{"id":"https://openalex.org/W3196238947","doi":"https://doi.org/10.1109/access.2021.3101229","title":"Disentangled Representation Learning in Real-World Image Datasets via Image Segmentation Prior","display_name":"Disentangled Representation Learning in Real-World Image Datasets via Image Segmentation Prior","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3196238947","doi":"https://doi.org/10.1109/access.2021.3101229","mag":"3196238947"},"language":"en","primary_location":{"id":"doi:10.1109/access.2021.3101229","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3101229","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09502079.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09502079.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5003910014","display_name":"Nao Nakagawa","orcid":"https://orcid.org/0000-0001-9260-0828"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Nao Nakagawa","raw_affiliation_strings":["Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-9260-0828","affiliations":[{"raw_affiliation_string":"Graduate School of Information Science and Technology, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5002757875","display_name":"Ren Togo","orcid":"https://orcid.org/0000-0002-4474-3995"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Ren Togo","raw_affiliation_strings":["Education and Research Center for Mathematical and Data Science, Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0002-4474-3995","affiliations":[{"raw_affiliation_string":"Education and Research Center for Mathematical and Data Science, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009032240","display_name":"Takahiro Ogawa","orcid":"https://orcid.org/0000-0001-5332-8112"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Takahiro Ogawa","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0001-5332-8112","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]},{"author_position":"last","author":{"id":null,"display_name":"Miki Haseyama","orcid":"https://orcid.org/0000-0003-1496-1761"},"institutions":[{"id":"https://openalex.org/I205349734","display_name":"Hokkaido University","ror":"https://ror.org/02e16g702","country_code":"JP","type":"education","lineage":["https://openalex.org/I205349734"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Miki Haseyama","raw_affiliation_strings":["Faculty of Information Science and Technology, Hokkaido University, Sapporo, Japan"],"raw_orcid":"https://orcid.org/0000-0003-1496-1761","affiliations":[{"raw_affiliation_string":"Faculty of Information Science and Technology, Hokkaido University, Sapporo, Japan","institution_ids":["https://openalex.org/I205349734"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I205349734"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0942,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.38282223,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"9","issue":null,"first_page":"110880","last_page":"110888"},"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":0.9980000257492065,"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":0.9980000257492065,"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":0.9948999881744385,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9790999889373779,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7725591659545898},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.7194767594337463},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.6284334659576416},{"id":"https://openalex.org/keywords/image-segmentation","display_name":"Image segmentation","score":0.6109497547149658},{"id":"https://openalex.org/keywords/disjoint-sets","display_name":"Disjoint sets","score":0.5915607810020447},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5899724364280701},{"id":"https://openalex.org/keywords/encoder","display_name":"Encoder","score":0.5136113166809082},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.5024938583374023},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.4982588291168213},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4175850450992584},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.35439053177833557},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11251670122146606}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7725591659545898},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.7194767594337463},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.6284334659576416},{"id":"https://openalex.org/C124504099","wikidata":"https://www.wikidata.org/wiki/Q56933","display_name":"Image segmentation","level":3,"score":0.6109497547149658},{"id":"https://openalex.org/C45340560","wikidata":"https://www.wikidata.org/wiki/Q215382","display_name":"Disjoint sets","level":2,"score":0.5915607810020447},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5899724364280701},{"id":"https://openalex.org/C118505674","wikidata":"https://www.wikidata.org/wiki/Q42586063","display_name":"Encoder","level":2,"score":0.5136113166809082},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.5024938583374023},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.4982588291168213},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4175850450992584},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.35439053177833557},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11251670122146606},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","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}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1109/access.2021.3101229","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3101229","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09502079.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:2087e42ef295476c88fc687fd9c69887","is_oa":true,"landing_page_url":"https://doaj.org/article/2087e42ef295476c88fc687fd9c69887","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","issn_l":null,"issn":null,"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":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 9, Pp 110880-110888 (2021)","raw_type":"article"},{"id":"pmh:oai:eprints.lib.hokudai.ac.jp:2115/82697","is_oa":false,"landing_page_url":"http://hdl.handle.net/2115/82697","pdf_url":null,"source":{"id":"https://openalex.org/S4306400549","display_name":"Hokkaido University Collection of Scholarly and Academic Papers (Hokkaido University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205349734","host_organization_name":"Hokkaido University","host_organization_lineage":["https://openalex.org/I205349734"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"article"},{"id":"pmh:oai:irdb.nii.ac.jp:01364:0007195135","is_oa":false,"landing_page_url":"https://hdl.handle.net/2115/82697","pdf_url":null,"source":{"id":"https://openalex.org/S7407056385","display_name":"Institutional Repositories DataBase (IRDB)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I184597095","host_organization_name":"National Institute of Informatics","host_organization_lineage":["https://openalex.org/I184597095"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access","raw_type":"journal article"}],"best_oa_location":{"id":"doi:10.1109/access.2021.3101229","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2021.3101229","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/9312710/09502079.