Capsule Networks have emerged as a powerful class of deep learning architectures, known for robust performance with relatively few parameters compared to Convolutional Neural Networks (CNNs). However, their inherent efficiency is often overshadowed by their slow, iterative routing mechanisms which establish connections between Capsule layers, posing computational challenges resulting in an inability to scale. In this paper, we introduce a novel, non-iterative routing mechanism, inspired by trainable prototype clustering. This innovative approach aims to mitigate computational complexity, while retaining, if not enhancing, performance efficacy. Furthermore, we harness a shared Capsule subspace, negating the need to project each lower-level Capsule to each higher-level Capsule, thereby significantly reducing memory requisites during training. Our approach demonstrates superior results compared to the current best non-iterative Capsule Network and tests on the Imagewoof dataset, which is too computationally demanding to handle efficiently by iterative approaches. Our findings underscore the potential of our proposed methodology in enhancing the operational efficiency and performance of Capsule Networks, paving the way for their application in increasingly complex computational scenarios. Code is available at https://github.com/mileseverett/ProtoCaps.

翻译：胶囊网络已成为一类强大的深度学习架构，其以较少的参数量实现稳健性能而著称，相较于卷积神经网络（CNN）具有明显优势。然而，其固有效率常被缓慢的迭代路由机制所掩盖——该机制负责建立胶囊层间的连接，因计算挑战导致难以扩展。本文提出一种受可训练原型聚类启发的新型非迭代路由机制。这一创新方法旨在降低计算复杂度的同时保持甚至提升性能效能。此外，我们利用共享胶囊子空间，无需将每个低层胶囊投影至每个高层胶囊，从而显著减少训练过程中的内存需求。我们的方法相较于当前最优的非迭代胶囊网络展现了更优性能，并在Imagewoof数据集上完成测试——该数据集因计算量过大而难以被迭代方法高效处理。实验结果表明，所提方法在提升胶囊网络运行效率与性能方面具有巨大潜力，为其在日益复杂的计算场景中的应用铺平道路。代码开源地址：https://github.com/mileseverett/ProtoCaps。