Browsing by Author "Hinterreiter, Andreas"

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
    ParaDime: A Framework for Parametric Dimensionality Reduction
    (The Eurographics Association and John Wiley & Sons Ltd., 2023) Hinterreiter, Andreas; Humer, Christina; Kainz, Bernhard; Streit, Marc; Bujack, Roxana; Archambault, Daniel; Schreck, Tobias
    ParaDime is a framework for parametric dimensionality reduction (DR). In parametric DR, neural networks are trained to embed high-dimensional data items in a low-dimensional space while minimizing an objective function. ParaDime builds on the idea that the objective functions of several modern DR techniques result from transformed inter-item relationships. It provides a common interface for specifying these relations and transformations and for defining how they are used within the losses that govern the training process. Through this interface, ParaDime unifies parametric versions of DR techniques such as metric MDS, t-SNE, and UMAP. It allows users to fully customize all aspects of the DR process.We show how this ease of customization makes ParaDime suitable for experimenting with interesting techniques such as hybrid classification/embedding models and supervised DR. This way, ParaDime opens up new possibilities for visualizing high-dimensional data.
  • Thumbnail Image
    Item
    A Process Model for Dashboard Onboarding
    (The Eurographics Association and John Wiley & Sons Ltd., 2022) Dhanoa, Vaishali; Walchshofer, Conny; Hinterreiter, Andreas; Stitz, Holger; Gröller, Eduard; Streit, Marc; Borgo, Rita; Marai, G. Elisabeta; Schreck, Tobias
    Dashboards are used ubiquitously to gain and present insights into data by means of interactive visualizations. To bridge the gap between non-expert dashboard users and potentially complex datasets and/or visualizations, a variety of onboarding strategies are employed, including videos, narration, and interactive tutorials. We propose a process model for dashboard onboarding that formalizes and unifies such diverse onboarding strategies. Our model introduces the onboarding loop alongside the dashboard usage loop. Unpacking the onboarding loop reveals how each onboarding strategy combines selected building blocks of the dashboard with an onboarding narrative. Specific means are applied to this narration sequence for onboarding, which results in onboarding artifacts that are presented to the user via an interface. We concretize these concepts by showing how our process model can be used to describe a selection of real-world onboarding examples. Finally, we discuss how our model can serve as an actionable blueprint for developing new onboarding systems.
  • Thumbnail Image
    Item
    Visualizing Pairwise Feature Interactions in Neural Additive Models
    (The Eurographics Association, 2023) Steinparz, Christian; Hinterreiter, Andreas; Streit, Marc; Gillmann, Christina; Krone, Michael; Lenti, Simone
    We present an approach for incorporating feature interactions into Neural Additive Models (NAMs), building upon existing work in this area, to enhance their predictive capabilities while maintaining interpretability. Our contribution focuses on the visual exploration and management of the increased number of feature maps resulting from the addition of pairwise feature combinations to NAMs. This method allows for effectively visualizing individual and pairwise feature interactions using line plots and heatmaps, respectively. To address the potential explosion in the number of feature maps, we apply different scoring functions to compute the importance of a feature map and then filter and sort them based on their importance. The proposed interactive dashboard effectively manages large sets of feature maps, while preserving the white-box properties of NAMs.