Deep Neural Networks

Learning to Invert Defocus Blur: A Data-Driven Approach to the Helsinki Deblur Challenge
Invited Talk: Presentation of our 1st place winning submission to the Helsinki Deblur Challenge.
Dec 15, 2021 9:50 AM — 10:50 AM Tampere University (Hybrid Virtual Conference)
Theophil Trippe, Martin Genzel, Jan Macdonald, Maximilian März
Code
Near-Exact Recovery for Sparse-View CT via Data-Driven Methods
Poster: Presentation of a detailed analysis of our 1st place winning AAPM DL-Sparse-View CT challenge submission.
Dec 13, 2021 12:45 PM — 2:00 PM Virtual Conference
Martin Genzel, Ingo Gühring, Jan Macdonald, Maximilian März
Code
Near-Exact Recovery for Sparse-View CT via Data-Driven Methods
This work presents an empirical study on the design and training of iterative neural networks for image reconstruction from tomographic …
Martin Genzel, Ingo Gühring, Jan Macdonald, Maximilian März
PDF Cite Code
Detecting Failure Modes in Image Reconstructions with Interval Neural Network Uncertainty

Purpose The quantitative detection of failure modes is important for making deep neural networks reliable and usable at scale. We …

Luis Oala, Cosmas Heiß, Jan Macdonald, Maximilian März, Gitta Kutyniok, Wojciech Samek
Preprint PDF Cite Code DOI
AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry
Invited Talk: Presentation of our 1st place winning AAPM DL-Sparse-View CT challenge submission.
Jul 28, 2021 4:30 PM — 5:30 PM Virtual Conference
Martin Genzel, Jan Macdonald, Maximilian März
Code
AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry
This report is dedicated to a short motivation and description of our contribution to the AAPM DL-Sparse-View CT Challenge (team name: …
Martin Genzel, Jan Macdonald, Maximilian März
PDF Cite Code
Interval Neural Networks as Instability Detectors for Image Reconstructions
Contributed Talk: Presentation of results from our paper.
Mar 9, 2021 1:45 PM — 2:00 PM Virtual Workshop
Jan Macdonald, Luis Oala, Maximilian März, Wojciech Samek
Code Video
Interval Neural Networks as Instability Detectors for Image Reconstructions
This work investigates the detection of instabilities that may occur when utilizing deep learning models for image reconstruction …
Jan Macdonald, Maximilian März, Luis Oala, Wojciech Samek
Preprint PDF Cite Code DOI
Explaining Neural Network Decisions Is Hard
Poster: Presentation of results based on our papers A Rate-Distortion Framework for Explaining Neural Network Decisions and The Computational Complexity of Understanding Network Decisions.
Jul 17, 2020 Virtual Workshop
Jan Macdonald, Stephan Wäldchen, Sascha Hauch, Gitta Kutyniok
Explaining Neural Network Decisions Is Hard
We connect the widespread idea of interpreting classifier decisions to probabilistic prime implicants. A set of input features is deemed …
Jan Macdonald, Stephan Wäldchen, Sascha Hauch, Gitta Kutyniok
PDF Cite Code