papers AI Learner
The Github is limit! Click to go to the new site.

Assessing Capsule Networks With Biased Data

2019-04-09
Bruno Ferrarini (1), Shoaib Ehsan (1), Adrien Bartoli (2), Aleš Leonardis (3), Klaus D. McDonald-Maier (1) ((1) University of Essex, CSEE, Wivenhoe Park, Colchester CO4 3SQ, UK (2) Faculté de Médecine, 28 Place Henri Dunant, 63000 Clermont-Ferrand, France (3) University of Birmingham, School of Computer Science, Birmingham B15 2TT, UK)

Abstract

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.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1904.04555

PDF

http://arxiv.org/pdf/1904.04555


Similar Posts

Comments