this post was submitted on 05 Jun 2024
662 points (99.8% liked)
LGBTQ+
2719 readers
98 users here now
founded 1 year ago
MODERATORS
you are viewing a single comment's thread
view the rest of the comments
view the rest of the comments
I wonder if the AI is detecting that the photo is taken from further away and below eye level which is more likely for a photo of a man, rather than looking at her facial characteristics?
It's possible to manipulate an image in a way that the original and the new one are indistinguishable to the human eye, but the AI model gives completely different results.
Like this helpful graphic I found
Or... edit the HTML...
You think someone would do that? Just go on the internet and lie?
Yeah, this is a valid point, if this is the exact case or not I don't know, but a lot of people don't realize a lot of the weird biases that can appear in the training data.
Like that AI trained to detect ig a mole was cancer or not. A lot of the training data that was cancer had rulers in them. So the AI learned rulers are cancerous.
I could easily see something stupid like angle the picture was taken from being something the AI erroniously assumed to be useful for determining biological sex in this case.