Review for NeurIPS paper: Depth Uncertainty in Neural Networks

Weaknesses: My main concern is mainly about the experiments section. It is great to see the demonstration of the method on ResNet-50. But I couldn't find the comparison of test accuracy through the paper. There is only log-likelihood included in the appendix. I would expect a comparison on test accuracy among DUN, MC-dropout, deep ensembles, deep ensembles with different depths.