Gordon Kindlmann

Zhuokai Zhao, Takumi Matsuzawa, William Irvine et al.

Proper evaluations are crucial for better understanding, troubleshooting, interpreting model behaviors and further improving model performance. While using scalar-based error metrics provides a fast way to overview model performance, they are often too abstract to display certain weak spots and lack information regarding important model properties, such as robustness. This not only hinders machine learning models from being more interpretable and gaining trust, but also can be misleading to both model developers and users. Additionally, conventional evaluation procedures often leave researchers unclear about where and how model fails, which complicates model comparisons and further developments. To address these issues, we propose a novel evaluation workflow, named Non-Equivariance Revealed on Orbits (NERO) Evaluation. The goal of NERO evaluation is to turn focus from traditional scalar-based metrics onto evaluating and visualizing models equivariance, closely capturing model robustness, as well as to allow researchers quickly investigating interesting or unexpected model behaviors. NERO evaluation is consist of a task-agnostic interactive interface and a set of visualizations, called NERO plots, which reveals the equivariance property of the model. Case studies on how NERO evaluation can be applied to multiple research areas, including 2D digit recognition, object detection, particle image velocimetry (PIV), and 3D point cloud classification, demonstrate that NERO evaluation can quickly illustrate different model equivariance, and effectively explain model behaviors through interactive visualizations of the model outputs. In addition, we propose consensus, an alternative to ground truths, to be used in NERO evaluation so that model equivariance can still be evaluated with new, unlabeled datasets.

Saeid Barati, Gordon Kindlmann, Hank Hoffmann

Approximate computing frameworks configure applications so they can operate at a range of points in an accuracy-performance trade-off space. Prior work has introduced many frameworks to create approximate programs. As approximation frameworks proliferate, it is natural to ask how they can be compared and combined to create even larger, richer trade-off spaces. We address these questions by presenting VIPER and BOA. VIPER compares trade-off spaces induced by different approximation frameworks by visualizing performance improvements across the full range of possible accuracies. BOA is a family of exploration techniques that quickly locate Pareto-efficient points in the immense trade-off space produced by the combination of two or more approximation frameworks. We use VIPER and BOA to compare and combine three different approximation frameworks from across the system stack, including: one that changes numerical precision, one that skips loop iterations, and one that manipulates existing application parameters. Compared to simply looking at Pareto-optimal curves, we find VIPER's visualizations provide a quicker and more convenient way to determine the best approximation technique for any accuracy loss. Compared to a state-of-the-art evolutionary algorithm, we find that BOA explores 14x fewer configurations yet locates 35% more Pareto-efficient points.

Andrew McNutt, Gordon Kindlmann, Michael Correll

Dirty data and deceptive design practices can undermine, invert, or invalidate the purported messages of charts and graphs. These failures can arise silently: a conclusion derived from a particular visualization may look plausible unless the analyst looks closer and discovers an issue with the backing data, visual specification, or their own assumptions. We term such silent but significant failures "visualization mirages". We describe a conceptual model of mirages and show how they can be generated at every stage of the visual analytics process. We adapt a methodology from software testing, "metamorphic testing", as a way of automatically surfacing potential mirages at the visual encoding stage of analysis through modifications to the underlying data and chart specification. We show that metamorphic testing can reliably identify mirages across a variety of chart types with relatively little prior knowledge of the data or the domain.

Charisee Chiw, Gordon Kindlmann, John Reppy

The scientific community use PDEs to model a range of problems. The people in this domain are interested in visualizing their results, but existing mechanisms for visualization can not handle the full richness of computations in the domain. We did an exploration to see how Diderot, a domain specific language for scientific visualization and image analysis, could be used to solve this problem. We demonstrate our first and modest approach of visualizing FE data with Diderot and provide examples. Using Diderot, we do a simple sampling and a volume rendering of a FE field. These examples showcase Diderot's ability to provide a visualization result for Firedrake. This paper describes the extension of the Diderot language to include FE data.

Thomas Schultz, Anna Vilanova, Ralph Brecheisen et al.

Fiber tracking based on diffusion weighted Magnetic Resonance Imaging (dMRI) allows for noninvasive reconstruction of fiber bundles in the human brain. In this chapter, we discuss sources of error and uncertainty in this technique, and review strategies that afford a more reliable interpretation of the results. This includes methods for computing and rendering probabilistic tractograms, which estimate precision in the face of measurement noise and artifacts. However, we also address aspects that have received less attention so far, such as model selection, partial voluming, and the impact of parameters, both in preprocessing and in fiber tracking itself. We conclude by giving impulses for future research.