{"updated":"2025-01-19T23:17:39.118874+00:00","links":{},"metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00194905","sets":["1164:4619:9659:9737"]},"path":["9737"],"owner":"44499","recid":"194905","title":["人と協調する半自己学習に基づく衛星画像上の地物検出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2019-02-28"},"_buckets":{"deposit":"a8a25bc8-88f7-4f04-bba0-399aac8f533a"},"_deposit":{"id":"194905","pid":{"type":"depid","value":"194905","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"人と協調する半自己学習に基づく衛星画像上の地物検出","author_link":["462609","462611","462610","462608"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"人と協調する半自己学習に基づく衛星画像上の地物検出"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般セッション","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2019-02-28","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"国立研究開発法人産業技術総合研究所人工知能研究センター"},{"subitem_text_value":"国立研究開発法人産業技術総合研究所人工知能研究センター"},{"subitem_text_value":"国立研究開発法人産業技術総合研究所人工知能研究センター"},{"subitem_text_value":"国立研究開発法人産業技術総合研究所人工知能研究センター"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)","subitem_text_language":"en"},{"subitem_text_value":"National Institute of Advanced Industrial Science and Technology (AIST)","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/194905/files/IPSJ-CVIM19216009.pdf","label":"IPSJ-CVIM19216009.pdf"},"date":[{"dateType":"Available","dateValue":"2021-02-28"}],"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM19216009.pdf","filesize":[{"value":"393.5 kB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"660","billingrole":"5"},{"tax":["include_tax"],"price":"330","billingrole":"6"},{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_date","version_id":"9983c09e-8b12-4c2d-a550-66b32d710950","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2019 by the Information Processing Society of Japan"}]},"item_4_creator_5":{"attribute_name":"著者名","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"上原, 和樹"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"野里, 博和"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"村川, 正宏"}],"nameIdentifiers":[{}]},{"creatorNames":[{"creatorName":"坂無, 英徳"}],"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":"衛星画像上の地物検出において，畳み込みニューラルネットワーク （CNN） は非常に有効である．しかしながら，リモートセンシングの領域においては，専門性やコストの観点から CNN を学習するのに十分なデータセットを用意することが困難である．そこで本研究では，限られたデータセットで CNN を効率よく学習するために，半自己学習手法を提案する．これは，半教師あり学習の一つである self-training 法を活用し，ユーザと協調しながらラベル付きデータを収集し，自己学習により学習効率を向上する手法である．衛星画像を用いた地物検出タスクに適用したところ，提案手法はすべてのデータを用いて学習した CNN と同等の性能を約 18% のデータ量で得ることができた．","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":"2019-02-28","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"9","bibliographicVolumeNumber":"2019-CVIM-216"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":194905,"created":"2025-01-19T00:59:55.742001+00:00"}