Hacker News Reader

Comment by chris_overseas | Hacker News Reader

The same thing happens for Vincent van Gogh, and presumably others too.

A good measure for whether you're more of a celebrity or an artist is how much of your face a google-image trained AI thinks belongs in your work.

Well what if the artist has a popular self portrait?

Smoke comes out of the computer, and Captain Kirk notches another victory for humanity.

Frida Kahlo comes to mind.

She's a rare exception in that she's mostly known for her self-portraits. Most other famous artists are mostly known for other things.

Again, if the training data was labeled well enough, confusion about this sort of thing shouldn't happen.

Either labelled well, or you have enough data and a good enough algorithm so that the computer can figure it out.

> A good measure for whether you're more of a celebrity or an artist is how much of your face a google-image trained AI thinks belongs in your work.

That this happens at all is evidence that the training data hasn't been curated, cleaned, or labeled well enough.

While it is the case the dataset isn’t well curated or perfectly labeled, it could just mean that grammar is not understood - the labels could be clear to a human, whether the image is a picture of Bob Ross or a painting by him. But the training misses that relationship. Even with poorly labeled data, I suspect AI will eventually figure out which labels are more likely to be poor and deal with it appropriately.

In the reverse direction, you can try:

A horse rides an astronaut

And you will probably generate an astronaut riding a horse. It’s not a poor description of what we want; our assumptions about how grammar should work aren’t being honored.

Not a problem with the Banksy images!

Reply on news.ycombinator.com