[kastnerkyle]

If we really want to get into "what is better" - the state of the art has recently moved significantly past this (paper [1] and blog [2]) - not to mention the recent submissions to ICLR in this realm [3][4]. GAN training is very tricky to get working in practice, especially on new problems, though conditional GAN seems to be a bit more stable in learning than the unconditional relatives.

This blog deserves credit for thinking differently about a problem and getting something useful out of it.

I think the goal of this inversion was to inspect what the cascade is "looking at" in some sense - and for that this does a great job! Inverting a lossy classification feature is nearly always going to be worse than something designed from the ground up to be a generative model.

[1] http://arxiv.org/abs/1512.09300

[2] http://torch.ch/blog/2015/11/13/gan.html

[3] https://github.com/Newmu/dcgan_code

[4] http://arxiv.org/abs/1511.05644