دورية أكاديمية
أعرض في EDS

Domain Adaptation through Photorealistic Enhanced Images for Semantic Segmentation

التفاصيل البيبلوغرافية
العنوان: Domain Adaptation through Photorealistic Enhanced Images for Semantic Segmentation
المؤلفون: Katayama, Takafumi, Song, Tian, Jiang, Xiantao, Leu, Jenq-Shiou, Shimamoto, Takashi
بيانات النشر: Hindawi
سنة النشر: 2023
المجموعة: Tokushima University Institutional Repository / 徳島大学機関リポジトリ
الوصف: In this paper, three types of domain adaptation which are defined as image-level domain adaptation, interdomain adaptation, and intradomain adaptation are efficiently combined to construct a high efficiency framework for semantic segmentation. The proposed domain adaptation platform can achieve a high reduction of time-consuming to generate exhausted supervised data in the real world using photorealistic images. The proposed framework achieved a mean Intersection-over-Union (mIoU) of 45.0%. Furthermore, by combining the proposed method with intradomain adaptation, the improvement of 1.2% mIoU is achieved compared to previous work.
نوع الوثيقة: article in journal/newspaper
اللغة: English
تدمد: 1024123X
15635147
العلاقة: http://repo.lib.tokushima-u.ac.jp/files/public/11/117837/20221213115659427792/MathProEng_2022_1848857.pdfTest; AA11947206; http://repo.lib.tokushima-u.ac.jp/117837Test
الإتاحة: http://repo.lib.tokushima-u.ac.jp/117837Test
حقوق: This is an open access article distributed under the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0Test/), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
رقم الانضمام: edsbas.34FB6F26
قاعدة البيانات: BASE
الوصف
تدمد:1024123X
15635147