Re:The Fourier transform is a neural network
by mochomocha on Thursday April 29, 2021 @11:05AM
(#26982098)
I have trained GANs on raw JPEG coefficients with moderate success as a pet project. Read the raw DCT coefficients without decompressing and train in this space. JPEG-decompress the output of the net to reconstruct an image in the pixel space. There are few papers doing similar things for supervised learning tasks iirc
[ Parent
| on HN ]
Re:The Fourier transform is a neural network
by akrymski on Thursday April 29, 2021 @11:11AM
(#26982195)
Using a standard loss function like MSE?
Yeah it kinda works when you feed JPEG coefficients into a typical time-domain CNN, but mathematically it seems that if you're using frequencies as inputs, your convolutions should become simple multiplications. Am I wrong?
Re:The Fourier transform is a neural network
by mochomocha on Thursday April 29, 2021 @11:19AM
(#26982310)
Yep, you can successfully do it without convolutions. Here is a pointer if you want to dig deeper: https://eng.uber.com/neural-networks-jpeg/ (there's prior art to that, but this one is well written)