Total Deep Variation: A Stable Regularizer for Inverse Problems

06/15/2020
by   Erich Kobler, et al.
0

Various problems in computer vision and medical imaging can be cast as inverse problems. A frequent method for solving inverse problems is the variational approach, which amounts to minimizing an energy composed of a data fidelity term and a regularizer. Classically, handcrafted regularizers are used, which are commonly outperformed by state-of-the-art deep learning approaches. In this work, we combine the variational formulation of inverse problems with deep learning by introducing the data-driven general-purpose total deep variation regularizer. In its core, a convolutional neural network extracts local features on multiple scales and in successive blocks. This combination allows for a rigorous mathematical analysis including an optimal control formulation of the training problem in a mean-field setting and a stability analysis with respect to the initial values and the parameters of the regularizer. In addition, we experimentally verify the robustness against adversarial attacks and numerically derive upper bounds for the generalization error. Finally, we achieve state-of-the-art results for numerous imaging tasks.

READ FULL TEXT

page 5

page 15

page 17

page 18

page 19

page 21

page 22

page 24

research
01/14/2020

Total Deep Variation for Linear Inverse Problems

Diverse inverse problems in imaging can be cast as variational problems ...
research
05/29/2018

Adversarial Regularizers in Inverse Problems

Inverse Problems in medical imaging and computer vision are traditionall...
research
02/28/2018

NETT: Solving Inverse Problems with Deep Neural Networks

Recovering a function or high-dimensional parameter vector from indirect...
research
01/13/2019

Neumann Networks for Inverse Problems in Imaging

Many challenging image processing tasks can be described by an ill-posed...
research
08/11/2020

TextureWGAN: Texture Preserving WGAN with MLE Regularizer for Inverse Problems

Many algorithms and methods have been proposed for inverse problems part...
research
07/20/2020

Quantifying Model Uncertainty in Inverse Problems via Bayesian Deep Gradient Descent

Recent advances in reconstruction methods for inverse problems leverage ...
research
03/18/2021

Hessian Initialization Strategies for L-BFGS Solving Non-linear Inverse Problems

L-BFGS is the state-of-the-art optimization method for many large scale ...

Please sign up or login with your details

Forgot password? Click here to reset