https://scholars.lib.ntu.edu.tw/handle/123456789/581300
標題: | MamboNet: Adversarial Semantic Segmentation for Autonomous Driving | 作者: | Liu J.-L Tsai A Fuh C.-S Huang F. CHIOU-SHANN FUH |
關鍵字: | Semantics; Adversarial networks; Autonomous driving; Contextual relationships; Ground truth data; Initial segmentation; Quantitative evaluation; Semantic segmentation; Spatial continuity; Autonomous vehicles | 公開日期: | 2021 | 卷: | 1386 CCIS | 起(迄)頁: | 354-362 | 來源出版物: | Communications in Computer and Information Science | 摘要: | Environment semantic maps provide essential information for autonomous vehicles to navigate in complex road scenarios. In this paper, an adversarial network to complement the conventional encoder-decoder semantic segmentation network is introduced. A newly proposed adversarial discriminator is piggybacked to the segmentation network, which is used to improve the spatial continuity and label consistency in a scene without explicitly specifying the contextual relationships. The segmentation network itself serves as a generator to produce an initial segmentation map (pixel-wise labels). The discriminator then takes the labels and compare them with the ground truth data to further update the generator in order to enhance the accuracy of the labeling result. Quantitative evaluations were conducted which show significant improvement on spatial continuity. ? 2021, Springer Nature Switzerland AG. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85104873031&doi=10.1007%2f978-3-030-72073-5_27&partnerID=40&md5=ef181a5887c9b6c581584f549eed89bb https://scholars.lib.ntu.edu.tw/handle/123456789/581300 |
ISSN: | 18650929 | DOI: | 10.1007/978-3-030-72073-5_27 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。