1 code implementation • 18 Nov 2022 • Theophil Trippe, Martin Genzel, Jan Macdonald, Maximilian März
This work presents a novel deep-learning-based pipeline for the inverse problem of image deblurring, leveraging augmentation and pre-training with synthetic data.
1 code implementation • 14 Jun 2022 • Martin Genzel, Ingo Gühring, Jan Macdonald, Maximilian März
This work is concerned with the following fundamental question in scientific machine learning: Can deep-learning-based methods solve noise-free inverse problems to near-perfect accuracy?
no code implementations • 13 Dec 2021 • Jan Macdonald, Stephan Wäldchen
We prove that no invariant parametrised family of distributions can exist unless at least one of the following three restrictions holds: First, the network layers have a width of one, which is unreasonable for practical neural networks.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1
no code implementations • NeurIPS Workshop Deep_Invers 2021 • Martin Genzel, Ingo Gühring, Jan Macdonald, Maximilian März
This work presents an empirical study on the design and training of iterative neural networks for image reconstruction from tomographic measurements with unknown geometry.
1 code implementation • 15 Oct 2021 • Jan Macdonald, Mathieu Besançon, Sebastian Pokutta
We study the effects of constrained optimization formulations and Frank-Wolfe algorithms for obtaining interpretable neural network predictions.
1 code implementation • 1 Jun 2021 • Martin Genzel, Jan Macdonald, Maximilian März
This report is dedicated to a short motivation and description of our contribution to the AAPM DL-Sparse-View CT Challenge (team name: "robust-and-stable").
1 code implementation • 9 Nov 2020 • Martin Genzel, Jan Macdonald, Maximilian März
In the past five years, deep learning methods have become state-of-the-art in solving various inverse problems.
1 code implementation • 27 Mar 2020 • Jan Macdonald, Maximilian März, Luis Oala, Wojciech Samek
This work investigates the detection of instabilities that may occur when utilizing deep learning models for image reconstruction tasks.
1 code implementation • 25 Mar 2020 • Luis Oala, Cosmas Heiß, Jan Macdonald, Maximilian März, Wojciech Samek, Gitta Kutyniok
We propose a fast, non-Bayesian method for producing uncertainty scores in the output of pre-trained deep neural networks (DNNs) using a data-driven interval propagating network.
2 code implementations • 27 May 2019 • Jan Macdonald, Stephan Wäldchen, Sascha Hauch, Gitta Kutyniok
We formalise the widespread idea of interpreting neural network decisions as an explicit optimisation problem in a rate-distortion framework.
no code implementations • 17 Jan 2019 • Dominik Alfke, Weston Baines, Jan Blechschmidt, Mauricio J. del Razo Sarmina, Amnon Drory, Dennis Elbrächter, Nando Farchmin, Matteo Gambara, Silke Glas, Philipp Grohs, Peter Hinz, Danijel Kivaranovic, Christian Kümmerle, Gitta Kutyniok, Sebastian Lunz, Jan Macdonald, Ryan Malthaner, Gregory Naisat, Ariel Neufeld, Philipp Christian Petersen, Rafael Reisenhofer, Jun-Da Sheng, Laura Thesing, Philipp Trunschke, Johannes von Lindheim, David Weber, Melanie Weber
We present a novel technique based on deep learning and set theory which yields exceptional classification and prediction results.