41–50 of 146 posts
It wasn't highlighted on the github readme, but I think that the satellite photo to map and map to satellite photo (!!!) is incredible as well: https://taesung89.github.io/cyclegan/2017/03/25/maps-compari...
Similar work DiscoGAN https://github.com/SKTBrain/DiscoGAN
TIL - remap green pixels to grey/white and you go from summer to a contrived notion of winter. This done easily in Photoshop. - select green pixels, smooth it a bit, then paint white over it.. - apply a blue cast on it https://s17.postimg.org/q68dz04sf/test.jpg
TIL - remap green pixels to grey/white and you go from summer to a contrived notion of winter. This done easily in Photoshop. - select green pixels, smooth it a bit, then paint white over it.. - apply a blue cast on it https://s17.postimg.org/q68dz04sf/test.jpg
it feels like there's a new deep learning paper each week, ever so slightly bringing me closer to an existential nervous breakdown.
Sadly, I didn't work through the books like I had planned at all. Lacked the discipline to come home and work through them at the time. I really regret it now as things are blowing up and, as you said, it seems like every week there is something new and interesting
The next step is "turning pencil drawings into photos" and using it to fabricate evidence on grand scale. Why bother catching politicians doing something when you can just draw them in? Will wreak havoc on societies with weak politics/reporting culture.
Journalist: "Here is a compromising photo of a politician."
Politician: "Here are 1M photos of every politician doing every imaginable illegal act. Prove that your one photo is not similarly fabricated."
it feels like there's a new deep learning paper each week, ever so slightly bringing me closer to an existential nervous breakdown.
Yeah, I feel that. I tell myself they're only tools, really no stranger than time frequency domain transformations to someone unfamiliar with the fourier transform. Yet there really is something disturbing about seeing a computer resurrect so much of the mind of an artist who's been dead for nearly a century. I know the GPU doesn't understand what it's doing, but did Monet? When I paint I don't really understand. The…
The next step is "turning pencil drawings into photos" and using it to fabricate evidence on grand scale. Why bother catching politicians doing something when you can just draw them in? Will wreak havoc on societies with weak politics/reporting culture.
How long until personal testimony and non-repudiable crypto signatures are the only admissible evidence in court?
Of course, eyewitness testimony is notoriously unreliable even when not intentionally deceptive, and testimony is much easier to falsify even without any technical aid than any other form of evidence, so relying solely on personal testimony wouldn't really help to avoid fabricated evidence, anyway.
It wasn't highlighted on the github readme, but I think that the satellite photo to map and map to satellite photo (!!!) is incredible as well: https://taesung89.github.io/cyclegan/2017/03/25/maps-compari...
Open a NIPS paper from 2010 or so, and you'll see extremely dense mathematics: nonparametrics, variational approximation, sampling theory, riemannian geometry. But from my (admittedly small) sampling of the convnet / RNN literature there really doesn't seem to be much maths there. The typical paper seems to run along the lines of "We tried this, and it worked".
I'm not sure whether there's anything to learn from this observation, but I think it's striking all the same.