News for hackers. Stuff that matters.
Re:Generative Adversarial Networks for Extreme Learned Image... by stochastic_monk on Thursday April 12, 2018 @07:47AM (#16819835)
I think that the title of the paper should state that it is for lossy image compression, which clearly states how it works and what task it performs.

I would be surprised if there wasn't a way to provide a learned, lossless method of compression, but that would be a very different paper and result.

There are no comments on this comment yet.