Martin Storath

Martin Storath

Auto-generated profile, based on publicly available information

Martin Storath

Faculty of Applied Natural Sciences and Humanities and Institute of Digital Engineering, Technische Hochschule Würzburg-Schweinfurt, Schweinfurt, Germany

Research Focus & Metrics

Academic Career Length

18Years (2009-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2016
Verified
Book Chapter
Closed access
PDF file
ZPZsuzsanna Püspöki
Zsuzsanna Püspöki
MSMartin Storath
Martin Storath
DSDaniel Sage
Daniel Sage
MUMichael Unser
Michael Unser

1 June 2018
Verified
Conference Paper
Closed access
MWMaurice Weiler
Maurice Weiler
FHFred A. Hamprecht
Fred A. Hamprecht
MSMartin Storath
Martin Storath
In many machine learning tasks it is desirable that a model's prediction transforms in an equivariant way under transformations of its input. Convolutional neural networks (CNNs) implement translational equivariance by construction; for other transformations, however, they are compelled to learn the proper mapping. In this work, we develop Steerable Filter CNNs (SFCNNs) which achieve joint equivariance under translations and rotations by design. The proposed architecture employs steerable filters to efficiently compute orientation dependent responses for many orientations without suffering interpolation artifacts from filter rotation. We utilize group convolutions which guarantee an equivariant mapping. In addition, we generalize He's weight initialization scheme to filters which are defined as a linear combination of a system of atomic filters. Numerical experiments show a substantial enhancement of the sample complexity with a growing number of sampled filter orientations and confirm that the network generalizes learned patterns over orientations. The proposed approach achieves state-of-the-art on the rotated MNIST benchmark and on the ISBI 2012 2D EM segmentation challenge.

5 June 2014 in IEEE Transactions on Signal Processing
Verified
Journal Article
Closed access
MSMartin Storath
Martin Storath
AWAndreas Weinmann
Andreas Weinmann
LDLaurent Demaret
Laurent Demaret
We recover jump-sparse and sparse signals from blurred incomplete data corrupted by (possibly non-Gaussian) noise using inverse Potts energy functionals. We obtain analytical results (existence of minimizers, complexity) on inverse Potts functionals and provide relations to sparsity problems. We then propose a new optimization method for these functionals which is based on dynamic programming and the alternating direction method of multipliers (ADMM). A series of experiments shows that the proposed method yields very satisfactory jump-sparse and sparse reconstructions, respectively. We highlight the capability of the method by comparing it with classical and recent approaches such as TV minimization (jump-sparse signals), orthogonal matching pursuit, iterative hard thresholding, and iteratively reweighted ℓ 1 minimization (sparse signals).

21 January 2015 in Inverse Problems
Verified
Journal Article
Closed access
MSMartin Storath
Martin Storath
AWAndreas Weinmann
Andreas Weinmann
JFJürgen Frikel
Jürgen Frikel
MUMichael Unser
Michael Unser

1 January 2014 in SIAM Journal on Imaging Sciences
Verified
Journal Article
Closed access
AWAndreas Weinmann
Andreas Weinmann
LDLaurent Demaret
Laurent Demaret
MSMartin Storath
Martin Storath
We consider total variation (TV) minimization for manifold-valued data. We propose a cyclic proximal point algorithm and a parallel proximal point algorithm to minimize TV functionals with $\ell^p$-type data terms in the manifold case. These algorithms are based on iterative geodesic averaging which makes them easily applicable to a large class of data manifolds. As an application, we consider denoising images which take their values in a manifold. We apply our algorithms to diffusion tensor images and interferometric SAR images as well as sphere- and cylinder-valued images. For the class of Cartan--Hadamard manifolds (which includes the data space in diffusion tensor imaging) we show the convergence of the proposed TV minimizing algorithms to a global minimizer.

1 January 2014 in SIAM Journal on Imaging Sciences
Verified
Journal Article
Closed access
MSMartin Storath
Martin Storath
AWAndreas Weinmann
Andreas Weinmann
We propose a fast splitting approach to the classical variational formulation of the image partitioning problem, which is frequently referred to as the Potts or piecewise constant Mumford--Shah model. For vector-valued images, our approach is significantly faster than the methods based on graph cuts and convex relaxations of the Potts model which are presently the state-of-the-art. The computational costs of our algorithm only grow linearly with the dimension of the data space which contrasts the exponential growth of the state-of-the-art methods. This allows us to process images with high-dimensional codomains such as multispectral images. Our approach produces results of a quality comparable with that of graph cuts and the convex relaxation strategies, and we do not need an a priori discretization of the label space. Furthermore, the number of partitions has almost no influence on the computational costs, which makes our algorithm also suitable for the reconstruction of piecewise constant (color or vectorial) images.