Ah! Your comment helped me understand the parent comment so much more. I thought it was more about data hygiene needs.

Yes a DT on raw pixel values, or a DT on raw time values will in general be quite terrible.

That said the convolutional structure is hard coded in those neural nets, only the weights are learned. It is not that the network discovered on its own that convolutions are a good idea. So NNs too really (damn autocorrect, it's rely, rely) on human insight and structuring upon which they can then build over.