[HTML][HTML] Capsule networks–a survey

MK Patrick, AF Adekoya, AA Mighty… - Journal of King Saud …, 2022 - Elsevier
Modern day computer vision tasks requires efficient solution to problems such as image
recognition, natural language processing, object detection, object segmentation and …

A novel Capsule Neural Network based model for drowsiness detection using electroencephalography signals

L Guarda, JE Tapia, EL Droguett, M Ramos - Expert Systems with …, 2022 - Elsevier
The early detection of drowsiness has become vital to ensure the correct and safe
development of several industries' tasks. Due to the transient mental state of a human …

Stacked capsule autoencoders

A Kosiorek, S Sabour, YW Teh… - Advances in neural …, 2019 - proceedings.neurips.cc
Abstract Objects are composed of a set of geometrically organized parts. We introduce an
unsupervised capsule autoencoder (SCAE), which explicitly uses geometric relationships …

Radiologist-level covid-19 detection using ct scans with detail-oriented capsule networks

A Mobiny, PA Cicalese, S Zare, P Yuan… - arXiv preprint arXiv …, 2020 - arxiv.org
Radiographic images offer an alternative method for the rapid screening and monitoring of
Coronavirus Disease 2019 (COVID-19) patients. This approach is limited by the shortage of …

Capsule routing via variational bayes

FDS Ribeiro, G Leontidis, S Kollias - … of the AAAI Conference on Artificial …, 2020 - aaai.org
Capsule networks are a recently proposed type of neural network shown to outperform
alternatives in challenging shape recognition tasks. In capsule networks, scalar neurons are …

How can we be so dense? the benefits of using highly sparse representations

S Ahmad, L Scheinkman - arXiv preprint arXiv:1903.11257, 2019 - arxiv.org
Most artificial networks today rely on dense representations, whereas biological networks
rely on sparse representations. In this paper we show how sparse representations can be …

Equivariant transformer networks

KS Tai, P Bailis, G Valiant - International Conference on …, 2019 - proceedings.mlr.press
How can prior knowledge on the transformation invariances of a domain be incorporated
into the architecture of a neural network? We propose Equivariant Transformers (ETs), a …

Unsupervised part representation by flow capsules

S Sabour, A Tagliasacchi, S Yazdani… - International …, 2021 - proceedings.mlr.press
Capsule networks aim to parse images into a hierarchy of objects, parts and relations. While
promising, they remain limited by an inability to learn effective low level part descriptions. To …

Capsule networks–A survey

M Kwabena Patrick, A Felix Adekoya, A Abra Mighty… - 2022 - dl.acm.org
Modern day computer vision tasks requires efficient solution to problems such as image
recognition, natural language processing, object detection, object segmentation and …

Improving the robustness of capsule networks to image affine transformations

J Gu, V Tresp - Proceedings of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
Convolutional neural networks (CNNs) achieve translational invariance by using pooling
operations. However, the operations do not preserve the spatial relationships in the learned …