How much information can a small image contain?
camerongordon.site
How much information can a small image contain?
1–10 of 30 posts
Re: How much information can a small image contain?
#2The introduction has lost me completely: such a long winded way to say that 32x32x3 bytes can represent 2^(32x32x3x8) different values.
Re: How much information can a small image contain?
#3The introduction has lost me completely: such a long winded way to say that 32x32x3 bytes can represent 2^(32x32x3x8) different values.
I think the point of the article is that there isn't 2^(32x32x3x8) meaningful images that can be encoded - there's far less than that because so many of the possible arrangements of the data are just meaningless noise, or millions of versions of the same thing with slightly altered color values etc.
The article is saying that neural networks are cool, because part of what they do is finding which images actually contain meaningful visual information.
Re: How much information can a small image contain?
#4Such nonsense drivel. How much an image contains can be inflated by doing some dishonest BS like creating a unique encoding to optimize for what each image is representing in RGB.
You can clearly see with steganographically encoded images that there is a limit if you want the image to remain and image - and still be able to store whatever arbitrary data in it. Being bound to the arbitrariness of data that can be stored is against the implications of the title, which is why this should be deemed nonsense.
Re: How much information can a small image contain?
#5The introduction has lost me completely: such a long winded way to say that 32x32x3 bytes can represent 2^(32x32x3x8) different values.
I think the point of the article is that there isn't 2^(32x32x3x8) meaningful images that can be encoded - there's far less than that because so many of the possible arrangements of the data are just meaningless noise, or millions of versions of the same thing with slightly altered color values etc. The article is saying that neural networks are cool, because part of what they do is finding which images actually cont…
But they don't, they often conflate noise with actual features, as long as the noise has some statistical bias, which given enough random generations, will. Try it yourself, generate random images using a uniform distribution (not gaussian) and run a SOTA classifier on them. Eventually you'll hit some minor false positives.
It errs in the same way we often see objects in clouds or constellations.
Re: How much information can a small image contain?
#6N^M, clearly.
Re: How much information can a small image contain?
#7If you want to look at the deeper questions the title invokes, this is the scam of how ThisPersonDoesNotExist and DALL-E work.
They deliver information to the brain, not actual pictures.
What they have created is amazing, but other than fooling other AI's their use is limited. They won't scale, they have gone the direction of information over fidelity.
Re: How much information can a small image contain?
#8Many moons ago, I wondered what it would look like if you iteratively generated every possible image. It doesn't sound very useful at all (and it certainly isn't) but I learned C++ and SDL that way.
This is probably terrible code by anybody's standards but maybe someone wants to take a look: https://github.com/svenstaro/infinerator
Re: How much information can a small image contain?
#9N^M, clearly.
Amateur.
Use the whole space [32x32x3 bytes = 3072 bytes] to encode a Busy Beaver.
Re: How much information can a small image contain?
#10Many moons ago, I wondered what it would look like if you iteratively generated every possible image. It doesn't sound very useful at all (and it certainly isn't) but I learned C++ and SDL that way. This is probably terrible code by anybody's standards but maybe someone wants to take a look: https://github.com/svenstaro/infinerator
I've thought about this as well; it's one of those weird things where you realize that with enough pixel count and shading options, every image you can think of exists within the total set of generated images.