Hacker News new | ask | show | jobs
by JyrkiAlakuijala 3388 days ago
It is old school: 100000+ cpu hours of Nelder-Mead method (+common tricks) to match butteraugli to a set of 4000 human rated image pairs created with an earlier version of Guetzli and specially-built image distortion algorithms.
3 comments
londons_explore 3388 days ago
How did you protect against overfitting? How about local maxima? Some of your constants look surprising to say the least.

Most notably:

* The gamma value of 0.38 (when most studies suggest 1.5 - 2.5 for human eye gamma)

* The significant difference in the vertical and horizontal constants (when as far as I know human eyes are equally sensitive to most distortions independant of angle).

link
JyrkiAlakuijala 3388 days ago
There was a large variety of regularization and optimization techniques used. An embarrassingly large amount of manual work went into both.

In this use the gamma is the inverse of something close to 2.6. Butteraugli needs both gamma correction and inverse gamma correction.

The FFT co-efficients only look weird, but they should actually lead to a symmetric result if our math is correct. In a future version we move away from the FFT, so I don't encourage anyone to actually debug that too much.

link
i336_ 3387 days ago
> In a future version we move away from the FFT

Do you have any idea when that will land in the open? Say, before 2018? Or maybe a little sooner?

link
i336_ 3387 days ago
Very confused as to why this was downvoted?
link
sqeaky 3387 days ago
Nothing to be embarrassed about, you got results. Results are what matters in the end.

This is even more the case with software. If this cost 20 or 20 million man hours is irrelevant in the long run because eventually it will be used enough to offset costs if it is as good as every one says. Of course short term cost hurt now, but sounds like you still had computers do much of the heavy lifting.

link
myle 3388 days ago
To those who didn't notice, that's one of the authors, well also took large part in previous related work.
link
i336_ 3387 days ago
Very nice.

One question: as the top-level comment in this thread noted, this algorithm may be specialized to certain kinds of images.

Can you release info about the kind of images/datsets this approach will pathologically fail with? That would be really really awesome.

link