The Deep Capsule Prior – advantages through complexity?

In inverse problems, an extensive number of ground truth samples for the training of supervised deep learning models is seldom available. Unsupervised approaches, like the Deep Image Prior, offer a valuable alternative in this case. In our work, we combine the idea of the Deep Image Prior with recen...

Full description

Saved in:
Bibliographic Details
Published inProceedings in applied mathematics and mechanics Vol. 21; no. 1
Main Authors Schmidt, Maximilian, Denker, Alexander, Leuschner, Johannes
Format Journal Article
LanguageEnglish
Published Berlin Wiley-VCH GmbH 01.12.2021
Online AccessGet full text

Cover

More Information
Summary:In inverse problems, an extensive number of ground truth samples for the training of supervised deep learning models is seldom available. Unsupervised approaches, like the Deep Image Prior, offer a valuable alternative in this case. In our work, we combine the idea of the Deep Image Prior with recently proposed capsule networks. The new model is tested against a standard convolutional Deep Image Prior on different image processing tasks and computed tomography reconstruction.
ISSN:1617-7061
1617-7061
DOI:10.1002/pamm.202100166