Name
Abstract | ||
|---|---|---|
We propose a sparse reconstruction framework (aNETT) for solving inverse problems. Opposed to existing sparse reconstruction techniques that are based on linear sparsifying transforms, we train an autoencoder network D○E with E acting as a nonlinear sparsifying transform and minimize a Tikhonov functional with learned regularizer formed by the ℓ
<sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">q</sup>
-norm of the encoder coefficients and a penalty for the distance to the data manifold. We propose a strategy for training an autoencoder based on a sample set of the underlying image class such that the autoencoder is independent of the forward operator and is subsequently adapted to the specific forward model. Numerical results are presented for sparse view CT, which clearly demonstrate the feasibility, robustness and the improved generalization capability and stability of aNETT over post-processing networks. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1109/ISBIWorkshops50223.2020.9153362 | 2020 IEEE 17th International Symposium on Biomedical Imaging Workshops (ISBI Workshops) |
Keywords | DocType | ISSN |
Inverse problems,sparsity,regularization,deep learning,autoencoder | Conference | 1945-7928 |
ISBN | Citations | PageRank |
978-1-7281-7402-0 | 0 | 0.34 |
References | Authors | |
2 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Obmann Daniel | 1 | 0 | 0.34 |
| Nguyen Linh | 2 | 0 | 0.34 |
| Schwab Johannes | 3 | 0 | 0.34 |
| Markus Haltmeier | 4 | 74 | 14.16 |