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

arXiv: https://arxiv.org/abs/2112.00793 · HTML: https://mlsanity.com/paper/2112.00793/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 26 references that are in the map.
- First posted on arXiv 1 Dec 2021.

## Builds on (most cited first, 13 of 13)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs](https://mlsanity.com/paper/1606.00915/) (2016)
- [Deep Image Prior](https://mlsanity.com/paper/1711.10925/) (2017)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [DeepRED: Deep Image Prior Powered by RED](https://mlsanity.com/paper/1903.10176/) (2019)
- [Image Restoration using Total Variation Regularized Deep Image Prior](https://mlsanity.com/paper/1810.12864/) (2018)
- [Multi-Task Attention-Based Semi-Supervised Learning for Medical Image Segmentation](https://mlsanity.com/paper/1907.12303/) (2019)
- [Universal Semi-Supervised Semantic Segmentation](https://mlsanity.com/paper/1811.10323/) (2018)
- [Compressed Sensing with Deep Image Prior and Learned Regularization](https://mlsanity.com/paper/1806.06438/) (2018)
- [Joint Left Atrial Segmentation and Scar Quantification Based on a DNN with Spatial Encoding and Shape Attention](https://mlsanity.com/paper/2006.13011/) (2020)
- [Learning Directional Feature Maps for Cardiac MRI Segmentation](https://mlsanity.com/paper/2007.11349/) (2020)
- [Automated Detection of Cortical Lesions in Multiple Sclerosis Patients with 7T MRI](https://mlsanity.com/paper/2008.06780/) (2020)
- [Chan-Vese Reformulation for Selective Image Segmentation](https://mlsanity.com/paper/1811.08751/) (2018)

## Abstract (arXiv)

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.