Neural nets learn the distribution and even causal factors in the data. To me it seems that this distribution is often just too complex for it to be robustly captured by something that doesn't learn. Learning causal factors critically depends on learning along the depth of the network of latent variables which is a particularly opaque process, but this is what MLPs seem to do quite canonically (convnet being just a restricted special case of MLPs). I mean discerning causal factors is pretty much canonically the act of accumulating evidence with priors (weighted summation), deciding whether it is sufficient evidence and signaling how much it is (non-linearity).
Case in point- DNNs for image recogn. use Sobel edge detectors and other "obsolete" filters to do their magickal magic.
Hardly correct. You can't magically learn any kind of task. You can't add arbitrary number of layers and hope for the back prop to do its magic. It is difficult. Deep learning techniques are what makes it somewhat feasible.
SIFT is not obsolete because of NNs. They all have their pros and cons. You have to select the right tool for the job. BTW SIFT is not an edge detector (That's the Canny Transform). It describes images using salient features in scale invariant manner.