Meeting Banner
Abstract #0051

The More the Merrier? - On the Number of Trainable Parameters in Iterative Neural Networks for Image Reconstruction

Andreas Kofler1, Tobias Schaeffter1,2,3, and Christoph Kolbitsch1,3
1Physikalisch-Technische Bundesanstalt, Braunschweig and Berlin, Germany, 2Department of Biomedical Engineering, Technische Universit├Ąt Berlin, Berlin, Germany, 3School of Imaging Sciences and Biomedical Engineering, King's College London, London, United Kingdom


Iterative neural networks (INNs) currently define the state-of-the-art for image reconstruction methods. With these methods, the obtained regularizers are not only optimally adapted to the employed physical model but also tailored to the reconstruction method the network implicitly defines. However, comparing the performance of different INNs-based methods is often challenging because of the black-box character of neural networks. In this work we construct an example which highlights the importance of keeping the number of trainable parameters approximately fixed when comparing INNs-based methods. If this aspect is not taken into consideration, wrong conclusions could be drawn.

This abstract and the presentation materials are available to members only; a login is required.

Join Here