Reviews: CondConv: Conditionally Parameterized Convolutions for Efficient Inference

The idea of CondConvs is interesting, but there are some important questions that the authors don't address and the lack of a proper discussion is frustrating and significantly weakens the paper. The authors give no discussion on the weight matrices W_i. Is each one of these supposed to be the same size as the convolutional layer that they are replacing? Do they all have the same number of channels? It seems to me that by replacing existing convolutional layers by CondConvs would increase the number of parameters in the model by a factor of n.