{"id":"https://openalex.org/W3130193634","doi":"https://doi.org/10.1109/icassp39728.2021.9414627","title":"How Convolutional Neural Networks Deal with Aliasing","display_name":"How Convolutional Neural Networks Deal with Aliasing","publication_year":2021,"publication_date":"2021-05-13","ids":{"openalex":"https://openalex.org/W3130193634","doi":"https://doi.org/10.1109/icassp39728.2021.9414627","mag":"3130193634"},"language":"en","primary_location":{"id":"doi:10.1109/icassp39728.2021.9414627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2102.07757","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5000836300","display_name":"Ant\u00f4nio H. Ribeiro","orcid":"https://orcid.org/0000-0003-3632-8529"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]},{"id":"https://openalex.org/I123387679","display_name":"Uppsala University","ror":"https://ror.org/048a87296","country_code":"SE","type":"education","lineage":["https://openalex.org/I123387679"]}],"countries":["BR","SE"],"is_corresponding":true,"raw_author_name":"Antonio H. Ribeiro","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Brazil","Uppsala University, Sweden","Universidade Federal de Minas Gerais,Department of Computer Science,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Uppsala University, Sweden","institution_ids":["https://openalex.org/I123387679"]},{"raw_affiliation_string":"Universidade Federal de Minas Gerais,Department of Computer Science,Brazil","institution_ids":["https://openalex.org/I110200422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083090794","display_name":"Thomas B. Sch\u00f6n","orcid":"https://orcid.org/0000-0001-5183-234X"},"institutions":[{"id":"https://openalex.org/I110200422","display_name":"Universidade Federal de Minas Gerais","ror":"https://ror.org/0176yjw32","country_code":"BR","type":"education","lineage":["https://openalex.org/I110200422"]}],"countries":["BR"],"is_corresponding":false,"raw_author_name":"Thomas B. Schon","raw_affiliation_strings":["Universidade Federal de Minas Gerais, Brazil","Universidade Federal de Minas Gerais,Department of Computer Science,Brazil"],"affiliations":[{"raw_affiliation_string":"Universidade Federal de Minas Gerais, Brazil","institution_ids":["https://openalex.org/I110200422"]},{"raw_affiliation_string":"Universidade Federal de Minas Gerais,Department of Computer Science,Brazil","institution_ids":["https://openalex.org/I110200422"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5000836300"],"corresponding_institution_ids":["https://openalex.org/I110200422","https://openalex.org/I123387679"],"apc_list":null,"apc_paid":null,"fwci":0.20443896,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.45621497,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"2755","last_page":"2759"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10688","display_name":"Image and Signal Denoising Methods","score":0.9991999864578247,"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/T10688","display_name":"Image and Signal Denoising Methods","score":0.9991999864578247,"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":0.9979000091552734,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9968000054359436,"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/computer-science","display_name":"Computer science","score":0.7693191170692444},{"id":"https://openalex.org/keywords/upsampling","display_name":"Upsampling","score":0.724091649055481},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.7188924551010132},{"id":"https://openalex.org/keywords/aliasing","display_name":"Aliasing","score":0.7104855179786682},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5510372519493103},{"id":"https://openalex.org/keywords/pooling","display_name":"Pooling","score":0.5507767796516418},{"id":"https://openalex.org/keywords/anti-aliasing","display_name":"Anti-aliasing","score":0.49959731101989746},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.48319923877716064},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.43850621581077576},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3746604323387146},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.3311256766319275},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.26393982768058777},{"id":"https://openalex.org/keywords/undersampling","display_name":"Undersampling","score":0.11586740612983704}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7693191170692444},{"id":"https://openalex.org/C110384440","wikidata":"https://www.wikidata.org/wiki/Q1143270","display_name":"Upsampling","level":3,"score":0.724091649055481},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.7188924551010132},{"id":"https://openalex.org/C4069607","wikidata":"https://www.wikidata.org/wiki/Q868732","display_name":"Aliasing","level":3,"score":0.7104855179786682},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5510372519493103},{"id":"https://openalex.org/C70437156","wikidata":"https://www.wikidata.org/wiki/Q7228652","display_name":"Pooling","level":2,"score":0.5507767796516418},{"id":"https://openalex.org/C534633266","wikidata":"https://www.wikidata.org/wiki/Q4774317","display_name":"Anti-aliasing","level":5,"score":0.49959731101989746},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.48319923877716064},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.43850621581077576},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3746604323387146},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.3311256766319275},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.26393982768058777},{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.11586740612983704},{"id":"https://openalex.org/C13895895","wikidata":"https://www.wikidata.org/wiki/Q3270773","display_name":"Speech