Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Jan Macdonald

Jan Macdonald

Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

Martin Genzel , Ingo Gühring , Jan Macdonald , Maximilian März

Figure 1 for Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

Figure 2 for Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

Figure 3 for Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

Figure 4 for Near-Exact Recovery for Tomographic Inverse Problems via Deep Learning

* ICML 2022 (long talk). Code available at https://github.com/jmaces/aapm-ct-challenge. arXiv admin note: text overlap with arXiv:2106.00280

Access Paper or Ask Questions

A Complete Characterisation of ReLU-Invariant Distributions

Jan Macdonald , Stephan Wäldchen

Figure 1 for A Complete Characterisation of ReLU-Invariant Distributions

Figure 2 for A Complete Characterisation of ReLU-Invariant Distributions

Figure 3 for A Complete Characterisation of ReLU-Invariant Distributions

Figure 4 for A Complete Characterisation of ReLU-Invariant Distributions

* 39 pages, 9 Figures

Access Paper or Ask Questions

Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings

Jan Macdonald , Mathieu Besançon , Sebastian Pokutta

Figure 1 for Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings

Figure 2 for Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings

Figure 3 for Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings

Figure 4 for Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings

* 16 pages, 19 figures, 1 table

Access Paper or Ask Questions

AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry

Martin Genzel , Jan Macdonald , Maximilian März

Figure 1 for AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry

Figure 2 for AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry

Figure 3 for AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry

Figure 4 for AAPM DL-Sparse-View CT Challenge Submission Report: Designing an Iterative Network for Fanbeam-CT with Unknown Geometry

* This is a technical report of a method participating in a not yet finished challenge. Therefore, it does not contain any final results. In particular, the reported reconstruction errors are only with respect to our own validation split of the provided training data. Once the official challenge report is released, these values will be updated with the results from the actual test set

Access Paper or Ask Questions

Solving Inverse Problems With Deep Neural Networks -- Robustness Included?

Martin Genzel , Jan Macdonald , Maximilian März

Figure 1 for Solving Inverse Problems With Deep Neural Networks -- Robustness Included?

Figure 2 for Solving Inverse Problems With Deep Neural Networks -- Robustness Included?

Figure 3 for Solving Inverse Problems With Deep Neural Networks -- Robustness Included?

Figure 4 for Solving Inverse Problems With Deep Neural Networks -- Robustness Included?

Access Paper or Ask Questions

Interval Neural Networks as Instability Detectors for Image Reconstructions

Jan Macdonald , Maximilian März , Luis Oala , Wojciech Samek

Figure 1 for Interval Neural Networks as Instability Detectors for Image Reconstructions

Figure 2 for Interval Neural Networks as Instability Detectors for Image Reconstructions

Figure 3 for Interval Neural Networks as Instability Detectors for Image Reconstructions

Figure 4 for Interval Neural Networks as Instability Detectors for Image Reconstructions

* JM, MM and LO contributed equally

Access Paper or Ask Questions

Interval Neural Networks: Uncertainty Scores

Luis Oala , Cosmas Heiß , Jan Macdonald , Maximilian März , Wojciech Samek , Gitta Kutyniok

Figure 1 for Interval Neural Networks: Uncertainty Scores

Figure 2 for Interval Neural Networks: Uncertainty Scores

Figure 3 for Interval Neural Networks: Uncertainty Scores

Figure 4 for Interval Neural Networks: Uncertainty Scores

* LO and CH contributed equally

Access Paper or Ask Questions

A Rate-Distortion Framework for Explaining Neural Network Decisions

Jan Macdonald , Stephan Wäldchen , Sascha Hauch , Gitta Kutyniok

Figure 1 for A Rate-Distortion Framework for Explaining Neural Network Decisions

Figure 2 for A Rate-Distortion Framework for Explaining Neural Network Decisions

Figure 3 for A Rate-Distortion Framework for Explaining Neural Network Decisions

Access Paper or Ask Questions