DeepCaps+: A Light Variant of DeepCaps

Pouya Shiri, Amirali Baniasadi

2023

Abstract

Image classification is one of the fundamental problems in the field of computer vision. Convolutional Neural Networks (CNN) are complex feed-forward neural networks that represent outstanding solutions for this problem. Capsule Network (CapsNet) is considered as the next generation of classifiers based on Convolutional Neural Networks. Despite its advantages including higher robustness to affine transformations, CapsNet does not perform well on complex data. Several works have tried to realize the true potential of CapsNet to provide better performance. DeepCaps is one of such networks with significantly improved performance. Despite its better performance on complex datasets such as CIFAR-10, DeepCaps fails to work on more complex datasets with a higher number of categories such as CIFAR-100. In this network, we introduce DeepCaps+ as an optimized variant of DeepCaps which includes fewer parameters and higher accuracy. Using a 7-ensemble model on the CIFAR-10 dataset, DeepCaps+ obtains a an accuracy of 91.63% while performing the inference 2.51x faster than DeepCaps. DeepCaps+ also obtains 67.56% test accuracy on the CIFAR-100 dataset, proving this network to be capable of handling complex datasets.

Paper Citation

in Harvard Style

Shiri P. and Baniasadi A. (2023). DeepCaps+: A Light Variant of DeepCaps. In Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP; ISBN 978-989-758-634-7, SciTePress, pages 212-220. DOI: 10.5220/0011728100003417

in Bibtex Style

@conference{visapp23,
author={Pouya Shiri and Amirali Baniasadi},
title={DeepCaps+: A Light Variant of DeepCaps},
booktitle={Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP},
year={2023},
pages={212-220},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0011728100003417},
isbn={978-989-758-634-7},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 18th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2023) - Volume 5: VISAPP
TI - DeepCaps+: A Light Variant of DeepCaps
SN - 978-989-758-634-7
AU - Shiri P.
AU - Baniasadi A.
PY - 2023
SP - 212
EP - 220
DO - 10.5220/0011728100003417
PB - SciTePress