The reviewed record of science sign in
Pith

arxiv: 2302.10279 · v2 · pith:L4P6DJHG · submitted 2023-02-20 · cs.CV · eess.IV

Image Reconstruction via Deep Image Prior Subspaces

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:L4P6DJHGrecord.jsonopen to challenge →

classification cs.CV eess.IV
keywords imageoptimisationdeepmethodsorderreconstructionsecondsubspace
0
0 comments X
read the original abstract

Deep learning has been widely used for solving image reconstruction tasks but its deployability has been held back due to the shortage of high-quality training data. Unsupervised learning methods, such as the deep image prior (DIP), naturally fill this gap, but bring a host of new issues: the susceptibility to overfitting due to a lack of robust early stopping strategies and unstable convergence. We present a novel approach to tackle these issues by restricting DIP optimisation to a sparse linear subspace of its parameters, employing a synergy of dimensionality reduction techniques and second order optimisation methods. The low-dimensionality of the subspace reduces DIP's tendency to fit noise and allows the use of stable second order optimisation methods, e.g., natural gradient descent or L-BFGS. Experiments across both image restoration and tomographic tasks of different geometry and ill-posedness show that second order optimisation within a low-dimensional subspace is favourable in terms of optimisation stability to reconstruction fidelity trade-off.

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.