Research Library

Premium Around the clock ‐ capsule networks and image transformations
Author(s)
Schmidt Maximilian
Publication year2021
Publication title
pamm
Resource typeJournals
PublisherWiley‐VCH GmbH
Abstract 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.
Subject(s)artificial intelligence , capsule , class (philosophy) , computer science , computer vision , convolutional neural network , data set , geology , image (mathematics) , paleontology , pattern recognition (psychology) , programming language , set (abstract data type)
Language(s)English
ISSN1617-7061
DOI10.1002/pamm.202000179

Seeing content that should not be on Zendy? Contact us.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here