{"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00205204","sets":["6504:10247:10254"]},"path":["10254"],"owner":"6748","recid":"205204","title":["ニューロンセグメンテーションにおけるマルチドメイン学習による汎化性能の改善"],"pubdate":{"attribute_name":"公開日","attribute_value":"2020-02-20"},"_buckets":{"deposit":"18db9508-b109-4431-ab5d-69a02dbd5f22"},"_deposit":{"id":"205204","pid":{"type":"depid","value":"205204","revision_id":0},"owners":[6748],"status":"published","created_by":6748},"item_title":"ニューロンセグメンテーションにおけるマルチドメイン学習による汎化性能の改善","author_link":["509048","509049","509047","509051","509050"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"ニューロンセグメンテーションにおけるマルチドメイン学習による汎化性能の改善"}]},"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":"2020-02-20","item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_22_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"神戸大"},{"subitem_text_value":"神戸大"},{"subitem_text_value":"神戸大"},{"subitem_text_value":"神戸大"},{"subitem_text_value":"神戸大"}]},"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/205204/files/IPSJ-Z82-2Q-07.pdf","label":"IPSJ-Z82-2Q-07.pdf"},"date":[{"dateType":"Available","dateValue":"2020-06-19"}],"format":"application/pdf","filename":"IPSJ-Z82-2Q-07.pdf","filesize":[{"value":"598.0 kB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"cf486185-0ed2-4e4c-a911-f1dd4fd1db9c","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2020 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"長谷川, 貴大"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Tristan, Hascoet"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"高島, 遼一"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"滝口, 哲也"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"有木, 康雄"}],"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":"脳全体における神経回路のマッピングの研究であるコネクトミクスにおいて、脳の電子顕微鏡画像から各ニューロンを識別することが重要である。深層学習によるニューロンの自動セグメンテーションに際して、データの取得にもアノテーションにも多大なコストがかかるため、転移学習をさせることが有力な選択肢の1つとなる。本稿では、U-Netと呼ばれる深層学習モデルを用いて、複数のドメインの公開データセットで学習させたモデルの汎化性能を検討した。また、それによって、目標となるドメインのデータセットでの転移学習のコストを低減させつつ、精度を向上させることを試みた。","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"170","bibliographic_titles":[{"bibliographic_title":"第82回全国大会講演論文集"}],"bibliographicPageStart":"169","bibliographicIssueDates":{"bibliographicIssueDate":"2020-02-20","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2020"}]},"relation_version_is_last":true,"weko_creator_id":"6748"},"id":205204,"updated":"2025-01-19T19:51:54.685625+00:00","links":{},"created":"2025-01-19T01:07:22.403450+00:00"}