Knowledge Commons of Institute of Automation,CAS
PointFlow: Flowing Semantics Through Points for Aerial Image Segmentation | |
Xiangtai, Li1; Hao, He2,3![]() ![]() | |
2021-06 | |
会议名称 | Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) |
页码 | 4217-4226 |
会议日期 | 2021-6-19 -> 2021-6-25 |
会议地点 | 线上会议 |
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. |
关键词 | Semantic Segmentation Aerial Image Segmentation |
收录类别 | EI |
语种 | 英语 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/48653 |
专题 | 多模态人工智能系统全国重点实验室_先进时空数据分析与学习 |
通讯作者 | Guangliang, Cheng; Yunhai, Tong |
作者单位 | 1.Key Laboratory of Machine Perception (MOE), Peking University 2.NLPR, Institute of Automation, Chinese Academy of Sciences 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.ETH Zurich 5.HKUST 6.SenseTime Research 7.Qing Yuan Research Institute, SJTU 8.Shanghai AI Laboratory |
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],2021:4217-4226. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
PointFlow.pdf(2430KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
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