Key points are not available for this paper at this time.
Capsule networks (CapsNets) have been known difficult to develop a deeper architecture, which is desirable for high performance in the deep learning era, due to the complex capsule routing algorithms. In this article, we present a simple yet effective capsule routing algorithm, which is presented by a residual pose routing. Specifically, the higher-layer capsule pose is achieved by an identity mapping on the adjacently lower-layer capsule pose. Such simple residual pose routing has two advantages: 1) reducing the routing computation complexity and 2) avoiding gradient vanishing due to its residual learning framework. On top of that, we explicitly reformulate the capsule layers by building a residual pose block. Stacking multiple such blocks results in a deep residual CapsNets (ResCaps) with a ResNet-like architecture. Results on MNIST, AffNIST, SmallNORB, and CIFAR-10/100 show the effectiveness of ResCaps for image classification. Furthermore, we successfully extend our residual pose routing to large-scale real-world applications, including 3-D object reconstruction and classification, and 2-D saliency dense prediction. The source code has been released on https://github.com/liuyi1989/ResCaps.
Building similarity graph...
Analyzing shared references across papers
Loading...
Yi Liu
De Cheng
Dingwen Zhang
IEEE Transactions on Neural Networks and Learning Systems
University of Sheffield
Northwestern Polytechnical University
Xidian University
Building similarity graph...
Analyzing shared references across papers
Loading...
Liu et al. (Tue,) studied this question.
www.synapsesocial.com/papers/6a0eee071c5e2d2319fa1add — DOI: https://doi.org/10.1109/tnnls.2023.3347722
Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context: