Using Deep Image Prior to Assist Variational Selective Segmentation Deep Learning Algorithms

Burrows, Liam ORCID: 0000-0002-6910-6693, Chen, Ke ORCID: 0000-0002-6093-6623 and Torella, Francesco ORCID: 0000-0003-0529-7387 (2021) Using Deep Image Prior to Assist Variational Selective Segmentation Deep Learning Algorithms. 17TH INTERNATIONAL SYMPOSIUM ON MEDICAL INFORMATION PROCESSING AND ANALYSIS, 12088. 120880s-120880s-10-.

	Text 2112.00793v1.pdf - Published version Download (3MB) \| Preview
	Text 2112.00793v1.pdf - Published version Download (3MB) \| Preview

Official URL: http://dx.doi.org/10.1117/12.2606212

Abstract

Variational segmentation algorithms require a prior imposed in the form of a regularisation term to enforce smoothness of the solution. Recently, it was shown in the Deep Image Prior work that the explicit regularisation in a model can be removed and replaced by the implicit regularisation captured by the architecture of a neural network. The Deep Image Prior approach is competitive, but is only tailored to one specific image and does not allow us to predict future images. We propose to incorporate the ideas from Deep Image Prior into a more traditional learning algorithm to allow us to use the implicit regularisation offered by the Deep Image Prior, but still be able to predict future images.

Item Type:	Article
Additional Information:	Presented at SIPAIM 2021
Uncontrolled Keywords:	Image segmentation, Selective segmentation, Deep Image Prior
Divisions:	Faculty of Science and Engineering > School of Physical Sciences
Depositing User:	Symplectic Admin
Date Deposited:	14 Dec 2021 08:31
Last Modified:	15 Mar 2024 12:05
DOI:	10.1117/12.2606212
Related URLs:	Author Publisher
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3145312