Earlier quoted context omitted.
Uber now has a deal with Waymo - so in effect they are still trying to do self-driving taxi's, but now via a complex business relationship.
Ah, just like I "make hamburgers" when I go through the McDonals drive-through, although it's via a business transaction.
Faster neural networks straight from JPEG (2018)
11–20 of 108 posts
Re: Faster neural networks straight from JPEG (2018)
#12Re: Faster neural networks straight from JPEG (2018)
#13Finally someone who did this, I've always thought this was a low hanging fruit. I wonder if you could make interesting and quickly trained diffusion models with this trick.
[1] https://openaccess.thecvf.com/content/CVPR2023/papers/Park_R...
Re: Faster neural networks straight from JPEG (2018)
#14Add "(2018)"
Re: Faster neural networks straight from JPEG (2018)
#15Re: Faster neural networks straight from JPEG (2018)
#16> Accuracy gains are due primarily to the specific use of a DCT representation, which turns out to work curiously well for image classification. It would seem quantization is a useful tool for any sort of NN-style application. If the expected output is intended to be human-like, why not feed it information that a typical human could not distinguish from a lossless representation? Seems like a simple game of expectati…
But we tend to ignore high-frequency data's specifics most of the time, so it psychologically works.
I often wonder though, what do my cat and dog hear when I'm playing compressed music? Does it sounds like a muddy phone call to them?
Re: Faster neural networks straight from JPEG (2018)
#17Finally someone who did this, I've always thought this was a low hanging fruit. I wonder if you could make interesting and quickly trained diffusion models with this trick.
Re: Faster neural networks straight from JPEG (2018)
#18For those interested, a modern version (vision transformers) was just published this year at CVPR https://openaccess.thecvf.com/content/CVPR2023/html/Park_RGB...
Interesting line: "With these two improvements -- ViT and data augmentation -- we show that our ViT-Ti model achieves up to 39.2% faster training and 17.9% faster inference with no accuracy loss compared to the RGB counterpart."
Re: Faster neural networks straight from JPEG (2018)
#19Earlier quoted context omitted.
Uber now has a deal with Waymo - so in effect they are still trying to do self-driving taxi's, but now via a complex business relationship.
Ah, just like I "make hamburgers" when I go through the McDonals drive-through, although it's via a business transaction.
Re: Faster neural networks straight from JPEG (2018)
#20Earlier quoted context omitted.
Ah, just like I "make hamburgers" when I go through the McDonals drive-through, although it's via a business transaction.
God this website is cynical. Licensing technology from another company to commercialize it is completely legitimate.