Joint coarse-and-fine semantic segmentation

Yi Cheng Chiu, Chih Yang Lin, Timothy Shih

研究成果: 書貢獻/報告類型會議論文篇章同行評審

1 引文 斯高帕斯(Scopus)

摘要

The issue of image semantic segmentation is renowned within computer vision and artificial intelligence. The ground truth in image segmentation is hard to produce and is time- and resource-intensive. Recent research on realtime image semantic segmentation based on deep learning has reduced image resolution through pooling operations, resulting in detail loss in the scene. In order to generate high-quality annotated data, in this paper, we propose a joint coarse-and-fine (JCF) architecture that can repair fragment defects based on a coarse module, and also produce fine details based on a fine module. The experiments show promising results compared to state-of-the-art methods.

原文???core.languages.en_GB???
主出版物標題2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019
發行者Institute of Electrical and Electronics Engineers Inc.
ISBN(電子)9781728109909
DOIs
出版狀態已出版 - 9月 2019
事件16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019 - Taipei, Taiwan
持續時間: 18 9月 201921 9月 2019

出版系列

名字2019 16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???16th IEEE International Conference on Advanced Video and Signal Based Surveillance, AVSS 2019
國家/地區Taiwan
城市Taipei
期間18/09/1921/09/19

指紋

深入研究「Joint coarse-and-fine semantic segmentation」主題。共同形成了獨特的指紋。

引用此