{"created":"2025-01-19T01:18:16.571964+00:00","updated":"2025-01-19T15:21:32.225194+00:00","metadata":{"_oai":{"id":"oai:ipsj.ixsq.nii.ac.jp:00217848","sets":["1164:4619:10826:10925"]},"path":["10925"],"owner":"44499","recid":"217848","title":["レイヤーとアテンションを追加したYOLO-v4による小さな目標に頑健な物体検出"],"pubdate":{"attribute_name":"公開日","attribute_value":"2022-05-05"},"_buckets":{"deposit":"0c9464ce-ce52-40ab-a1ce-bd69cda5526c"},"_deposit":{"id":"217848","pid":{"type":"depid","value":"217848","revision_id":0},"owners":[44499],"status":"published","created_by":44499},"item_title":"レイヤーとアテンションを追加したYOLO-v4による小さな目標に頑健な物体検出","author_link":["565185","565186"],"item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"レイヤーとアテンションを追加したYOLO-v4による小さな目標に頑健な物体検出"},{"subitem_title":"Robust Small Objects Detection Using YOLO-v4 with attention and Layer","subitem_title_language":"en"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"一般講演セッション1 ","subitem_subject_scheme":"Other"}]},"item_type_id":"4","publish_date":"2022-05-05","item_4_text_3":{"attribute_name":"著者所属","attribute_value_mlt":[{"subitem_text_value":"中央大学理工学研究科"}]},"item_4_text_4":{"attribute_name":"著者所属(英)","attribute_value_mlt":[{"subitem_text_value":"The Graduate School of Science and Engineering,Chuo University","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/217848/files/IPSJ-CVIM22230035.pdf","label":"IPSJ-CVIM22230035.pdf"},"format":"application/pdf","billing":["billing_file"],"filename":"IPSJ-CVIM22230035.pdf","filesize":[{"value":"1.4 MB"}],"mimetype":"application/pdf","priceinfo":[{"tax":["include_tax"],"price":"0","billingrole":"20"},{"tax":["include_tax"],"price":"0","billingrole":"44"}],"accessrole":"open_login","version_id":"750dbc28-8007-4eb5-a62e-6129dfad7fc7","displaytype":"detail","licensetype":"license_note","license_note":"Copyright (c) 2022 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":"李, 越東"}],"nameIdentifiers":[{}]}]},"item_4_creator_6":{"attribute_name":"著者名(英)","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"Li, Yuedong","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":"リモートセンシングは元々，従来の深層学習モデルでよく用いられるようなオブジェクト検出や分類のためではないだろう．著者は従来の YOLOv4 ネットワーク構造に基づいて，小さな目標に対する 104＊104 の特徴検出層を追加し，csSE モジュールを追加し，活性化関数は LeakyRelu を MISH 関数に設定されることで，衛星画像中の小さな目標の検出能力を向上させることがわかった．結果は，DIOR データセットで mAP@0.5 は約 9.12％ の改善が見られた．","subitem_description_type":"Other"}]},"item_4_description_8":{"attribute_name":"論文抄録(英)","attribute_value_mlt":[{"subitem_description":"It is a difficult problem how to make traditional neural network algorithm show good adaptability to the typical target detection of remote sensing image in the field of remote sensing. In probing the latest YOLOv4 core idea, network structure and algorithm, the network structure is firstly improved by adding 104×104 feature layer scale and embedding csSE module. Then, use the Mish activation function to replace the original activation function Leaky ReLU to obtain better generalization, and the typical target detection algorithm performance of YOLOv4 is improved for remote sensing image. Finally, it is verified by designing contrast experiment. The results showed that the mAP@0.5 both increased by 9.12% on the DIOR test set.","subitem_description_type":"Other"}]},"item_4_biblio_info_10":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicPageEnd":"5","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":"2022-05-05","bibliographicIssueDateType":"Issued"},"bibliographicIssueNumber":"35","bibliographicVolumeNumber":"2022-CVIM-230"}]},"relation_version_is_last":true,"weko_creator_id":"44499"},"id":217848,"links":{}}