论文标题
动量胶囊网络
Momentum Capsule Networks
论文作者
论文摘要
胶囊网络是一类神经网络，可在许多计算机视觉任务上取得有希望的结果。但是，由于高度计算和内存要求，基线胶囊网络未能在更复杂的数据集上达到最新结果。我们通过提出一个新的网络体系结构来解决这个问题，称为动量胶囊网络（Mocapsnet）。 Mocapsnets的灵感来自动量Resnets，这是一种应用可逆残留构件的网络。可逆的网络允许重新计算向反向传播算法中正向通行的激活，因此可以大大减少这些内存要求。在本文中，我们提供了一个框架，介绍如何将可逆的残留构建块应用于胶囊网络。我们将表明，Mocapsnet在MNIST，SVHN，CIFAR-10和CIFAR-100上击败了基线胶囊网络的准确性，同时使用的内存较少。源代码可在https://github.com/moejoe95/mocapsnet上找到。
Capsule networks are a class of neural networks that achieved promising results on many computer vision tasks. However, baseline capsule networks have failed to reach state-of-the-art results on more complex datasets due to the high computation and memory requirements. We tackle this problem by proposing a new network architecture, called Momentum Capsule Network (MoCapsNet). MoCapsNets are inspired by Momentum ResNets, a type of network that applies reversible residual building blocks. Reversible networks allow for recalculating activations of the forward pass in the backpropagation algorithm, so those memory requirements can be drastically reduced. In this paper, we provide a framework on how invertible residual building blocks can be applied to capsule networks. We will show that MoCapsNet beats the accuracy of baseline capsule networks on MNIST, SVHN, CIFAR-10 and CIFAR-100 while using considerably less memory. The source code is available on https://github.com/moejoe95/MoCapsNet.
