Bredius, CarloTian, ZonglinTelea, AlexandruArchambault, DanielNabney, IanPeltonen, Jaakko2022-06-022022-06-022022978-3-03868-182-3https://doi.org/10.2312/mlvis.20221068https://diglib.eg.org:443/handle/10.2312/mlvis20221068We present a method to visually assess the stability of deep learned projections. For this, we perturb the high-dimensional data by controlled sequences and visualize the resulting changes in the 2D projection. We apply our method to a recent deep learned projection framework on several training configurations (learned projections and real-world datasets). Our method, which is simple to implement, runs at interactive rates, sheds several novel insights on the stability of the explored method.Attribution 4.0 International LicenseCCS Concepts: Human-centered computing --> Information visualization; Visual analytics; Visualization systems and toolsHuman centered computingInformation visualizationVisual analyticsVisualization systems and tools10.2312/mlvis.202210681-55 pages