no code implementations • 15 Dec 2023 • Martin Burger, Samira Kabri
The aim of this paper is to provide a theoretically founded investigation of state-of-the-art learning approaches for inverse problems.
no code implementations • 5 Dec 2023 • Tjeerd Jan Heeringa, Tim Roith, Christoph Brune, Martin Burger
This paper presents a method for finding a sparse representation of Barron functions.
1 code implementation • 2 Apr 2023 • Samira Kabri, Tim Roith, Daniel Tenbrinck, Martin Burger
In this paper we investigate the use of Fourier Neural Operators (FNOs) for image classification in comparison to standard Convolutional Neural Networks (CNNs).
1 code implementation • 14 Dec 2022 • Samira Kabri, Alexander Auras, Danilo Riccio, Hartmut Bauermeister, Martin Benning, Michael Moeller, Martin Burger
The reconstruction of images from their corresponding noisy Radon transform is a typical example of an ill-posed linear inverse problem as arising in the application of computerized tomography (CT).
no code implementations • 1 Jul 2022 • Martin Burger, Alex Rossi
In this paper we provide a novel approach to the analysis of kinetic models for label switching, which are used for particle systems that can randomly switch between gradient flows in different energy landscapes.
no code implementations • 8 Dec 2021 • Martin Burger
In particular we will discuss a reinterpretation of machine learning problems in the framework of regularization theory and a reinterpretation of variational methods for inverse problems in the framework of risk minimization.
no code implementations • NeurIPS Workshop Deep_Invers 2021 • Subhadip Mukherjee, Carola-Bibiane Schönlieb, Martin Burger
Variational regularization has remained one of the most successful approaches for reconstruction in imaging inverse problems for several decades.
1 code implementation • 15 Jul 2021 • Protim Bhattacharjee, Martin Burger, Anko Boerner, Veniamin I. Morgenshtern
In this work we present an algorithm, called the RoI Prioritised Sampling (RPS), that prioritises Region-of-Interests (RoIs) in an exploration scenario in order to utilise the limited resources of the imaging instrument on the rover effectively.
no code implementations • 13 Jul 2021 • Philipp Werner, Martin Burger, Florian Frank, Harald Garcke
The aim of this paper is to develop suitable models for the phenomenon of cell blebbing, which allow for computational predictions of mechanical effects including the crucial interaction of the cell membrane and the actin cortex.
1 code implementation • 4 Jun 2021 • Leon Bungert, Tim Roith, Daniel Tenbrinck, Martin Burger
We propose a novel strategy for Neural Architecture Search (NAS) based on Bregman iterations.
1 code implementation • 10 May 2021 • Leon Bungert, Tim Roith, Daniel Tenbrinck, Martin Burger
In contrast to established methods for sparse training the proposed family of algorithms constitutes a regrowth strategy for neural networks that is solely optimization-based without additional heuristics.
Ranked #164 on Image Classification on CIFAR-10
1 code implementation • 24 Feb 2021 • Leo Schwinn, An Nguyen, René Raab, Leon Bungert, Daniel Tenbrinck, Dario Zanca, Martin Burger, Bjoern Eskofier
The susceptibility of deep neural networks to untrustworthy predictions, including out-of-distribution (OOD) data and adversarial examples, still prevent their widespread use in safety-critical applications.
no code implementations • 18 Feb 2021 • Tatiana A. Bubba, Martin Burger, Tapio Helin, Luca Ratti
We consider a statistical inverse learning problem, where the task is to estimate a function $f$ based on noisy point evaluations of $Af$, where $A$ is a linear operator.
no code implementations • 5 Nov 2020 • Leo Schwinn, An Nguyen, René Raab, Dario Zanca, Bjoern Eskofier, Daniel Tenbrinck, Martin Burger
We empirically show that by incorporating this nonlocal gradient information, we are able to give a more accurate estimation of the global descent direction on noisy and non-convex loss surfaces.
no code implementations • 23 Oct 2020 • Hartmut Bauermeister, Martin Burger, Michael Moeller
One of the main challenges in linear inverse problems is that a majority of such problems are ill-posed in the sense that the solution does not depend on the data continuously.
no code implementations • 28 May 2020 • Leon Bungert, Martin Burger, Yury Korolev, Carola-Bibiane Schoenlieb
We study variational regularisation methods for inverse problems with imperfect forward operators whose errors can be modelled by order intervals in a partial order of a Banach lattice.
