Interactive single-image segmentation is ubiquitous in the scientific and commercial imaging software. In this work, we focus on the single-image segmentation problem only with some seeds such as scribbles. Inspired by the dynamic receptive field in the human being's visual system, we propose the Gaussian dynamic convolution (GDC) to fast and efficiently aggregate the contextual information for neural networks. The core idea is randomly selecting the spatial sampling area according to the Gaussian distribution offsets. Our GDC can be easily used as a module to build lightweight or complex segmentation networks. We adopt the proposed GDC to address the typical single-image segmentation tasks. Furthermore, we also build a Gaussian dynamic pyramid Pooling to show its potential and generality in common semantic segmentation. Experiments demonstrate that the GDC outperforms other existing convolutions on three benchmark segmentation datasets including Pascal-Context, Pascal-VOC 2012, and Cityscapes. Additional experiments are also conducted to illustrate that the GDC can produce richer and more vivid features compared with other convolutions. In general, our GDC is conducive to the convolutional neural networks to form an overall impression of the image.

翻译：在科学和商业成像软件中,互动的单一图像分割是无处不在的。 在这项工作中,我们只关注单图像分割问题,只关注一些种子,如雕刻等。在人类视觉系统中的动态接受场的启发下,我们建议高萨动态合成(GDC)快速和有效地汇总神经网络的背景资料。核心理念是根据高萨分布偏差随机选择空间取样区。我们的GDC可以很容易地用作构建轻度或复杂分化网络的模块。我们采用拟议的GDC来解决典型的单一图像分割任务。此外,我们还建了一个高萨动态金字塔组合,以展示其潜力和常态分化中的一般特性。实验表明GDC在三个基准分层数据集上(包括帕斯卡尔-康特、帕斯卡尔-VOC 2012 和城市景象)优于其他现有分层数据组(包括帕斯卡尔-康特、 帕斯卡尔- VOC 和城市景象) 。还进行了更多的实验,以说明GDC能够产生更丰富和更生的特性特征,而与整个变动的图象网络相比,GDC一般而言,它更有利于整个图象。