{"id":"https://openalex.org/W3000640486","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207431","title":"Improving Image Autoencoder Embeddings with Perceptual Loss","display_name":"Improving Image Autoencoder Embeddings with Perceptual Loss","publication_year":2020,"publication_date":"2020-07-01","ids":{"openalex":"https://openalex.org/W3000640486","doi":"https://doi.org/10.1109/ijcnn48605.2020.9207431","mag":"3000640486"},"language":"en","primary_location":{"id":"doi:10.1109/ijcnn48605.2020.9207431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","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/2001.03444","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5008391614","display_name":"Gustav Grund Pihlgren","orcid":"https://orcid.org/0000-0003-0100-4030"},"institutions":[{"id":"https://openalex.org/I190632392","display_name":"Lule\u00e5 University of Technology","ror":"https://ror.org/016st3p78","country_code":"SE","type":"education","lineage":["https://openalex.org/I190632392"]}],"countries":["SE"],"is_corresponding":true,"raw_author_name":"Gustav Grund Pihlgren","raw_affiliation_strings":["EISLAB Machine Learning, Lule\u00e5 University of Technology, Lule\u00e5, Sweden","Lule\u00e5 University of Technology"],"affiliations":[{"raw_affiliation_string":"EISLAB Machine Learning, Lule\u00e5 University of Technology, Lule\u00e5, Sweden","institution_ids":["https://openalex.org/I190632392"]},{"raw_affiliation_string":"Lule\u00e5 University of Technology","institution_ids":["https://openalex.org/I190632392"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072244112","display_name":"Fredrik Sandin","orcid":"https://orcid.org/0000-0001-5662-825X"},"institutions":[{"id":"https://openalex.org/I190632392","display_name":"Lule\u00e5 University of Technology","ror":"https://ror.org/016st3p78","country_code":"SE","type":"education","lineage":["https://openalex.org/I190632392"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Fredrik Sandin","raw_affiliation_strings":["EISLAB Machine Learning, Lule\u00e5 University of Technology, Lule\u00e5, Sweden","Lule\u00e5 University of Technology"],"affiliations":[{"raw_affiliation_string":"EISLAB Machine Learning, Lule\u00e5 University of Technology, Lule\u00e5, Sweden","institution_ids":["https://openalex.org/I190632392"]},{"raw_affiliation_string":"Lule\u00e5 University of Technology","institution_ids":["https://openalex.org/I190632392"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073619925","display_name":"Marcus Liwicki","orcid":"https://orcid.org/0000-0003-4029-6574"},"institutions":[{"id":"https://openalex.org/I190632392","display_name":"Lule\u00e5 University of Technology","ror":"https://ror.org/016st3p78","country_code":"SE","type":"education","lineage":["https://openalex.org/I190632392"]}],"countries":["SE"],"is_corresponding":false,"raw_author_name":"Marcus Liwicki","raw_affiliation_strings":["EISLAB Machine Learning, Lule\u00e5 University of Technology, Lule\u00e5, Sweden","Lule\u00e5 University of Technology"],"affiliations":[{"raw_affiliation_string":"EISLAB Machine Learning, Lule\u00e5 University of Technology, Lule\u00e5, Sweden","institution_ids":["https://openalex.org/I190632392"]},{"raw_affiliation_string":"Lule\u00e5 University of Technology","institution_ids":["https://openalex.org/I190632392"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008391614"],"corresponding_institution_ids":["https://openalex.org/I190632392"],"apc_list":null,"apc_paid":null,"fwci":0.83973854,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.73187603,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9995999932289124,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.9995999932289124,"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/T11105","display_name":"Advanced Image Processing Techniques","score":0.9987999796867371,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9962999820709229,"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/autoencoder","display_name":"Autoencoder","score":0.8053145408630371},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7551885843276978},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7066162824630737},{"id":"https://openalex.org/keywords/feature","display_name":"Feature (linguistics)","score":0.5920436382293701},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5842468738555908},{"id":"https://openalex.org/keywords/perception","display_name":"Perception","score":0.5711936950683594},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.5138819217681885},{"id":"https://openalex.org/keywords/perspective","display_name":"Perspective (graphical)","score":0.5124895572662354},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.48433053493499756},{"id":"https://openalex.org/keywords/pixel","display_name":"Pixel","score":0.4670525789260864},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.44647374749183655},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.3661308288574219},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.32417505979537964}],"concepts":[{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.8053145408630371},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7551885843276978},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7066162824630737},{"id":"https://openalex.org/C2776401178","wikidata":"https://www.wikidata.org/wiki/Q12050496","display_name":"Feature (linguistics)","level":2,"score":0.5920436382293701},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5842468738555908},{"id":"https://openalex.org/C26760741","wikidata":"https://www.wikidata.org/wiki/Q160402","display_name":"Perception","level":2,"score":0.5711936950683594},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.5138819217681885},{"id":"https://openalex.org/C12713177","wikidata":"https://www.wikidata.org/wiki/Q1900281","display_name":"Perspective (graphical)","level":2,"score":0.5124895572662354},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.48433053493499756},{"id":"https://openalex.org/C160633673","wikidata":"https://www.wikidata.org/wiki/Q355198","display_name":"Pixel","level":2,"score":0.4670525789260864},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.44647374749183655},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.3661308288574219},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.32417505979537964},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C169760540","wikidata":"https://www.wikidata.org/wiki/Q207011","display_name":"Neuroscience","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/ijcnn48605.2020.9207431","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ijcnn48605.2020.9207431","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 International Joint Conference on Neural Networks (IJCNN)","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2001.03444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.03444","pdf_url":"https://arxiv.org/pdf/2001.03444","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":"","raw_type":"text"},{"id":"mag:3000640486","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2001.03444.pdf","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.2001.03444","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2001.03444","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":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2001.03444","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2001.03444","pdf_url":"https://arxiv.org/pdf/2001.03444","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":"","raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":47,"referenced_works":["https://openalex.org/W117096852","https://openalex.org/W1598866093","https://openalex.org/W1825675169","https://openalex.org/W1876967670","https://openalex.org/W1959608418","https://openalex.org/W1965555277","https://openalex.org/W2025768430","https://openalex.org/W2099471712","https://openalex.org/W2108598243","https://openalex.org/W2118858186","https://openalex.org/W2163605009","https://openalex.org/W2172174689","https://openalex.org/W2331128040","https://openalex.org/W2335728318","https://openalex.org/W2561050497","https://openalex.org/W2625219738","https://openalex.org/W2766736793","https://openalex.org/W2772628703","https://openalex.org/W2774385398","https://openalex.org/W2804047946","https://openalex.org/W2890208753","https://openalex.org/W2943865428","https://openalex.org/W2962851944","https://openalex.org/W2963174698","https://openalex.org/W2963270775","https://openalex.org/W2963676163","https://openalex.org/W2964167449","https://openalex.org/W2978506536","https://openalex.org/W3037207827","https://openalex.org/W6604803494","https://openalex.org/W6635810480","https://openalex.org/W6638389677","https://openalex.org/W6640963894","https://openalex.org/W6677919164","https://openalex.org/W6684191040","https://openalex.org/W6684753728","https://openalex.org/W6685133223","https://openalex.org/W6687506355","https://openalex.org/W6692550842","https://openalex.org/W6703116779","https://openalex.org/W6730493023","https://openalex.org/W6733974131","https://openalex.org/W6746342343","https://openalex.org/W6751795773","https://openalex.org/W6754184789","https://openalex.org/W6762913911","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W3010954243","https://openalex.org/W2099471712","https://openalex.org/W2952102627","https://openalex.org/W2901383445","https://openalex.org/W2888022311","https://openalex.org/W2145094598","https://openalex.org/W193255932","https://openalex.org/W2558661413","https://openalex.org/W2765371849","https://openalex.org/W3092201749","https://openalex.org/W2175711684","https://openalex.org/W3137606981","https://openalex.org/W3033806859","https://openalex.org/W2980280361","https://openalex.org/W3080294851","https://openalex.org/W3119773509","https://openalex.org/W3104195492","https://openalex.org/W2526782364","https://openalex.org/W2096422372","https://openalex.org/W2898779401"],"abstract_inverted_index":{"Autoencoders":[0,54],"are":[1,55,84,106],"commonly":[2],"trained":[3,56,85,119,134,144],"using":[4,66],"element-wise":[5,8,146],"loss.":[6,41,78,147],"However,":[7],"loss":[9,46,68,137,164],"disregards":[10],"high-level":[11],"structures":[12],"in":[13,125],"the":[14,37,48,93,96,111,117,126,129,149,154,167],"image":[15,127],"which":[16],"can":[17,165],"lead":[18],"to":[19,29,57,86],"embeddings":[20,52,115,130],"that":[21,31],"disregard":[22],"them":[23],"as":[24,74,76,99],"well.":[25],"A":[26,79],"recent":[27],"improvement":[28],"autoencoders":[30,133],"helps":[32],"alleviate":[33],"this":[34],"problem":[35],"is":[36,176],"use":[38],"of":[39,50,81,104,156,159],"perceptual":[40,45,67,136,163],"This":[42],"work":[43],"investigates":[44],"from":[47,60,116],"perspective":[49],"encoder":[51],"themselves.":[53],"embed":[58],"images":[59,98],"three":[61],"different":[62,82],"computer":[63],"vision":[64],"datasets":[65,94],"based":[69],"on":[70,92,153],"a":[71,160,170],"pretrained":[72],"model":[73],"well":[75],"pixel-wise":[77],"host":[80],"predictors":[83,112],"perform":[87],"object":[88,157],"positioning":[89,158],"and":[90],"classification":[91],"given":[95],"embedded":[97],"input.":[100],"The":[101,121,173],"two":[102],"kinds":[103],"losses":[105],"evaluated":[107],"by":[108,132,169],"comparing":[109],"how":[110],"performed":[113],"with":[114,135,145],"differently":[118],"autoencoders.":[120],"results":[122,150,168],"show":[123,151],"that,":[124,152],"domain,":[128],"generated":[131],"enable":[138],"more":[139],"accurate":[140],"predictions":[141],"than":[142],"those":[143],"Furthermore,":[148],"task":[155],"small-scale":[161],"feature,":[162],"improve":[166],"factor":[171],"10.":[172],"experimental":[174],"setup":[175],"available":[177],"online:":[178],"https://github.com/guspih/Perceptual-Autoencoders":[179]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":5}],"updated_date":"2026-02-09T09:26:11.010843","created_date":"2025-10-10T00:00:00"}