Browsing by Author "Streit, Marc"

Now showing 1 - 4 of 4
  • Thumbnail Image
    Item
    Interactive Attribution-based Explanations for Image Segmentation
    (The Eurographics Association, 2022) Humer, Christina; Elharty, Mohamed; Hinterreiter, Andreas; Streit, Marc; Krone, Michael; Lenti, Simone; Schmidt, Johanna
    Explanations of deep neural networks (DNNs) give users a better understanding of the inner workings and generalizability of a network. While the majority of research focuses on explanations for classification networks, in this work we focus on explainability for image segmentation networks. As a first contribution, we introduce a lightweight framework that allows generalizing certain attribution-based explanations, originally developed for classification networks, to also work for segmentation networks. The second contribution is a web-based tool that utilizes this framework and allows users to interactively explore segmentation networks. We demonstrate the approach using a self-trained mushroom segmentation network.
  • Thumbnail Image
    Item
    The State of the Art in Visualizing Multivariate Networks
    (The Eurographics Association and John Wiley & Sons Ltd., 2019) Nobre, Carolina; Meyer, Miriah; Streit, Marc; Lex, Alexander; Laramee, Robert S. and Oeltze, Steffen and Sedlmair, Michael
    Multivariate networks are made up of nodes and their relationships (links), but also data about those nodes and links as attributes. Most real-world networks are associated with several attributes, and many analysis tasks depend on analyzing both, relationships and attributes. Visualization of multivariate networks, however, is challenging, especially when both the topology of the network and the attributes need to be considered concurrently. In this state-of-the-art report, we analyze current practices and classify techniques along four axes: layouts, view operations, layout operations, and data operations. We also provide an analysis of tasks specific to multivariate networks and give recommendations for which technique to use in which scenario. Finally, we survey application areas and evaluation methodologies.
  • Thumbnail Image
    Item
    TourDino: A Support View for Confirming Patterns in Tabular Data
    (The Eurographics Association, 2019) Eckelt, Klaus; Adelberger, Patrick; Zichner, Thomas; Wernitznig, Andreas; Streit, Marc; Landesberger, Tatiana von and Turkay, Cagatay
    Seeking relationships and patterns in tabular data is a common data exploration task. To confirm hypotheses that are based on visual patterns observed during exploratory data analysis, users need to be able to quickly compare data subsets, and get further information on the significance of the result and the statistical test applied. Existing tools, however, either focus on the comparison of a single data type, such as comparing numerical attributes only, or provide little or no statistical evaluation to assess a hypothesis. To fill this gap, we present TourDino, a support view that helps users who are not experts in statistics to verify generated hypotheses and confirm insights gained during the exploration of tabular data. In TourDino we present an overview of the statistical significance of various row or column comparisons. On demand, we show further details, including the test score, a textual description, and a detail visualization explaining the results. To demonstrate the efficacy of our approach, we have integrated TourDino in the Ordino drug discovery platform for the purpose of identifying new drug targets.
  • Thumbnail Image
    Item
    Visualization of Rubik's Cube Solution Algorithms
    (The Eurographics Association, 2019) Steinparz, Christian Alexander; Hinterreiter, Andreas; Stitz, Holger; Streit, Marc; Landesberger, Tatiana von and Turkay, Cagatay
    Rubik's Cube is among the world's most famous puzzle toys. Despite its relatively simple principle, it requires dedicated, carefully planned algorithms to be solved. In this paper, we present an approach to visualize how different solution algorithms navigate through the high-dimensional space of Rubik's Cube states. We use t-distributed stochastic neighbor embedding (t-SNE) to project feature vector representations of cube states to two dimensions. t-SNE preserves the similarity of cube states and leads to clusters of intermediate states and bundles of cube solution pathways in the projection. Our prototype implementation allows interactive exploration of differences between algorithms, showing detailed state information on demand.