# Advanced Capsule Networks via Context Awareness

## TL;DR

This paper enhances Capsule Networks by integrating context-aware pooling and reconstruction layers, demonstrating comparable accuracy to deep learning models with significantly reduced training time on an ASL dataset.

## Contribution

The paper introduces improved Capsule Network architecture with context-aware pooling and reconstruction, and compares its performance and training efficiency against established deep learning models.

## Key findings

- Capsule Networks perform comparably to DL models on ASL dataset.
- Enhanced CN architecture reduces training time significantly.
- Demonstration provided for practical illustration.

## Abstract

Capsule Networks (CN) offer new architectures for Deep Learning (DL) community. Though its effectiveness has been demonstrated in MNIST and smallNORB datasets, the networks still face challenges in other datasets for images with distinct contexts. In this research, we improve the design of CN (Vector version) namely we expand more Pooling layers to filter image backgrounds and increase Reconstruction layers to make better image restoration. Additionally, we perform experiments to compare accuracy and speed of CN versus DL models. In DL models, we utilize Inception V3 and DenseNet V201 for powerful computers besides NASNet, MobileNet V1 and MobileNet V2 for small and embedded devices. We evaluate our models on a fingerspelling alphabet dataset from American Sign Language (ASL). The results show that CNs perform comparably to DL models while dramatically reducing training time. We also make a demonstration and give a link for the purpose of illustration.