EuroVisPosters2023
Permanent URI for this collection
Browse
Browsing EuroVisPosters2023 by Author "Döllner, Jürgen"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Constructing Hierarchical Continuity in Hilbert & Moore Treemaps(The Eurographics Association, 2023) Scheibel, Willy; Döllner, Jürgen; Gillmann, Christina; Krone, Michael; Lenti, SimoneThe Hilbert and Moore treemap layout algorithms are based on the space-filling Hilbert and Moore curves, respectively, to map tree-structured datasets to a 2D treemap layout. Considering multiple snapshots of a time-variant dataset, one of the design goals for Hilbert and Moore treemaps is layout stability, i.e., low changes in the layout for low changes in the underlying tree-structured data. For this, their underlying space-filling curve is expected to be continuous across all nodes and hierarchy levels, which has to be considered throughout the layouting process. We propose optimizations to subdivision templates, their orientation, and discuss the continuity of the underlying space-filling curve. We show real-world examples of Hilbert and Moore treemaps for small and large datasets with continuous space-filling curves, allowing for improved layout stability.Item A Dashboard for Interactive Convolutional Neural Network Training And Validation Through Saliency Maps(The Eurographics Association, 2023) Cech, Tim; Simsek, Furkan; Scheibel, Willy; Döllner, Jürgen; Gillmann, Christina; Krone, Michael; Lenti, SimoneQuali-quantitative methods provide ways for interrogating Convolutional Neural Networks (CNN). For it, we propose a dashboard using a quali-quantitative method based on quantitative metrics and saliency maps. By those means, a user can discover patterns during the training of a CNN. With this, they can adapt the training hyperparameters of the model, obtaining a CNN that learned patterns desired by the user. Furthermore, they neglect CNNs which learned undesirable patterns. This improves users' agency over the model training process.