This paper proposes a novel method for high-quality image segmentation of both objects and scenes. Inspired by the dilation and erosion operations in morphological image processing techniques, the pixel-level image segmentation problems are treated as squeezing object boundaries. From this perspective, a novel and efficient \textbf{Boundary Squeeze} module is proposed. This module is used to squeeze the object boundary from both inner and outer directions, which contributes to precise mask representation. A bi-directionally flow-based warping process is proposed to generate such squeezed feature representation, and two specific loss signals are designed to supervise the squeezing process. The Boundary Squeeze module can be easily applied to both instance and semantic segmentation tasks as a plug-and-play module by building on top of some existing methods. Moreover, the proposed module is light-weighted, and thus has potential for practical usage. Experiment results show that our simple yet effective design can produce high-quality results on several different datasets. Besides, several other metrics on the boundary are used to prove the effectiveness of our method over previous work. Our approach yields significant improvement on challenging COCO and Cityscapes datasets for both instance and semantic segmentation, and outperforms previous state-of-the-art PointRend in both accuracy and speed under the same setting. Codes and models will be published at \url{https://github.com/lxtGH/BSSeg}.
翻译:本文提出了一种对天体和场景进行高质量图像分割的新方法。 受形态图像处理技术中的放大和侵蚀操作的启发, 像素级图像分割问题被作为挤压对象界限处理。 从这个角度, 提出了一个新的和高效的\ textbf{Boundary Squeeze} 模块。 这个模块用于从内向和外向挤压物体边界, 这有助于精确的掩码表示。 提议了一个双向流动扭曲进程, 以产生这种挤压的特征表示, 并设计了两个具体的损失信号来监督挤压过程。 边界缩缩模件模块可以很容易地应用到实例和语系分割模块中, 以某些现有方法的顶层为基础。 此外, 拟议的模块具有轻量的重量, 因而具有实际使用的潜力。 实验结果显示, 我们简单而有效的设计可以在多个不同的数据集中产生高质量的结果。 此外, 边界上的另外几个指标被用来证明 http://cal- combregal- 方法在先前的工作中的有效性, 和Seal- sal- sal sal sal sal settal- views view 方法将带来具有挑战性。 我们在以前的工作和Sal- preal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- viewal- view view views 和 Sal- sal- sal- sal- sal- sal- sal- viewd- viewd- sal- sal- sal- viewd- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- vical- sal- sal- sal- viction- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- sal- vid- sal- sal- sal- sal- sal- sal- sal- sal- vial- sal-