Numerical Analysis Numerical Analysis Optimization and Control 47A52, 65J20, 65J22, 65K10
1 code implementation • 5 Dec 2019 • Martin Burger, Yury Korolev, Simone Parisotto, Carola-Bibiane Schönlieb
We introduce a first order Total Variation type regulariser that decomposes a function into a part with a given Lipschitz constant (which is also allowed to vary spatially) and a jump part.
Numerical Analysis Numerical Analysis 65J20, 65J22, 68U10, 94A08
no code implementations • 12 Mar 2019 • Martin Burger, Yury Korolev, Carola-Bibiane Schönlieb, Christiane Stollenwerk
We introduce a new regularizer in the total variation family that promotes reconstructions with a given Lipschitz constant (which can also vary spatially).
no code implementations • 7 Mar 2019 • Daniel Tenbrinck, Fjedor Gaede, Martin Burger
In this paper we propose a variational method defined on finite weighted graphs, which allows to sparsify a given 3D point cloud while giving the flexibility to control the appearance of the resulting approximation based on the chosen regularization functional.
Numerical Analysis Discrete Mathematics Data Structures and Algorithms Optimization and Control
no code implementations • 27 Feb 2019 • Leon Bungert, Martin Burger, Daniel Tenbrinck
In this work we investigate the computation of nonlinear eigenfunctions via the extinction profiles of gradient flows.
no code implementations • 9 May 2017 • Byung-Woo Hong, Ja-Keoung Koo, Martin Burger, Stefano Soatto
We present an adaptive regularization scheme for optimizing composite energy functionals arising in image analysis problems.
no code implementations • 23 Mar 2017 • Martin Benning, Michael Möller, Raz Z. Nossek, Martin Burger, Daniel Cremers, Guy Gilboa, Carola-Bibiane Schönlieb
In this paper we demonstrate that the framework of nonlinear spectral decompositions based on total variation (TV) regularization is very well suited for image fusion as well as more general image manipulation tasks.
no code implementations • 15 Mar 2017 • Trinh Van Chien, Khanh Quoc Dinh, Byeungwoo Jeon, Martin Burger
Although block compressive sensing (BCS) makes it tractable to sense large-sized images and video, its recovery performance has yet to be significantly improved because its recovered images or video usually suffer from blurred edges, loss of details, and high-frequency oscillatory artifacts, especially at a low subrate.
no code implementations • 8 Sep 2016 • Byung-Woo Hong, Ja-Keoung Koo, Hendrik Dirks, Martin Burger
The desired properties, robustness and effectiveness, of the regularization parameter selection in a variational framework for imaging problems are achieved by merely replacing the static regularization parameter with our adaptive one.
no code implementations • 12 Jul 2016 • Martin Burger, Hendrik Dirks, Carola-Bibiane Schönlieb
The aim of this paper is to derive and analyze a variational model for the joint estimation of motion and reconstruction of image sequences, which is based on a time-continuous Eulerian motion model.
no code implementations • 1 Dec 2015 • Martin Burger, Hendrik Dirks, Lena Frerking
The aim of this paper is to discuss and evaluate total variation based regularization methods for motion estimation, with particular focus on optical flow models.
no code implementations • 5 Oct 2015 • Guy Gilboa, Michael Moeller, Martin Burger
We present in this paper the motivation and theory of nonlinear spectral representations, based on convex regularizing functionals.
no code implementations • 13 Dec 2014 • Martin Burger, Alex Sawatzky, Gabriele Steidl
Variational methods in imaging are nowadays developing towards a quite universal and flexible tool, allowing for highly successful approaches on tasks like denoising, deblurring, inpainting, segmentation, super-resolution, disparity, and optical flow estimation.