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.
翻译:Capsule 网络是一系列神经网络,在许多计算机视觉任务上取得了有希望的成果。然而,由于计算和记忆要求高,基准胶囊网络未能在更复杂的数据集上达到最先进的结果。我们通过提议一个新的网络结构(称为Momentum Capsule 网络(MoCapsNet))来解决这个问题。MappsNets受到Momentum ResNets的启发,这是一种使用可逆剩余建筑块的网络类型。可更新的网络允许重新计算后再分析算法中前传路的激活,因此这些记忆要求可以大幅降低。在本文中,我们将提供一个框架,说明如何将不可逆剩余建筑块应用到胶囊网络上。我们将显示,MACpsNet在使用记忆量要少得多的情况下,在MMSIS、SVHN、CIFAR-10和CIFAR-100上,比基线胶囊网络的精确度要高。源代码可以在 https://github.com/moejoe95/MoCapsNet上查阅。