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

Open Sourcing a Deep Learning Solution for Detecting NSFW Images

yahooeng.tumblr.com

Post reply on HN
Print view View original

101–110 of 153 posts

Re: Open Sourcing a Deep Learning Solution for Detecting NSFW Images

#101

Post by Joof »

derefr wrote: post #82
Asooka wrote: post #44

Earlier quoted context omitted.

Interesting thought - doesn't every single porn producer now have a valid copyright claim on the trained network? I don't see how you can argue this isn't a derivative work based on the movies they produced.

I was debating with a friend about just this: whether a text-to-speech model is a derivative work of audio recordings by a given speaker, such that they'd then have claim on ownership of it. (You could almost certainly create an [overfit] model that could re-generate the original performance of a text from said text.) Moot if it was a work-for-hire, of course; but if I, say, created a Samuel L. Jackson speech model b…

I imagine you couldn't put his name on it which would be a huge deal if you wanted to sell it.

Re: Open Sourcing a Deep Learning Solution for Detecting NSFW Images

#102

Post by Houshalter »

XCSme wrote: post #15
brianwawok wrote: post #5

So can it be reversed to become the ultimate porn-finding neural network?

When you said "reversed" I thought about it being a porn-generative neural network. Just enter your favorite keywords and an unique, tailored to your needs scene will be generated just for you!

This has been done, sort of. NSFW: http://deepdickdreams.tumblr.com/

Re: Open Sourcing a Deep Learning Solution for Detecting NSFW Images

#103

Post by Joof »

NicoJuicy wrote: post #17

We are not releasing the training images or other details due to the nature of the data, but instead we open source the output model which can be used for classification by a developer. I'm guessing the one who had to input the data/images had a fun time at work :p

Or they just turned safe search off and collected everything that doesn't also turn up on moderate search.

Re: Open Sourcing a Deep Learning Solution for Detecting NSFW Images

#104

Post by imh »

zardo wrote: post #22
XCSme wrote: post #15

Earlier quoted context omitted.

When you said "reversed" I thought about it being a porn-generative neural network. Just enter your favorite keywords and an unique, tailored to your needs scene will be generated just for you!

As long as what you need is a nightmarish version of the requested scene. What happens here with generating illegal content? If you put a public text->image gan up, and someone uses it to generate child porn, are you responsible? How could you make sure it couldn't?

I was wondering about illegal content in a totally different sense. I know from personal experience that overfitted generative models end up just memorizing the data set you trained it on. Say I overfit a model on Shakespeare, and you ask it to generate Shakespeare-like sonnets. It will do a fantastic job because it will just spit out one of his sonnets verbatim. Claiming that my network wrote it is ludicrous. The line is fuzzy where it's not overfitting and starts to generate its own content. For what you're talking about, if your model learns entirely from other people's movies, at what point is it not just a super weird codec for those people's IP?

Re: Open Sourcing a Deep Learning Solution for Detecting NSFW Images

#105

Post by mattthebaker »

ganwar wrote: post #66

To be precise they are only releasing the already trained model. The associated dataset is not being made public. Thus, it is meant to be for off the shelf use rather than being able to tinker with the network to produce nuanced results.

Or they just don't want to be distributing gigabytes of porn... most of which is probably under copyright.

Making the data set available and whether you can tinker with or retrain it are very different things.

Re: Open Sourcing a Deep Learning Solution for Detecting NSFW Images

#106

Post by gozur88 »

gizmo686 wrote: post #42
artursapek wrote: post #35

Earlier quoted context omitted.

Would computer generated child porn be illegal? No children are harmed in its creation.

No " (8) “child pornography” means any visual depiction, including any photograph, film, video, picture, or computer or computer-generated image or picture, whether made or produced by electronic, mechanical, or other means, of sexually explicit conduct, where— (A) the production of such visual depiction involves the use of a minor engaging in sexually explicit conduct; (B) such visual depiction is a digital image, c…

Wouldn't that make it illegal under 8B?

Re: Open Sourcing a Deep Learning Solution for Detecting NSFW Images

#107

Post by the_af »

bahro wrote: post #12

I should update my sexy map finder: http://exclav.es/2016/05/20/sexy-maps/

Those are some hot map pictures!

I don't understand how Google's algorithm can be misled into finding sexiness in those. I imagine it has something to do with skin tones or flesh colors, but then what about the high-contrast patchwork of green and brown fields Google finds "likely to contain adult content"? That's totally puzzling.

The confusion with medical images is way more understandable. If you squint, you can almost imagine those are pics of skin cancer or lesions.

Oddly enough, I even see violence in the "violent" picture. In an abstract, Rorschach Test sort of way. Well done, Google!

Re: Open Sourcing a Deep Learning Solution for Detecting NSFW Images

#109

Post by joshvm »

pjreddie wrote: post #62
joshmn wrote: post #56

I'm not a deep learning person whatsoever, but I do have an interesting use case that I won't disclose publicly: Is there a way to build this, and output detections based on the, ugh, object it has detected? e.g. penis 0.94 vagina 0.01

Yes. You would have to have a large training set with these labels but it would be pretty straightforward to train. You would probably want a tagging model not a classifier because there could be multiple objects of interest in the same image. If you get me the training data I could train a model for you pretty quickly.

What's the current ML pet method for multi-label image classification? It seems like you could string together a bunch of individual classifiers e.g. "Scene contains dog", "Scene contains cat", but is there an efficient (and effective) way of doing it in one go? Does it significantly increase the complexity of the network? I would imagine a cat detector would be far simpler than a cat and/or dog detector.
Post reply on HN