E3S Web Conf.
Volume 229, 2021The 3rd International Conference of Computer Science and Renewable Energies (ICCSRE’2020)
|Number of page(s)||12|
|Published online||25 January 2021|
From Auto-encoders to Capsule Networks: A Survey
University Hassan First, Faculty of Science and Technology of Settat, Computing, Imaging and Modeling of Complex Systems Laboratory, Morocco
Convolutional Neural Networks are a very powerful Deep Learning structure used in image processing, object classification and segmentation. They are very robust in extracting features from data and largely used in several domains. Nonetheless, they require a large number of training datasets and relations between features get lost in the Max-pooling step, which can lead to a wrong classification. Capsule Networks(CapsNets) were introduced to overcome these limitations by extracting features and their pose using capsules instead of neurons. This technique shows an impressive performance in one-dimensional, two-dimensional and three-dimensional datasets as well as in sparse datasets. In this paper, we present an initial understanding of CapsNets, their concept, structure and learning algorithm. We introduce the progress made by CapsNets from their introduction in 2011 until 2020. We compare different CapsNets series architectures to demonstrate strengths and challenges. Finally, we quote different implementations of Capsule Networks and show their robustness in a variety of domains. This survey provides the state-of-theartof Capsule Networks and allows other researchers to get a clear view of this new field. Besides, we discuss the open issues and the promising directions of future research, which may lead to a new generation of CapsNets.
Key words: Convolutional Neural Networks / Auto-encoders / Capsule Networks / Routing by Agreement Between Capsules / EM Routing / Stacked Capsule Network / Deep Learning.
© The Authors, published by EDP Sciences, 2021
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.