# An Improved Capsule Network for Image Classification Using Multi-Scale Feature Extraction

## TL;DR

This paper introduces an improved capsule network with multi-scale feature extraction to enhance image classification performance and reduce overfitting.

## Contribution

The novel contribution is a modified capsule network with a multi-scale feature extraction module and additional optimizations for better performance.

## Key findings

- The enhanced capsule network achieved high classification accuracy on CIFAR-10, CIFAR-100, and CUB datasets.
- It also achieved 98.21% and 95.38% accuracy on the ISIC and Forged Face EXP datasets.
- The network's modifications improved generalization and reduced overfitting compared to standard capsule networks.

## Abstract

In the realm of image classification, the capsule network is a network topology that packs the extracted features into many capsules, performs sophisticated capsule screening using a dynamic routing mechanism, and finally recognizes that each capsule corresponds to a category feature. Compared with previous network topologies, the capsule network has more sophisticated operations, uses a large number of parameter matrices and vectors to express picture attributes, and has more powerful image classification capabilities. However, in the practical application field, the capsule network has always been constrained by the quantity of calculation produced by the complicated structure. In the face of basic datasets, it is prone to over-fitting and poor generalization and often cannot satisfy the high computational overhead when facing complex datasets. Based on the aforesaid problems, this research proposes a novel enhanced capsule network topology. The upgraded network boosts the feature extraction ability of the network by incorporating a multi-scale feature extraction module based on proprietary star structure convolution into the standard capsule network. At the same time, additional structural portions of the capsule network are changed, and a variety of optimization approaches such as dense connection, attention mechanism, and low-rank matrix operation are combined. Image classification studies are carried out on different datasets, and the novel structure suggested in this paper has good classification performance on CIFAR-10, CIFAR-100, and CUB datasets. At the same time, we also achieved 98.21% and 95.38% classification accuracy on two complicated datasets of skin cancer ISIC derived and Forged Face EXP.