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.

翻译：胶囊网络已成为一类强大的深度学习架构，其以相对较少的参数实现鲁棒性能而闻名，相较于卷积神经网络（CNN）具有显著优势。然而，其固有效率常因在胶囊层间建立连接所需的缓慢迭代路由机制而受到制约，这一机制带来了计算挑战，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。该创新方法旨在降低计算复杂度的同时，保持甚至提升性能有效性。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，从而在训练过程中显著降低内存需求。我们的方法在性能上优于当前最佳的非迭代胶囊网络，并在Imagewoof数据集上进行了测试——该数据集因计算需求过高而难以被迭代方法高效处理。研究结果揭示了所提方法在提升胶囊网络运行效率与性能方面的潜力，为其在日益复杂的计算场景中的应用铺平了道路。