Figure 2 Left Asymptotic confidence We plot the mean confidence in the predicted in distribution class for different models as one moves away from samples along the trajectories

We attempted to find such directions by running the following type of attack. In Figure 2 GOOD also stands out as having low confidence in all directions that we studied. However, there is no guarantee that GOOD does not also get in some direction asymptotically overconfident. Each convolu-tional layer is directly followed by a ReLU. In Section 2.1 we describe semi-joint training of We see that the AUCs of ProoD-S are almost identical to those of OE.