Path Capsule Networks
Path Capsule Networks
复制标题
DOI：
10.1007/s11063-020-10273-0
复制
发表时间：
2019-02
影响因子：
3.1
通讯作者：
Mohammed Amer;T. Maul
中科院分区：
文献类型：
--
作者：
Mohammed Amer;T. Maul
胶囊网络（CapsNet）作为卷积神经网络的增强，通过姿态估计来补充卷积神经网络的不变性和等方差。CapsNet通过较浅的架构和显著减少的参数数量取得了非常不错的性能。然而，CapsNet中第一层的宽度仍然影响着它的大量参数，而浅度可能会限制胶囊的表示能力。为了解决这些限制，我们介绍了路径胶囊网络（PathCapsNet），这是CapsNet的深度并行多路径版本。我们表明，深度、最大池化、DropCircuit正则化和新的协议路由技术的明智协调可以获得比CapsNet更好或相当的结果，同时进一步显著减少参数计数。
Capsule network (CapsNet) was introduced as an enhancement over convolutional neural networks, supplementing the latter’s invariance properties with equivariance through pose estimation. CapsNet achieved a very decent performance with a shallow architecture and a significant reduction in parameters count. However, the width of the first layer in CapsNet is still contributing to a significant number of its parameters and the shallowness may be limiting the representational power of the capsules. To address these limitations, we introduce Path Capsule Network (PathCapsNet), a deep parallel multi-path version of CapsNet. We show that a judicious coordination of depth, max-pooling, regularization by DropCircuit and a new fan-in routing by agreement technique can achieve better or comparable results to CapsNet, while further reducing the parameter count significantly.