://openalex.org/W2108598243","https://openalex.org/W2183341477","https://openalex.org/W2746600820","https://openalex.org/W2765424254","https://openalex.org/W2908510526","https://openalex.org/W2949736877","https://openalex.org/W2962843773","https://openalex.org/W2963446712","https://openalex.org/W2963542245","https://openalex.org/W2963855133","https://openalex.org/W2963918968","https://openalex.org/W2982083293","https://openalex.org/W2990138404","https://openalex.org/W2992308087","https://openalex.org/W2998508940","https://openalex.org/W3035452548","https://openalex.org/W3035682985","https://openalex.org/W3094502228","https://openalex.org/W3103557498","https://openalex.org/W3106412272","https://openalex.org/W3138516171","https://openalex.org/W4221158957","https://openalex.org/W4288581820","https://openalex.org/W4307823382","https://openalex.org/W4312443924","https://openalex.org/W6631190155","https://openalex.org/W6637162671","https://openalex.org/W6640425456","https://openalex.org/W6674330103","https://openalex.org/W6757817989","https://openalex.org/W6758139636","https://openalex.org/W6762718338","https://openalex.org/W6766978945","https://openalex.org/W6784333009","https://openalex.org/W6788135285","https://openalex.org/W6810266835"],"related_works":["https://openalex.org/W2058170566","https://openalex.org/W2755342338","https://openalex.org/W2772917594","https://openalex.org/W2775347418","https://openalex.org/W2166024367","https://openalex.org/W3116076068","https://openalex.org/W2229312674","https://openalex.org/W2951359407","https://openalex.org/W2079911747","https://openalex.org/W1969923398"],"abstract_inverted_index":{"This":[0],"research":[1],"thoroughly":[2],"analyses":[3],"the":[4,16,50,71,84,107,128,141,153],"effects":[5],"of":[6,173],"various":[7],"image":[8,51],"distortions":[9,24],"on":[10,106],"different":[11],"neural":[12],"network":[13],"architectures,":[14],"utilizing":[15],"ImageNet":[17],"validation":[18],"dataset.":[19],"The":[20,101],"study":[21],"reveals":[22],"that":[23,155],"such":[25,81],"as":[26],"blur,":[27],"noise,":[28],"JPEG":[29],"compression,":[30],"and":[31,122,143],"grid":[32],"patterns":[33],"significantly":[34],"elevate":[35],"error":[36,46,164],"rates.":[37],"Contrast":[38],"change":[39],"yielded":[40],"inconsistent":[41],"impacts,":[42],"only":[43],"occasionally":[44],"increasing":[45],"rates,":[47,165],"while":[48],"rescaling":[49],"drastically":[52],"(when":[53],"target":[54],"size":[55],"was":[56],"more":[57,125],"than":[58,62],"five":[59],"times":[60],"smaller":[61],"original)":[63],"led":[64],"to":[65,78,96,115,127,134],"substantial":[66],"model":[67,144],"performance":[68],"degradation,":[69],"although":[70],"images":[72],"became":[73],"difficult":[74],"for":[75,169],"even":[76],"humans":[77],"recognize":[79],"at":[80],"scales.":[82],"Among":[83],"architectures":[85,118],"tested,":[86],"EfficientNet":[87],"models":[88,132,156],"demonstrated":[89],"superior":[90],"robustness,":[91],"which":[92,166],"can":[93],"be":[94,150],"attributed":[95],"their":[97],"scalable":[98],"input":[99],"sizes.":[100],"Vision":[102],"Transformer":[103],"(ViT),":[104],"trained":[105],"extensive":[108],"JFT-300M":[109],"dataset,":[110],"also":[111,149],"showcased":[112],"notable":[113],"resilience":[114],"distortions.":[116,130],"Other":[117],"like":[119],"ConvNeXt,":[120],"Swin,":[121],"ResNetD":[123],"were":[124],"susceptible":[126],"tested":[129],"MobileNetV3-based":[131],"seem":[133],"provide":[135],"an":[136],"exceptionally":[137],"good":[138],"ratio":[139],"between":[140],"robustness":[142],"size,":[145],"but":[146],"this":[147,158],"could":[148],"caused":[151],"by":[152],"fact":[154],"from":[157],"family":[159],"have":[160],"inherently":[161],"higher":[162],"base":[163],"intrinsically":[167],"allows":[168],"a":[170],"larger":[171],"margin":[172],"error.":[174]},"counts_by_year":[{"year":2025,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}