This is indistinguishable from something that would be hanging in an art museum, and anyone pretending otherwise only believes so because they know a priori that it is generated by ML.
Honestly I would consider buying something like this, though I'd never waste my money on something so pretentious from a human. This, however, is an achievement, and there's beauty in that.
Edit: in fact, if love to see two tests: a blind test with a series of humans, and a classifier trained to differentiate between machine and human generated art. I have no doubt that the humans would not score much better than chance - I bet only an artificial discriminator would be able to tell, and then only because of subtle differences in pixel distributions that humans won't perceive. Throw in a couple different GANs trained on different distributions and even a machine will have trouble telling the difference!
"This is indistinguishable from something that would be hanging in an art museum."
Haha, the exact opposite of my scroll through. I thought to myself: "These look like a clone stamp sampled and then vomited up all the lovely modernist paintings I've seen at art museums."
This is indistinguishable from something that would be hanging in an art museum, and anyone pretending otherwise only believes so because they know a priori that it is generated by ML.
I certainly couldn't distinguish an individual images from something I might see in a museum. At the same time, scrolling the images felt very different than scrolling through a series of images by a given artist or images from a given show.
This is what an image search for cubists and wikiart looks like. Also feels very different.
Which is just to say this sequence feels different. I couldn't tell if it's better or worse. It does feel bleak, opaque, oppressive, washed-out. All that is something some art aims for. But it could just be the randomness of the pictures, like they're well-spoken words in a language I don't know.
I think this is quite expected, since ANN constructs its own view on stuffs, which is basically deconstruction of images into local components, like local color relation and sub-patterns. Global composition and shapes will be destroyed in favor of local composition, which is pretty much what many modern abstract paintings were after.
While ANN can mass-produced stuffs like this, that doesn't mean it's gonna replace artists. It's gonna be the opposite: if artists learn through AIs, each of which trained on different sets of data (which can overlap), we will be able to see works in a different level. It's like go players study AlphaGo for new principles that humankind have missed.
Thanks for the reference! I think you've reminded of the vocabulary needed to express my impression of the images.
IE, That's definitely how the images feel - just texture and composition.
The thing is that I think that art involves using texture to "say" something. The artist puts combines represent of the physical world with reference to previous artists and images with composition. Some artists stress one or the other of these things - so that, yeah, a pure composition painting can definitely be "good enough to be in a museum". But a stream of painting like this definitely doesn't feel a museum or art as a whole.
Whilst these all the samples seem to have decent form, use of colour and space, one can quickly see derivate concepts and images from more famous original works and an excess of 3D forms. There's also a challenge in understanding the meaning of each painting. Also, a lot of penguin type shapes for some reason.
One of the tests you describe - a classifier trained to differentiate between machine and human generated art - is exactly what the ML GAN model is doing.
The generative adversarial network (GAN) has a generative part and a discriminative part which compete with each other. The generative model creates the images that you see in the gallery. The discriminative model tries to predicts whether an image is real or was generated. When it starts failing often, we know that the generative model is getting better (of course, the details are much more complicated).
I don't it's fair to call it pretentious if from a human but beautiful if from a computer. You even said it yourself
> ... anyone pretending otherwise only believes so because they know a priori that it is generated by ML.
To me, a large part of an artworks beauty comes from its ability to make me feel something. These works make me feel nothing at all. So I cannot call them beautiful.
The only reason these are indistinguishable from "pretentious" paintings is because those were used for a training set. Use a "non-pretentious" set and you will get corresponding generated art. Particular images generated are almost not the point, in my opinion.
I answered 18 correct answers out of 20. Do I qualify as an art critic now?
I assume that the AI generated art would be harder but what is the point really? I would only see the point if the model was trained with something else and ‘it came up with modern art looking images’.
And this works because modern art is flexible enough to allow all kinds of things. Why not do the test on generated text? AI still fails terribly on that mainly because it is not sentient, it does not actually understand anything of it
Honestly I would consider buying something like this, though I'd never waste my money on something so pretentious from a human. This, however, is an achievement, and there's beauty in that.
Edit: in fact, if love to see two tests: a blind test with a series of humans, and a classifier trained to differentiate between machine and human generated art. I have no doubt that the humans would not score much better than chance - I bet only an artificial discriminator would be able to tell, and then only because of subtle differences in pixel distributions that humans won't perceive. Throw in a couple different GANs trained on different distributions and even a machine will have trouble telling the difference!