Thanks. There is no evaluation of mode collapse in the whole paper. You have been vocal against hyping results, which I respect, so I was surprised to see you make a statement that is not reflected by the results in your paper. Thank you for sending the reference.
Full paper here: https://twitter.com/arXiv_Daily/status/1184138720871534592?s=20 … We show that better optimization leads to better expression of modes in GANs. This is empirical and not main focus. Thanks for pointing out your work. We will look at it closely
-
-
-
This Tweet is unavailable.
- Show replies
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.