DL-CapsNet: A Deep and Light Capsule Network

TL;DR

DL-CapsNet is a deep, efficient capsule network variant that achieves high accuracy with fewer parameters, enabling faster training and inference on complex, multi-category datasets.

Contribution

We introduce DL-CapsNet, a deep capsule network with a novel Capsule Summarization layer that reduces complexity and enhances performance.

Findings

High accuracy on complex datasets

Fewer parameters than traditional CapsNet

Faster training and inference

Abstract

Capsule Network (CapsNet) is among the promising classifiers and a possible successor of the classifiers built based on Convolutional Neural Network (CNN). CapsNet is more accurate than CNNs in detecting images with overlapping categories and those with applied affine transformations. In this work, we propose a deep variant of CapsNet consisting of several capsule layers. In addition, we design the Capsule Summarization layer to reduce the complexity by reducing the number of parameters. DL-CapsNet, while being highly accurate, employs a small number of parameters and delivers faster training and inference. DL-CapsNet can process complex datasets with a high number of categories.