Capsule networks use routing algorithms to flow information between consecutive layers. In the existing routing procedures, capsules produce predictions (termed votes) for capsules of the next layer. In a nutshell, the next-layer capsule’s input is a weighted sum over all the votes it receives. In this paper, we propose non-iterative cluster routing for capsule networks. In the proposed cluster routing, capsules produce vote clusters instead of individual votes for next-layer capsules, and each vote cluster sends its centroid to a next-layer capsule. Generally speaking, the next-layer capsule’s input is a weighted sum over the centroid of each vote cluster it receives. The centroid that comes from a cluster with a smaller variance is assigned a larger weight in the weighted sum process. Compared with the state-of-the-art capsule networks, the proposed capsule networks achieve the best accuracy on the Fashion-MNIST and SVHN datasets with fewer parameters, and achieve the best accuracy on the smallNORB and CIFAR-10 datasets with a moderate number of parameters. The proposed capsule networks also produce capsules with disentangled representation and generalize well to images captured at novel viewpoints. The proposed capsule networks also preserve 2D spatial information of an input image in the capsule channels: if the capsule channels are rotated, the object reconstructed from these channels will be rotated by the same transformation.

胶囊网络使用路由算法在连续层之间传输信息。在现有的路由过程中，胶囊为下一层的胶囊生成预测（称为投票）。简而言之，下一层胶囊的输入是它收到的所有投票的加权和。在本文中，我们提出了胶囊网络的非迭代集群路由。在提议的集群路由中，胶囊为下一层胶囊生成投票集群而不是个人投票，并且每个投票集群将其质心发送到下一层胶囊。一般来说，下一层胶囊的输入是它接收到的每个投票簇的质心的加权和。来自方差较小的簇的质心在加权求和过程中被分配较大的权重。与最先进的胶囊网络相比，所提出的胶囊网络在参数较少的 Fashion-MNIST 和 SVHN 数据集上实现了最佳精度，并在参数数量适中的 smallNORB 和 CIFAR-10 数据集上实现了最佳精度。所提出的胶囊网络还产生具有解缠结表示的胶囊，并且可以很好地泛化到在新视点捕获的图像。所提出的胶囊网络还将输入图像的二维空间信息保存在胶囊通道中：如果胶囊通道旋转，则从这些通道重建的对象将通过相同的变换旋转。所提出的胶囊网络还产生具有解缠结表示的胶囊，并且可以很好地泛化到在新视点捕获的图像。所提出的胶囊网络还将输入图像的二维空间信息保存在胶囊通道中：如果胶囊通道旋转，则从这些通道重建的对象将通过相同的变换旋转。所提出的胶囊网络还产生具有解缠结表示的胶囊，并且可以很好地泛化到在新视点捕获的图像。所提出的胶囊网络还将输入图像的二维空间信息保存在胶囊通道中：如果胶囊通道旋转，则从这些通道重建的对象将通过相同的变换旋转。