pith. machine review for the scientific record. sign in

arxiv: 1904.07457 · v1 · submitted 2019-04-16 · 💻 cs.CV · cs.LG· stat.ML

Recognition: unknown

A Bayesian Perspective on the Deep Image Prior

Authors on Pith no claims yet
classification 💻 cs.CV cs.LGstat.ML
keywords priorimageapproachdeepinferencenetworktasksbayesian
0
0 comments X
read the original abstract

The deep image prior was recently introduced as a prior for natural images. It represents images as the output of a convolutional network with random inputs. For "inference", gradient descent is performed to adjust network parameters to make the output match observations. This approach yields good performance on a range of image reconstruction tasks. We show that the deep image prior is asymptotically equivalent to a stationary Gaussian process prior in the limit as the number of channels in each layer of the network goes to infinity, and derive the corresponding kernel. This informs a Bayesian approach to inference. We show that by conducting posterior inference using stochastic gradient Langevin we avoid the need for early stopping, which is a drawback of the current approach, and improve results for denoising and impainting tasks. We illustrate these intuitions on a number of 1D and 2D signal reconstruction tasks.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.