{"links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00229895","sets":["6504:11436:11440"]},"path":["11440"],"owner":"44499","recid":"229895","title":["レイヤー方向／チャンネル方向のアテンションに基づく畳み込みニューラルネットワークによる画像超解像"],"pubdate":{"attribute_name":"公開日","attribute_value":"2023-02-16"},"_buckets":{"deposit":"6dd94981-8fa3-482f-8c9c-b1f276ff7dd8"},"_deposit":{"id":"229895","pid":{"type":"depid","value":"229895","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"レイヤー方向／チャンネル方向のアテンションに基づく畳み込みニューラルネットワークによる画像超解像","author_link":["618431","618430"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"レイヤー方向／チャンネル方向のアテンションに基づく畳み込みニューラルネットワークによる画像超解像"}]},"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":"2023-02-16","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":"東京工科大"},{"subitem_text_value":"東京工科大"}]},"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/229895/files/IPSJ-Z85-1Q-07.pdf","label":"IPSJ-Z85-1Q-07.pdf"},"date":[{"dateType":"Available","dateValue":"2023-11-17"}],"format":"application/pdf","filename":"IPSJ-Z85-1Q-07.pdf","filesize":[{"value":"1.0 MB"}],"mimetype":"application/pdf","accessrole":"open_date","version_id":"a5ceaed7-06b7-4527-a75a-3a29a3ebd128","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2023 by the Information Processing Society of Japan"}]},"item_22_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"ユンコウ, セキ"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"青木, 輝勝"}],"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":"近年，ディープラーニングの急速な発展に伴い，画像の超解像に関する研究が飛躍的に進展している．しかし，既存のアルゴリズムでは，レイヤー特徴や高周波情報を有効に利用する機能がない．その結果，再構成された高解像度画像の品質は実用上十分なものではない．この問題を解決するために，本研究では，CADN (Channel attention Dense Network) と呼ばれる新しい超解像手法を提案する．CADNは低解像度画像から高解像度画像へのエンドツーエンドの学習マッピングをできる畳み込みニューラルネットワークネットワーク．CADNは，RDB（Residual Dense Block）とECAB（Efficient Channel Attention Block）を組み合わせたレイヤー方向のアテンションとチャンネル方向のアテンションに基づくCADB（channel attention Dense Block）に構成された．実験の結果によるとCADNは5つのデータセットで既存の手法を上回る","subitem_description_type":"Other"}]},"item_22_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"194","bibliographic_titles":[{"bibliographic_title":"第85回全国大会講演論文集"}],"bibliographicPageStart":"193","bibliographicIssueDates":{"bibliographicIssueDate":"2023-02-16","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"1","bibliographicVolumeNumber":"2023"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"created":"2025-01-19T01:29:19.915910+00:00","updated":"2025-01-19T11:22:23.710267+00:00","id":229895}