PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation | |
Xiangtai, Li5; Hao, He3,4; Xia, Li1; Duo, Li2; Guangliang, Cheng6,7; Jianping, Shi6,8; Lubin, Weng4; Yunhai, Tong5; Zhouchen, Lin5 | |
2021-06 | |
会议日期 | 2021-6-19 -> 2021-6-25 |
会议地点 | 线上会议 |
关键词 | Semantic Segmentation Aerial Image Segmentation |
页码 | 4217-4226 |
英文摘要 | Aerial Image Segmentation is a particular semantic segmentation problem and has several challenging characteristics that general semantic segmentation does not have. There are two critical issues: The one is an extremely foreground-background imbalanced distribution, and the other is multiple small objects along with the complex background. Such problems make the recent dense affinity context modeling perform poorly even compared with baselines due to over-introduced background context. To handle these problems, we propose a point-wise affinity propagation module based on the Feature Pyramid Network (FPN) framework, named PointFlow. Rather than dense affinity learning, a sparse affinity map is generated upon selected points between the adjacent features, which reduces the noise introduced by the background while keeping efficiency. In particular, we design a dual point matcher to select points from the salient area and object boundaries, respectively. Experimental results on three different aerial segmentation datasets suggest that the proposed method is more effective and efficient than state-of-the-art general semantic segmentation methods. Especially, our methods achieve the best speed and accuracy trade-off on three aerial benchmarks. Further experiments on three general semantic segmentation datasets prove the generality of our method. |
语种 | 英语 |
内容类型 | 会议论文 |
源URL | [http://ir.ia.ac.cn/handle/173211/48653] |
专题 | 自动化研究所_模式识别国家重点实验室_遥感图像处理团队 |
通讯作者 | Guangliang, Cheng; Yunhai, Tong |
作者单位 | 1.ETH Zurich 2.HKUST 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.NLPR, Institute of Automation, Chinese Academy of Sciences 5.Key Laboratory of Machine Perception (MOE), Peking University 6.SenseTime Research 7.Shanghai AI Laboratory 8.Qing Yuan Research Institute, SJTU |
推荐引用方式 GB/T 7714 | Xiangtai, Li,Hao, He,Xia, Li,et al. PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation[C]. 见:. 线上会议. 2021-6-19 -> 2021-6-25. |
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