论文标题
Wasserstein路由胶囊网络
Wasserstein Routed Capsule Networks
论文作者
论文摘要
胶囊网络提供了有趣的属性，并为当今的深神经网络体系结构提供了替代方案。但是，最近的方法未能始终如一地在不同的图像数据集中取得竞争成果。我们提出了一个新的参数有效的胶囊体系结构，可以通过使用具有近似Wasestein物镜的神经网络来解决复杂的任务，以在整个架构中动态选择胶囊。这种方法着重于实施强大的路由方案，该方案可以使用几乎没有开销来提供改进的结果。我们进行了几项验证所提出概念的消融研究，并表明我们的网络能够使用较少的参数在CIFAR-10上实质上超过1.2％的其他胶囊方法。
Capsule networks offer interesting properties and provide an alternative to today's deep neural network architectures. However, recent approaches have failed to consistently achieve competitive results across different image datasets. We propose a new parameter efficient capsule architecture, that is able to tackle complex tasks by using neural networks trained with an approximate Wasserstein objective to dynamically select capsules throughout the entire architecture. This approach focuses on implementing a robust routing scheme, which can deliver improved results using little overhead. We perform several ablation studies verifying the proposed concepts and show that our network is able to substantially outperform other capsule approaches by over 1.2 % on CIFAR-10, using fewer parameters.
