Q. in GANs, why don't discriminators produce per-pixel losses for the generator's backprop? Surely a bad image is not due to all pixels equally, but the D produces a global loss anyway and throws away more precise supervision. Is it a perf/RAM limitation, or something deeper?
-
-
The D usually emits a single scalar loss for the whole image, eg 0-3 for a WGAN. My suggestion is that it could instead emit for, say, a 64x64px image, a 64x64 array filled with 0-3 scalars, explaining how each pixel contributes to the global average loss of 2.2234.
-
(There's an analogy with PixelCNN, I think, but in this case the conditioning of each pixel's loss is much more implicit.)
End of conversation
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.