Using Deep Image Prior to Assist Variational Selective Segmentation Deep Learning Algorithms
This work addresses the problem of image segmentation for researchers and practitioners by providing a more generalizable method, though it is incremental as it builds on existing Deep Image Prior concepts.
The paper tackles the limitation of Deep Image Prior, which lacks generalizability to new images, by integrating its implicit regularization into a traditional learning algorithm, enabling prediction on future images while maintaining competitive performance.
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.