Assessing Capsule Networks With Biased Data

04/09/2019
by   Bruno Ferrarini, et al.
14

Machine learning based methods achieves impressive results in object classification and detection. Utilizing representative data of the visual world during the training phase is crucial to achieve good performance with such data driven approaches. However, it not always possible to access bias-free datasets thus, robustness to biased data is a desirable property for a learning system. Capsule Networks have been introduced recently and their tolerance to biased data has received little attention. This paper aims to fill this gap and proposes two experimental scenarios to assess the tolerance to imbalanced training data and to determine the generalization performance of a model with unfamiliar affine transformations of the images. This paper assesses dynamic routing and EM routing based Capsule Networks and proposes a comparison with Convolutional Neural Networks in the two tested scenarios. The presented results provide new insights into the behaviour of capsule networks.

READ FULL TEXT
research
11/18/2019

Improving the Robustness of Capsule Networks to Image Affine Transformations

Convolutional neural networks (CNNs) achieve translational invariance us...
research
01/29/2021

Efficient-CapsNet: Capsule Network with Self-Attention Routing

Deep convolutional neural networks, assisted by architectural design str...
research
10/14/2020

An Adversarial Attack against Stacked Capsule Autoencoder

Capsule network is a kind of neural network which uses spatial relations...
research
05/21/2019

Limitations of routing-by-agreement based capsule networks

Classical neural networks add a bias term to the sum of all weighted inp...
research
01/05/2022

Quantum Capsule Networks

Capsule networks, which incorporate the paradigms of connectionism and s...
research
10/15/2018

Polyphonic Sound Event Detection by using Capsule Neural Networks

Artificial sound event detection (SED) has the aim to mimic the human ab...
research
05/21/2018

VideoCapsuleNet: A Simplified Network for Action Detection

The recent advances in Deep Convolutional Neural Networks (DCNNs) have s...

Please sign up or login with your details

Forgot password? Click here to reset