David Malmgren-Hansen

David Malmgren-Hansen, Allan Aasbjerg Nielsen, Leif Toudal Pedersen

This paper explores the similarities of output layers in Neural Networks (NNs) with logistic regression to explain importance of inputs by Z-scores. The network analyzed, a network for fusion of Synthetic Aperture Radar (SAR) and Microwave Radiometry (MWR) data, is applied to prediction of arctic sea ice. With the analysis the importance of MWR relative to SAR is found to favor MWR components. Further, as the model represents image features at different scales, the relative importance of these are as well analyzed. The suggested methodology offers a simple and easy framework for analyzing output layer components and can reduce the number of components for further analysis with e.g. common NN visualization methods.

Wail Mustafa, Christian Kehl, Ulrik Lund Olsen et al.

Spectral computed tomography (CT) is an emerging technology capable of providing high chemical specificity, which is crucial for many applications such as detecting threats in luggage. This type of application requires both fast and high-quality image reconstruction and is often based on sparse-view (few) projections. The conventional filtered back projection (FBP) method is fast but it produces low-quality images dominated by noise and artifacts in sparse-view CT. Iterative methods with, e.g., total variation regularizers can circumvent that but they are computationally expensive, as the computational load proportionally increases with the number of spectral channels. Instead, we propose an approach for fast reconstruction of sparse-view spectral CT data using a U-Net convolutional neural network architecture with multi-channel input and output. The network is trained to output high-quality CT images from FBP input image reconstructions. Our method is fast at run-time and because the internal convolutions are shared between the channels, the computational load increases only at the first and last layers, making it an efficient approach to process spectral data with a large number of channels. We have validated our approach using real CT scans. Our results show qualitatively and quantitatively that our approach outperforms the state-of-the-art iterative methods. Furthermore, the results indicate that the network can exploit the coupling of the channels to enhance the overall quality and robustness.

David Malmgren-Hansen, Allan Aasbjerg Nielsen, Rasmus Engholm

Convolutional Neural Networks (Convnets) have achieved good results in a range of computer vision tasks the recent years. Though given a lot of attention, visualizing the learned representations to interpret Convnets, still remains a challenging task. The high dimensionality of internal representations and the high abstractions of deep layers are the main challenges when visualizing Convnet functionality. We present in this paper a technique based on clustering internal Convnet representations with a Dirichlet Process Gaussian Mixture Model, for visualization of learned representations in Convnets. Our method copes with the high dimensionality of a Convnet by clustering representations across all nodes of each layer. We will discuss how this application is useful when considering transfer learning, i.e.\ transferring a model trained on one dataset to solve a task on a different one.