{"id":209837,"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00209837","sets":["1164:4619:10416:10532"]},"path":["10532"],"owner":"44499","recid":"209837","title":["深層学習モデルの判断根拠を利用した 偏りを持つデータセットに対する精度向上"],"pubdate":{"attribute_name":"公開日","attribute_value":"2021-02-25"},"_buckets":{"deposit":"af8f43b0-f147-4ca6-9597-ce12237b40fa"},"_deposit":{"id":"209837","pid":{"type":"depid","value":"209837","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"深層学習モデルの判断根拠を利用した 偏りを持つデータセットに対する精度向上","author_link":["530086","530087","530089","530088"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"深層学習モデルの判断根拠を利用した 偏りを持つデータセットに対する精度向上"},{"subitem_title":"Improving Accuracy on Biased Datasets via Explanations of Deep Neural Networks","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"セッション5-2","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2021-02-25","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":" NTT ソフトウェアイノベーションセンタ"},{"subitem_text_value":" NTT ソフトウェアイノベーションセンタ"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"Software Innovation Center, NTT","subitem_text_language":"en"},{"subitem_text_value":"Software Innovation Center, NTT","subitem_text_language":"en"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"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/209837/files/IPSJ-CVIM21225039.pdf","label":"IPSJ-CVIM21225039.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM21225039.pdf","filesize":[{"value":"2.6 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"67523048-3771-4b4d-999b-08cc1ef2ef85","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2021 by the Institute of Electronics, Information and Communication Engineers This SIG report is only available to those in membership of the SIG."}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"足立, 一樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"山口, 真弥"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Kazuki, Adachi","creatorNameLang":"en"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"Shin’ya, Yamaguchi","creatorNameLang":"en"}],"nameIdentifiers":[{}]}]},"item_4_source_id_9":{"attribute_name":"書誌レコードID","attribute_value_mlt":[{"subitem_source_identifier":"AA11131797","subitem_source_identifier_type":"NCID"}]},"item_4_textarea_12":{"attribute_name":"Notice","attribute_value_mlt":[{"subitem_textarea_value":"SIG Technical Reports are nonrefereed and hence may later appear in any journals, conferences, symposia, etc."}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourceuri":"http://purl.org/coar/resource_type/c_18gh","resourcetype":"technical report"}]},"item_4_source_id_11":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"2188-8701","subitem_source_identifier_type":"ISSN"}]},"item_4_description_7":{"attribute_name":"論文抄録","attribute_value_mlt":[{"subitem_description":"深層学習の訓練データセットは多様な特徴を持ったデータを含むことが望ましいが，実際にはタスクに無関係な特徴の偏りを持つデータセットが作られやすい．このため，タスクに関係のない特徴に偏りを持つデータセットで学習したモデルは入力データ分布の変化に対して精度が低下しやすい問題がある．本稿ではこの問題への対処を目的として，画像変換手法によるモデルが着目するべき特徴の検出と，判断根拠を活用して着目するべき特徴に対して重み付けする手法を提案する．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"Although it is desirable that training datasets for deep learning have diverse features, datasets that have biased features irrelevant to target tasks are likely to be created actually. Deep learning models trained on such biased datasets degrade its accuracy toward input distribution shift. To tackle this problem, we propose Independent Feature Focusing (IFF), the method to detect features on which models should focus and regularize its attribution to improve accuracy.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"6","bibliographic_titles":[{"bibliographic_title":"研究報告コンピュータビジョンとイメージメディア（CVIM）"}],"bibliographicPageStart":"1","bibliographicIssueDates":{"bibliographicIssueDate":"2021-02-25","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"39","bibliographicVolumeNumber":"2021-CVIM-225"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"updated":"2025-01-19T18:22:28.802470+00:00","created":"2025-01-19T01:11:07.278902+00:00","links":{}}