{"id":"https://openalex.org/W4401908131","doi":"https://doi.org/10.1109/icdl61372.2024.10644158","title":"Ablation Study to Clarify the Mechanism of Object Segmentation in Multi-Object Representation Learning","display_name":"Ablation Study to Clarify the Mechanism of Object Segmentation in Multi-Object Representation Learning","publication_year":2024,"publication_date":"2024-05-20","ids":{"openalex":"https://openalex.org/W4401908131","doi":"https://doi.org/10.1109/icdl61372.2024.10644158"},"language":"en","primary_location":{"id":"doi:10.1109/icdl61372.2024.10644158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl61372.2024.10644158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"article","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/A5110426492","display_name":"Takayuki Komatsu","orcid":null},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":true,"raw_author_name":"Takayuki Komatsu","raw_affiliation_strings":["Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo,Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo,Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019675297","display_name":"Yoshiyuki Ohmura","orcid":"https://orcid.org/0000-0002-9158-5360"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yoshiyuki Ohmura","raw_affiliation_strings":["Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo,Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo,Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010543059","display_name":"Yasuo Kuniyoshi","orcid":"https://orcid.org/0000-0001-8443-4161"},"institutions":[{"id":"https://openalex.org/I74801974","display_name":"The University of Tokyo","ror":"https://ror.org/057zh3y96","country_code":"JP","type":"education","lineage":["https://openalex.org/I74801974"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Yasuo Kuniyoshi","raw_affiliation_strings":["Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo,Tokyo,Japan,113-8656"],"affiliations":[{"raw_affiliation_string":"Laboratory for Intelligent Systems and Informatics, Graduate School of Information Science and Technology, The University of Tokyo,Tokyo,Japan,113-8656","institution_ids":["https://openalex.org/I74801974"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5110426492"],"corresponding_institution_ids":["https://openalex.org/I74801974"],"apc_list":null,"apc_paid":null,"fwci":0.4922,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.64059086,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9998999834060669,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.9993000030517578,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9991000294685364,"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/mechanism","display_name":"Mechanism (biology)","score":0.6741774082183838},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.6572895050048828},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6544559597969055},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6403123736381531},{"id":"https://openalex.org/keywords/segmentation","display_name":"Segmentation","score":0.6285361051559448},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5570968985557556},{"id":"https://openalex.org/keywords/ablation","display_name":"Ablation","score":0.4695618450641632},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.40638452768325806},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.1310165524482727},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.061306893825531006}],"concepts":[{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.6741774082183838},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.6572895050048828},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6544559597969055},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6403123736381531},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.6285361051559448},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5570968985557556},{"id":"https://openalex.org/C2778902805","wikidata":"https://www.wikidata.org/wiki/Q322177","display_name":"Ablation","level":2,"score":0.4695618450641632},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.40638452768325806},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.1310165524482727},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.061306893825531006},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"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/C146978453","wikidata":"https://www.wikidata.org/wiki/Q3798668","display_name":"Aerospace engineering","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl61372.2024.10644158","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl61372.2024.10644158","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.46000000834465027,"id":"https://metadata.un.org/sdg/10","display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W1965555277","https://openalex.org/W2121044470","https://openalex.org/W2194775991","https://openalex.org/W2796704765","https://openalex.org/W2963150697","https://openalex.org/W2990500698","https://openalex.org/W3037784242","https://openalex.org/W4235169531","https://openalex.org/W4252684946","https://openalex.org/W4285704217","https://openalex.org/W4287758375","https://openalex.org/W4295246696","https://openalex.org/W4295312788","https://openalex.org/W4380635116","https://openalex.org/W6640963894","https://openalex.org/W6750852989","https://openalex.org/W6758420182","https://openalex.org/W6759669191","https://openalex.org/W6766312635","https://openalex.org/W6766978945","https://openalex.org/W6772619266","https://openalex.org/W6779809370","https://openalex.org/W6779889584","https://openalex.org/W6791489083","https://openalex.org/W6793805516"],"related_works":["https://openalex.org/W2913786724","https://openalex.org/W2357783023","https://openalex.org/W2013863777","https://openalex.org/W2118389769","https://openalex.org/W4394573179","https://openalex.org/W2382997850","https://openalex.org/W2390968135","https://openalex.org/W3020408180","https://openalex.org/W2917979353","https://openalex.org/W1834370135"],"abstract_inverted_index":{"The":[0],"goal":[1],"of":[2,25,52,78,91,116],"multi-object":[3,79,105],"representation":[4,17,80,106,152],"learning":[5,18,24,107],"is":[6,62,66,132,147,174],"to":[7,74],"represent":[8],"a":[9,179,192],"visual":[10],"input":[11,28],"that":[12,72,139,172,176],"contains":[13],"multiple":[14,183],"objects.":[15],"Multi-object":[16],"methods":[19,42],"have":[20,43],"adopted":[21],"simultaneous":[22],"unsupervised":[23],"segmenting":[26],"an":[27],"image":[29,49],"into":[30,37],"individual":[31],"objects":[32,36],"and":[33,55,69,94,120,159],"encoding":[34],"these":[35],"each":[38,127],"latent":[39,53,184],"vector.":[40],"Previous":[41],"combined":[44],"many":[45],"techniques,":[46],"such":[47],"as":[48,113,200],"reconstruction,":[50],"regularization":[51,143],"vectors,":[54],"other":[56,161],"auxiliary":[57],"loss":[58,101,128,144,194],"functions.":[59],"Therefore,":[60],"it":[61,173],"not":[63,155],"clear":[64],"what":[65],"the":[67,75,89,96,100,104,114,117,122,140,160,197,201],"essential":[68],"simple":[70],"mechanism":[71,90,181,199],"contributes":[73],"appropriate":[76],"behavior":[77],"learning.":[81],"In":[82],"this":[83,168,188],"study,":[84],"we":[85,170],"focused":[86],"on":[87,99,167],"elucidating":[88],"object":[92,123,151],"segmentation":[93,124,157],"conducted":[95],"ablation":[97,118],"study":[98,119],"functions":[102],"in":[103,130],"method.":[108],"We":[109,186],"employed":[110],"MONet":[111,131],"[1]":[112],"target":[115],"evaluated":[121],"performance":[125,158],"when":[126],"function":[129,195],"removed":[133],"or":[134],"replaced.":[135],"Our":[136],"results":[137],"showed":[138],"Variational":[141],"Autoencoder":[142],"[2],":[145],"which":[146],"used":[148],"for":[149],"single":[150],"learning,":[153],"did":[154,163],"affect":[156,164],"losses":[162],"it.":[165],"Based":[166],"result,":[169],"hypothesized":[171],"important":[175],"there":[177],"exists":[178],"winner-take-all":[180],"among":[182],"vectors.":[185],"confirmed":[187],"hypothesis":[189],"by":[190],"evaluating":[191],"new":[193],"with":[196],"same":[198],"hypothesis.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1}],"updated_date":"2026-04-07T14:57:38.498316","created_date":"2025-10-10T00:00:00"}