coding","level":2,"score":0.0},{"id":"https://openalex.org/C64922751","wikidata":"https://www.wikidata.org/wiki/Q4650799","display_name":"Audio signal","level":3,"score":0.0},{"id":"https://openalex.org/C127220857","wikidata":"https://www.wikidata.org/wiki/Q2719318","display_name":"Audio signal processing","level":4,"score":0.0}],"mesh":[],"locations_count":5,"locations":[{"id":"doi:10.1109/icassp39728.2021.9414627","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icassp39728.2021.9414627","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2102.07757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.07757","pdf_url":"https://arxiv.org/pdf/2102.07757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},{"id":"mag:3130193634","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2102.07757","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2102.07757","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2102.07757","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"},{"id":"doi:10.17023/vetj-yg30","is_oa":true,"landing_page_url":"https://doi.org/10.17023/vetj-yg30","pdf_url":null,"source":{"id":"https://openalex.org/S7407051697","display_name":"IEEE RESOURCE CENTERS","issn_l":null,"issn":[],"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":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2102.07757","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2102.07757","pdf_url":"https://arxiv.org/pdf/2102.07757","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3130193634.pdf","grobid_xml":"https://content.openalex.org/works/W3130193634.grobid-xml"},"referenced_works_count":28,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1523493493","https://openalex.org/W2129131372","https://openalex.org/W2134120396","https://openalex.org/W2162363099","https://openalex.org/W2163605009","https://openalex.org/W2177153902","https://openalex.org/W2194775991","https://openalex.org/W2296616510","https://openalex.org/W2889424860","https://openalex.org/W2913314773","https://openalex.org/W2937918341","https://openalex.org/W2963248464","https://openalex.org/W2964253222","https://openalex.org/W2970971581","https://openalex.org/W2996904338","https://openalex.org/W3107291594","https://openalex.org/W3126857817","https://openalex.org/W4250955649","https://openalex.org/W6631190155","https://openalex.org/W6684191040","https://openalex.org/W6739868092","https://openalex.org/W6751831877","https://openalex.org/W6758857762","https://openalex.org/W6761673875","https://openalex.org/W6766978945","https://openalex.org/W6781848295","https://openalex.org/W6786277304"],"related_works":["https://openalex.org/W3163065207","https://openalex.org/W3204615985","https://openalex.org/W3209677189","https://openalex.org/W2913314773","https://openalex.org/W2272036301","https://openalex.org/W3107291594","https://openalex.org/W2159498728","https://openalex.org/W2807007689","https://openalex.org/W2797622827","https://openalex.org/W3014257411","https://openalex.org/W3109195399","https://openalex.org/W2796876546","https://openalex.org/W2786054724","https://openalex.org/W3128448487","https://openalex.org/W2805548887","https://openalex.org/W3024735542","https://openalex.org/W2964850033","https://openalex.org/W2962949867","https://openalex.org/W3142114057","https://openalex.org/W2920348561"],"abstract_inverted_index":{"The":[0,104],"convolutional":[1,15],"neural":[2],"network":[3],"(CNN)":[4],"remains":[5],"an":[6,156,170],"essential":[7],"tool":[8],"in":[9,58,63,66,80,110,151,159,175,189],"solving":[10],"computer":[11],"vision":[12],"problems.":[13],"Standard":[14],"architectures":[16],"consist":[17],"of":[18,21,33,43,88,130,141,178],"stacked":[19],"layers":[20,61],"operations":[22],"that":[23,35,74,96,148,169],"progressively":[24],"downscale":[25],"the":[26,44,59,64,85,126,134,138,145,149,152,162,165,190],"image.":[27],"Aliasing":[28],"is":[29,70,92,113],"a":[30],"well-known":[31],"side-effect":[32],"downsampling":[34,55],"may":[36],"take":[37],"place:":[38],"it":[39,91],"causes":[40],"high-frequency":[41],"components":[42],"original":[45],"signal":[46],"to":[47,84,94,108,117],"become":[48],"indistinguishable":[49],"from":[50,77,186],"its":[51],"low-frequency":[52],"components.":[53],"While":[54],"takes":[56],"place":[57,79,188],"max-pooling":[60],"or":[62],"strided-convolutions":[65],"these":[67,81,89],"models,":[68,90],"there":[69],"no":[71],"explicit":[72],"mechanism":[73],"prevents":[75],"aliasing":[76,185],"taking":[78,187],"layers.":[82,192],"Due":[83],"impressive":[86],"performance":[87],"natural":[93],"suspect":[95],"they,":[97],"somehow,":[98],"implicitly":[99],"deal":[100],"with":[101],"this":[102,111],"distortion.":[103],"question":[105,127],"we":[106,136,167],"aim":[107],"answer":[109],"paper":[112],"simply:":[114],"\"how":[115],"and":[116],"what":[118],"extent":[119],"do":[120],"CNNs":[121,139],"counteract":[122],"aliasing?\"":[123],"We":[124],"explore":[125],"by":[128],"means":[129],"two":[131],"examples:":[132],"In":[133,164],"first,":[135],"assess":[137],"capability":[140],"distinguishing":[142],"oscillations":[143],"at":[144,161],"input,":[146],"showing":[147],"redundancies":[150],"intermediate":[153,191],"channels":[154],"play":[155],"important":[157],"role":[158],"succeeding":[160],"task;":[163],"second,":[166],"show":[168],"image":[171],"classifier":[172],"CNN":[173],"while,":[174],"principle,":[176],"capable":[177],"implementing":[179],"anti-aliasing":[180],"filters,":[181],"does":[182],"not":[183],"prevent":[184]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}