Box-supervised instance segmentation has recently attracted lots of research efforts while little attention is received in aerial image domain. In contrast to the general object collections, aerial objects have large intra-class variances and inter-class similarity with complex background. Moreover, there are many tiny objects in the high-resolution satellite images. This makes the recent pairwise affinity modeling method inevitably to involve the noisy supervision with the inferior results. To tackle these problems, we propose a novel aerial instance segmentation approach, which drives the network to learn a series of level set functions for the aerial objects with only box annotations in an end-to-end fashion. Instead of learning the pairwise affinity, the level set method with the carefully designed energy functions treats the object segmentation as curve evolution, which is able to accurately recover the object's boundaries and prevent the interference from the indistinguishable background and similar objects. The experimental results demonstrate that the proposed approach outperforms the state-of-the-art box-supervised instance segmentation methods. The source code is available at https://github.com/LiWentomng/boxlevelset.
翻译:框监督的图像分割最近吸引了许多研究努力,而在空中图像域却很少引起注意。 与一般物体收藏相比, 航空物体具有很大的类内差异和类别间相似性, 并且背景复杂。 此外, 高分辨率卫星图像中有许多细小的物体。 这使得最近的对称相似性模型方法不可避免地会涉及杂乱的监视和下等结果。 为了解决这些问题, 我们提议了一种新的航空实例分割方法, 它将驱动网络学习空中物体的一系列定级功能, 并且只有端到端的框说明。 使用精心设计的能源函数的定级方法, 而不是学习对等近性, 将对象分割作为曲线演化处理, 从而能够准确恢复物体的边界, 并防止来自无法分辨的背景和类似对象的干扰。 实验结果显示, 拟议的方法超越了状态的艺术框监督实例分割方法。 源代码可在 https://github.com/LiWentomng/boxset 上查阅 。