Hacker News Reader

Comment by Stanleyc23 | Hacker News Reader

Just a random idea: could machine learning algorithms that do object recognition help to improve the compression of images or videos? Maybe a lossy algorithm could compress away "irrelevant" things. This way a high resolution frame might have lower resolution objects inside but it would he ok because the important part of the content is preserved.

View on HN

Absolutely, yes. There is a very deep link between compression and "understanding". I think we have every reason to believe that networks that can understand/"explain away" the content/statistics of a scene ought to be able to compress them better.

I presume someone (or likely many people) are working on exactly this.

Very cool! if anyone who comes across this particular thread knows about papers/research being written about this topic, I'd be very interested to learn more.

There is an award-winning compressor that uses many statistical models (and a 3-layered dense neural network) to compress the data losslessly: http://www.byronknoll.com/cmix.html

Also there is a free book that contains descriptions of various common and exotic compression formats http://www.mattmahoney.net/dc/dce.html

Overall I think we are yet to see the full potential of deep learning unleashed on data compression. For example the neural network in cmix compressor is quite primitive compared to modern architectures. Someone will certainly find a way to do better than that!

ah thanks. really appreciate the lead. do you yourself happen to have much experience in the space of machine learning or compression?

I think a fully trained neural network is, in a sense, a "lossy" (possibly very lossy) description of the training set.

Oh what I was imagining was more like if I was watching a news broadcast and so all I care about was the news anchor person, and the main on screen grapic/text. If you Compress down other things like the table or the background or wrote an algorithm to selectively stream resolutions tied to the object streamed instead of the frame streamed. Is that a viable form of "compression" using existing computer vision tech?

Autoencoders are a long known approach to use neural networks for lossy compression. Some papers about using these models as aids for compression are googleable.

Reply on news.ycombinator.com