Premium
Around the clock ‐ capsule networks and image transformations
Author(s) -
Schmidt Maximilian
Publication year - 2021
Publication title -
pamm
Language(s) - English
Resource type - Journals
ISSN - 1617-7061
DOI - 10.1002/pamm.202000179
Subject(s) - convolutional neural network , computer science , artificial intelligence , set (abstract data type) , class (philosophy) , image (mathematics) , capsule , pattern recognition (psychology) , data set , computer vision , programming language , botany , biology
Capsule networks are a promising new model class for image processing tasks. We investigate and compare their classification performance with convolutional neural networks on a new entry level image data set. In our experiments the capsules are able to learn the effect of rotated input images from data and outperform a comparable convolutional architecture. The results also show that convolutional and capsule networks need structural adjustment to respond to transformations that are not included in the training set.