Review for NeurIPS paper: Deep Metric Learning with Spherical Embedding

Weaknesses: 1) I think the main drawback of this paper is that, the design of the SEC loss is somehow too straightforward and trivial. It simply minimizes the distance between the norm of each feature and the average norm, which acts as an additional term of the existing losses. A more elegant design should be expected for the NeurIPS level. It seems the latter, but in this case how to update \mu during training? Whenever the parameters of the metric are updated, all the features are changed, and \mu should be re-calculated.