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"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":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[{"display_name":"Sustainable cities and communities","score":0.4699999988079071,"id":"https://metadata.un.org/sdg/11"}],"awards":[{"id":"https://openalex.org/G4515739553","display_name":"Super-MultiModal Human Analysis Platform for Next Generation of Advanced Retrieval","funder_award_id":"17H01744","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"},{"id":"https://openalex.org/G8739887802","display_name":null,"funder_award_id":"JP21H03456","funder_id":"https://openalex.org/F4320334764","funder_display_name":"Japan Society for the Promotion of Science"}],"funders":[{"id":"https://openalex.org/F4320334764","display_name":"Japan Society for the Promotion of Science","ror":"https://ror.org/00hhkn466"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3196238947.pdf","grobid_xml":"https://content.openalex.org/works/W3196238947.grobid-xml"},"referenced_works_count":74,"referenced_works":["https://openalex.org/W1834627138","https://openalex.org/W1901129140","https://openalex.org/W1959608418","https://openalex.org/W2099471712","https://openalex.org/W2138011018","https://openalex.org/W2163605009","https://openalex.org/W2163922914","https://openalex.org/W2186094539","https://openalex.org/W2237250383","https://openalex.org/W2560023338","https://openalex.org/W2591674338","https://openalex.org/W2604469346","https://openalex.org/W2753738274","https://openalex.org/W2807692250","https://openalex.org/W2903538854","https://openalex.org/W2903782687","https://openalex.org/W2904849495","https://openalex.org/W2911290044","https://openalex.org/W2913775392","https://openalex.org/W2919112510","https://openalex.org/W2948012107","https://openalex.org/W2948162522","https://openalex.org/W2950662112","https://openalex.org/W2962770929","https://openalex.org/W2962820504","https://openalex.org/W2963226019","https://openalex.org/W2963366547","https://openalex.org/W2963664914","https://openalex.org/W2963717490","https://openalex.org/W2963881378","https://openalex.org/W2964127395","https://openalex.org/W2964160479","https://openalex.org/W2970210011","https://openalex.org/W2970263573","https://openalex.org/W2970832466","https://openalex.org/W2971081162","https://openalex.org/W2971155163","https://openalex.org/W2977001478","https://openalex.org/W2981628132","https://openalex.org/W2981978388","https://openalex.org/W2996536863","https://openalex.org/W2999455429","https://openalex.org/W2999895744","https://openalex.org/W3005031238","https://openalex.org/W3005226846","https://openalex.org/W3015218297","https://openalex.org/W3034371424","https://openalex.org/W3034494316","https://openalex.org/W3035090613","https://openalex.org/W3035399978","https://openalex.org/W3035574324","https://openalex.org/W4288333413","https://openalex.org/W4293469690","https://openalex.org/W4295112158","https://openalex.org/W4320013936","https://openalex.org/W6639824700","https://openalex.org/W6640963894","https://openalex.org/W6684191040","https://openalex.org/W6718140377","https://openalex.org/W6729906282","https://openalex.org/W6734451663","https://openalex.org/W6745687250","https://openalex.org/W6748391871","https://openalex.org/W6756663807","https://openalex.org/W6757140150","https://openalex.org/W6758720093","https://openalex.org/W6758800702","https://openalex.org/W6759669191","https://openalex.org/W6765487385","https://openalex.org/W6767370287","https://openalex.org/W6767379522","https://openalex.org/W6768000218","https://openalex.org/W6769616852","https://openalex.org/W6773762762"],"related_works":["https://openalex.org/W4256429076","https://openalex.org/W1971174658","https://openalex.org/W2099195351","https://openalex.org/W2348092930","https://openalex.org/W2012063272","https://openalex.org/W3129272755","https://openalex.org/W2138685729","https://openalex.org/W2587900963","https://openalex.org/W26693340","https://openalex.org/W1522196789"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,16,95,113],"novel":[3],"method":[4,28,148],"that":[5,97,146],"can":[6],"learn":[7],"easy-to-interpret":[8],"latent":[9,105],"representations":[10],"in":[11,78],"real-world":[12,57,81,138],"image":[13,22,34,58,82,100,115,130,139],"datasets":[14,83],"using":[15,137],"VAE-based":[17],"model":[18,121],"by":[19,32,43],"splitting":[20],"an":[21,92,99,133],"into":[23,101],"several":[24],"disjoint":[25,102],"regions.":[26],"Our":[27],"performs":[29],"object-wise":[30],"disentanglement":[31,45,55,73,77,151],"exploiting":[33],"segmentation":[35,116,131],"and":[36,94,142,152],"alpha":[37],"compositing.":[38],"With":[39],"remarkable":[40],"results":[41],"obtained":[42],"unsupervised":[44],"methods":[46,62],"for":[47,56,76],"toy":[48],"datasets,":[49,140],"recent":[50],"studies":[51],"have":[52],"tackled":[53],"challenging":[54],"datasets.":[59],"However,":[60],"these":[61],"involve":[63],"deviations":[64],"from":[65],"the":[66,87],"standard":[67],"VAE":[68,88],"architecture,":[69],"which":[70,118],"has":[71],"favorable":[72],"properties.":[74],"Thus,":[75],"images":[79],"of":[80,86,104],"with":[84],"preservation":[85],"backbone,":[89],"we":[90],"designed":[91],"encoder":[93,111],"decoder":[96],"embed":[98],"sets":[103],"variables":[106],"corresponding":[107],"to":[108,122],"objects.":[109],"The":[110],"includes":[112],"pre-trained":[114],"network,":[117],"allows":[119],"our":[120,147],"focus":[123],"only":[124],"on":[125],"representation":[126],"learning":[127],"while":[128],"adopting":[129],"as":[132],"inductive":[134],"bias.":[135],"Evaluations":[136],"CelebA":[141],"Stanford":[143],"Cars,":[144],"showed":[145],"achieves":[149],"improved":[150],"transferability.":[153]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}