Skip to main content
. Author manuscript; available in PMC: 2019 Dec 23.
Published in final edited form as: Adv Neural Inf Process Syst. 2019 Dec;32:9392–9402.

Figure 5: Coping with Noise:

Figure 5:

We test the robustness of our approach on a simple synthetic example. In each panel, we show noisy SFs (left) as binary points and the corresponding slice indicator’s output (right) as a heatmap of probabilities. We show that the indicator assigns low relative probabilities on noisy (40%, middle) samples and ignores a very noisy (80%, right) SF, assigning relatively uniform scores to all samples.