{"id":235902,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00235902","sets":["6504:11678:11689"]},"path":["11689"],"owner":"44499","recid":"235902","title":["Self-Supervised Pre-training of Vision Transformers Using Stable Diffusion-Generated Images"],"pubdate":{"attribute_name":"公開日","attribute_value":"2024-03-01"},"_buckets":{"deposit":"2ad21256-1e0b-4cbd-a8cb-0aa1d6f2024c"},"_deposit":{"id":"235902","pid":{"type":"depid","value":"235902","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"Self-Supervised Pre-training of Vision Transformers Using Stable Diffusion-Generated Images","author_link":["644673","644672"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"Self-Supervised Pre-training of Vision Transformers Using Stable Diffusion-Generated Images"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"人工知能と認知科学","subitem_subject_scheme":"Other"}]},"item_type_id":"22","publish_date":"2024-03-01","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"eng"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"創価大"},{"subitem_text_value":"創価大"}]},"item_publisher":{"attribute_name":"出版者","attribute_value_mlt":[{"subitem_publisher":"情報処理学会","subitem_publisher_language":"ja"}]},"publish_status":"0","weko_shared_id":-1,"item_file_price":{"attribute_name":"Billing file","attribute_type":"file","attribute_value_mlt":[{"url":{"url":"https://ipsj.ixsq.nii.ac.jp/record/235902/files/IPSJ-Z86-7C-06.pdf","label":"IPSJ-Z86-7C-06.pdf"},"date":[{"dateType":"Available","dateValue":"2024-07-03"}],"format":"application/pdf","filename":"IPSJ-Z86-7C-06.pdf","filesize":[{"value":"916.3 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"2b674192-40b8-4223-ad93-3db96f0085c7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2024 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"ルイス, モルミレ"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"渥美, 雅保"}],"nameIdentifiers":[{}]}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_5794","resourcetype":"conference paper"}]},"item_22_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AN00349328","subitem_source_identifier_type":"NCID"}]},"item_22_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"Traditional dataset building involves time-consuming tasks such as web scraping, cleaning, and labeling. Our proposed method utilizes a fast stable diffusion technique to efficiently generate synthetic images from text prompts, eliminating the need for manual data collection while mitigating biases and mislabeling. We conduct experiments with a vision transformer, comparing models trained on real datasets, datasets enhanced with synthetic images, and fully synthetic datasets. The results showcase the efficacy of stable diffusion-synthesized images in enhancing model generalization and accuracy, highlighting the potential of this approach in the realm of computer vision.","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"112","bibliographic_titles":[{"bibliographic_title":"第86回全国大会講演論文集"}],"bibliographicPageStart":"111","bibliographicIssueDates":{"bibliographicIssueDate":"2024-03-01","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2024"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T09:28:23.120342+00:00","created":"2025-01-19T01:37:39.407118+00:00","links":{}}