LE-CapsNet: A Light and Enhanced Capsule Network

TL;DR

LE-CapsNet is a lightweight, faster, and more accurate capsule network variant that improves image recognition and robustness to transformations, addressing CapsNet's speed and resource limitations.

Contribution

We introduce LE-CapsNet, a novel, resource-efficient capsule network that enhances accuracy and inference speed over traditional CapsNet.

Findings

Achieves 76.73% accuracy on CIFAR-10 with 4x faster inference.

Attains 94.3% accuracy on AffNIST, outperforming CapsNet.

Reduces resource consumption while improving robustness.

Abstract

Capsule Network (CapsNet) classifier has several advantages over CNNs, including better detection of images containing overlapping categories and higher accuracy on transformed images. Despite the advantages, CapsNet is slow due to its different structure. In addition, CapsNet is resource-hungry, includes many parameters and lags in accuracy compared to CNNs. In this work, we propose LE-CapsNet as a light, enhanced and more accurate variant of CapsNet. Using 3.8M weights, LECapsNet obtains 76.73% accuracy on the CIFAR-10 dataset while performing inference 4x faster than CapsNet. In addition, our proposed network is more robust at detecting images with affine transformations compared to CapsNet. We achieve 94.3% accuracy on the AffNIST dataset (compared to CapsNet 90.52%).