Densely Cascaded Shadow Detection Network via Deeply Supervised Parallel Fusion | |
Wang, Yupei; Zhao, Xin; Li, Yin; Hu, Xuecai; Huang, Kaiqi | |
2019 | |
会议日期 | July 13-19 2018 |
会议地点 | Stockholm, Sweden |
英文摘要 | Shadow detection is an important and challenging problem in computer vision. Recently, single image shadow detection had achieved major progress with the development of deep convolutional networks. However, existing methods are still vulnerable to background clutters, and often fail to capture the global context of an input image. These global contextual and semantic cues are essential for accurately localizing the shadow regions. Moreover, rich spatial details are required to segment shadow regions with precise shape. To this end, this paper presents a novel model characterized by a deeply supervised parallel fusion (DSPF) network and a densely cascaded learning scheme. The DSPF network achieves a comprehensive fusion of global semantic cues and local spatial details by multiple stacked parallel fusion branches, which are learned in a deeply supervised manner. Moreover, the densely cascaded learning scheme is employed to refine the spatial details. Our method is evaluated on two widely used shadow detection benchmarks. Experimental results show that our method outperforms state-of-the-arts by a large margin. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/23351] |
专题 | 中国科学院自动化研究所 |
作者单位 | 1.Institute of Automation, Chinese Academy of Sciences 2.University of Chinese Academy of Sciences |
推荐引用方式 GB/T 7714 | Wang, Yupei,Zhao, Xin,Li, Yin,et al. Densely Cascaded Shadow Detection Network via Deeply Supervised Parallel Fusion[C]. 见:. Stockholm, Sweden. July 13-19 2018. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论