Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

Meta Releases New AI-Based Photo Segmentation Tool to Everybody

arstechnica.com

Post reply on HN
Print view View original

71–80 of 82 posts

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#71

Post by Name_Chawps »

sokoloff wrote: post #16
Name_Chawps wrote: post #13

Earlier quoted context omitted.

The weights are not "source".

That is likely true in the most pedantic sense, but in practice, if I create an algorithm that works by using a series of matrix transformations against a set of carefully chosen (read: "trained") matrices and I open-source only the matrix manipulation code but not the specially chosen matrices, I think there's a fair argument to say that I haven't open-sourced the entire algorithm. In the phrase "the model is open-s…

I'd be curious to know if you think open source companies should share all of their database records too.

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#72

Post by Name_Chawps »

flangola7 wrote: post #51
Name_Chawps wrote: post #13

Earlier quoted context omitted.

The weights are not "source".

The actual source code is not important. The source code can be printed on a single A4 page, the valuable final product is the weights you get after running the code for fifty million dollars of compute time.

If they start claiming they're "open weights" or "open final product" I'll be up in arms.

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#73

Post by sokoloff »

Name_Chawps wrote: post #71
sokoloff wrote: post #16

Earlier quoted context omitted.

That is likely true in the most pedantic sense, but in practice, if I create an algorithm that works by using a series of matrix transformations against a set of carefully chosen (read: "trained") matrices and I open-source only the matrix manipulation code but not the specially chosen matrices, I think there's a fair argument to say that I haven't open-sourced the entire algorithm. In the phrase "the model is open-s…

I'd be curious to know if you think open source companies should share all of their database records too.

I think of two broad categories of database records: transactional data (data created while running the system) and domain data (data created during development and shipped to production as part of the release process).

The former type of data I wouldn't expect to ever be open-sourced. The latter type might or might not be, depending on the intent of open-sourcing the related system.

If I created a human language translation system that used a SQL database to store the dictionary (domain) data and claimed the system was open-source without shipping the domain data, I think people would rightly say that the system was not fully opened.

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#74

Post by dvngnt_ »

bick_nyers wrote: post #44
graderjs wrote: post #24

I relly hope Meta (FB research) releases this wonderful noise reduction library: https://github.com/facebookresearch/denoiser I tested MANY while building various audio tech and this was by far the best (beats the shit out of all the python Pandas Hugging Face lists etc). Incredibly ability to cut noise (tho, it must be noted that perceptual improvements for humans do not usually increase machine transcription as AI…

Somewhat tangential question, have you looked for/found any audio models/tools that can be used for separating out individual voices to separate audio tracks automatically? Perhaps this is already possible with existing tools that I am uninitiated in.

meta has demucs which is the best I've used so far

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#75

Post by sokoloff »

Name_Chawps wrote: post #72
flangola7 wrote: post #51

Earlier quoted context omitted.

The actual source code is not important. The source code can be printed on a single A4 page, the valuable final product is the weights you get after running the code for fifty million dollars of compute time.

If they start claiming they're "open weights" or "open final product" I'll be up in arms.

They are claiming that. They are also delivering on that claim: https://github.com/facebookresearch/segment-anything#model-c...

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#76

Post by kristopolous »

NelsonMinar wrote: post #37
sillysaurusx wrote: post #9

Meta does stellar work in AI. I’m quite certain the recent DMCAs were a case of the left hand not knowing what the right hand is doing. This model is open source in every sense of the word, and they’ve now released two impactful models in the span of a month. This tweet chain is a pretty great overview: https://twitter.com/drjimfan/status/1643647849824161792?s=61...

The Economist had a recent overview of the AI competitive landscape that highlights Meta's outsize role thanks to their embrace of openness. https://www.economist.com/business/2023/03/26/big-tech-and-t...

They're well on their way to yahoo'ing themselves - valuable and significant software contributions for a platform nobody is using.

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#77

Post by ukuina »

bick_nyers wrote: post #44
graderjs wrote: post #24

I relly hope Meta (FB research) releases this wonderful noise reduction library: https://github.com/facebookresearch/denoiser I tested MANY while building various audio tech and this was by far the best (beats the shit out of all the python Pandas Hugging Face lists etc). Incredibly ability to cut noise (tho, it must be noted that perceptual improvements for humans do not usually increase machine transcription as AI…

Somewhat tangential question, have you looked for/found any audio models/tools that can be used for separating out individual voices to separate audio tracks automatically? Perhaps this is already possible with existing tools that I am uninitiated in.

Does Ultimate Vocal Remover 5 fit the bill?

Despite the name, it can also do audio separation.

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#78

Post by graderjs »

stephanos2k wrote: post #63
graderjs wrote: post #24

I relly hope Meta (FB research) releases this wonderful noise reduction library: https://github.com/facebookresearch/denoiser I tested MANY while building various audio tech and this was by far the best (beats the shit out of all the python Pandas Hugging Face lists etc). Incredibly ability to cut noise (tho, it must be noted that perceptual improvements for humans do not usually increase machine transcription as AI…

Have you tested https://hushaudioapp.com ? Its quality is amazing.

Have you tested the FB one?

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#79

Post by tomcam »

SimonPStevens wrote: post #62
tomcam wrote: post #59

Earlier quoted context omitted.

I’m glad Microsoft is open sourcing a lot of things. I have never, ever seen a convincing business case for their doing so, however. Not your opinion. A compelling business case.

The business case for open sourcing dev tooling is that more developers will use them and build on them and that brings more people to your platforms.

Sure. Any proof at all for that? I mean it's the obvious answer, but generally in business people who don't pay for things tend not to pay for things. In fact, in the enterprise having a big budget is the way you keep your corporate power. Free stuff isn't a way to keep your budget high.

Again, I would like to agree with your thinking. I just don't think the real world backs it up.

Re: Meta Releases New AI-Based Photo Segmentation Tool to Everybody

#80

Post by bane »

bick_nyers wrote: post #64
bane wrote: post #46

Earlier quoted context omitted.

That's called "speaker diarization" and there's quite a bit of work in the field. https://github.com/topics/speaker-diarization I have no idea what's good or the best, but there's a starting point!

Thank you for the proper terminology, googling these things in plain English just doesn't do it anymore

Not a problem and good luck!
Post reply on HN