Momentum Capsule Networks

01/26/2022
by   Josef Gugglberger, et al.
0

Capsule networks are a class of neural networks that achieved promising results on many computer vision tasks. However, baseline capsule networks have failed to reach state-of-the-art results on more complex datasets due to the high computation and memory requirements. We tackle this problem by proposing a new network architecture, called Momentum Capsule Network (MoCapsNet). MoCapsNets are inspired by Momentum ResNets, a type of network that applies reversible residual building blocks. Reversible networks allow for recalculating activations of the forward pass in the backpropagation algorithm, so those memory requirements can be drastically reduced. In this paper, we provide a framework on how invertible residual building blocks can be applied to capsule networks. We will show that MoCapsNet beats the accuracy of baseline capsule networks on MNIST, SVHN and CIFAR-10 while using considerably less memory. The source code is available on https://github.com/moejoe95/MoCapsNet.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/15/2021

Training Deep Capsule Networks with Residual Connections

Capsule networks are a type of neural network that have recently gained ...
research
12/07/2021

CapsProm: A Capsule Network For Promoter Prediction

Locating the promoter region in DNA sequences is of paramount importance...
research
07/14/2017

The Reversible Residual Network: Backpropagation Without Storing Activations

Deep residual networks (ResNets) have significantly pushed forward the s...
research
08/26/2019

Fashion Image Retrieval with Capsule Networks

In this study, we investigate in-shop clothing retrieval performance of ...
research
01/10/2020

Diagnosing Colorectal Polyps in the Wild with Capsule Networks

Colorectal cancer, largely arising from precursor lesions called polyps,...
research
08/12/2021

m-RevNet: Deep Reversible Neural Networks with Momentum

In recent years, the connections between deep residual networks and firs...
research
11/02/2019

An Algorithm for Routing Capsules in All Domains

Building on recent work on capsule networks, we propose a new form of "r...

Please sign up or login with your details

Forgot password? Click here to reset