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. Code will be provided in (https: //github.com/lxtGH/PFSegNets).
翻译:空心图像分割是一个特殊的语义分割问题, 并且具有若干具有挑战性的特点, 一般语义分割没有产生。 有两个关键问题 : 一个问题是一个极强的地表- 地表背景分布不均, 另一个问题是一个与复杂背景一起的多小天体。 这些问题使得最近密度稠密的亲近环境建模与基准相比表现不佳, 与过度引入的背景背景背景的基线相比也是如此。 为了处理这些问题, 我们提议了一个基于地貌相近网络( FPFN) 框架, 名为 PointFlow 的点和亲近性传播模块。 我们的方法不是密集的亲近性学习, 而是在相邻地物特征之间的选定点上绘制一个稀薄的亲近性地图, 减少背景带来的噪音, 同时保持效率。 特别是, 我们设计了一个双点匹配器, 分别从显要区和对象边界选择点。 三个不同的空中分割数据集的实验结果表明, 拟议的方法比州际一般语系分割法方法更有效和高效。 特别是, 我们的方法在三种航空基准中达到最佳速度和精确的贸易/ 。 标准 。 。