论文标题
通过蜂窝自动机进行图像分割
Image segmentation via Cellular Automata
论文作者
论文摘要
在本文中，我们提出了一种构建细胞自动机的新方法，以解决现实世界的分割问题。我们设计和训练一个可以成功分割高分辨率图像的蜂窝自动机。我们认为一个菌落密集地居住在像素网格中，并且所有单元格受到随机更新的控制，该更新使用了当前状态，颜色和$ 3 \ times 3 $邻域的状态。可能的规则空间由小型神经网络定义。更新规则与大量随机子集并行反复应用，并在收敛后生成分割掩码，然后将其反向传播以使用标准梯度下降方法学习最佳更新规则。我们证明，只有有限的轨迹长度就可以有效地学习此类模型，并且它们显示出非常出色的组织信息的能力，仅使用局部信息交换，以产生全球一致的分割结果。从实际的角度来看，我们的方法使我们能够构建非常有效的模型 - 我们最小的自动机使用少于10,000个参数来求解复杂的分割任务。
In this paper, we propose a new approach for building cellular automata to solve real-world segmentation problems. We design and train a cellular automaton that can successfully segment high-resolution images. We consider a colony that densely inhabits the pixel grid, and all cells are governed by a randomized update that uses the current state, the color, and the state of the $3\times 3$ neighborhood. The space of possible rules is defined by a small neural network. The update rule is applied repeatedly in parallel to a large random subset of cells and after convergence is used to produce segmentation masks that are then back-propagated to learn the optimal update rules using standard gradient descent methods. We demonstrate that such models can be learned efficiently with only limited trajectory length and that they show remarkable ability to organize the information to produce a globally consistent segmentation result, using only local information exchange. From a practical perspective, our approach allows us to build very efficient models -- our smallest automaton uses less than 10,000 parameters to solve complex segmentation tasks.
