CardioCaps: Attention-based Capsule Network for Class-Imbalanced Echocardiogram Classification

arXiv:2403.09108v1 Announce Type: new
Abstract: Capsule Neural Networks (CapsNets) is a novel architecture that utilizes vector-wise representations formed by multiple neurons. Specifically, the Dynamic Routing CapsNets (DR-CapsNets) employ an affine matrix and dynamic routing mechanism to train capsules and acquire translation-equivariance properties, enhancing its robustness compared to traditional Convolutional Neural Networks (CNNs). Echocardiograms, which capture moving images of the heart, present unique challenges for traditional image classification methods. In this paper, we explore the potential of DR-CapsNets and propose CardioCaps, …

abstract architecture arxiv attention capsule class classification cnns convolutional neural networks cs.cv dynamic matrix multiple network networks neural networks neurons novel robustness routing train translation type vector wise