I did some experiments that really highlight how heavily image recognition algorithms depend on probability - and how unprepared they are for surrealism. #machinelearning
@janellecshane You might find this interesting:
It's an art project, which uses AI to generate patterns, which fool other AIs.
Those patterns for example make an AI recognize a tank painted with it as an umbrella or similar.
@freundTech Thanks for the link! I hope they'll post some of the results sometime - it would be interesting to read.
My student trained some classifiers on ImageNet and the result was that all quadrupeds were predicted as dog.
We then switched to MS Coco and found that -- while the caption generation is often good for a laugh -- the object detection was not pretty good in most cases.
Not detecting sheep on trees maybe shows that the Deep Networks now have actually a good "common sense"
I wonder how it fare on the columbine harvester picture?
@deeds Ha, what a picture! As you predicted, Microsoft Azure (trained on Coco, I believe) reported it as "a crowd of people"
@deeds But Cloudsight is an interesting case! It seamlessly uses humans for the hard one and since the caption was part of the photo...
Object: "green and yellow combine harvester"
Scene: "This Look Like A Sick Concert Text"
@janellecshane Surrealism relies upon contextual comprehension.
That is an AI-hard problem, and until we have functionally structured AI designs, that will be very hard to achieve, and effectively impossible to prove if we do achieve it.
The Wandering Shop is a Mastodon instance initially geared for the science fiction and fantasy community but open to anyone. We want our 'local' timeline to have the feel of a coffee shop at a good convention: tables full of friendly conversation on a wide variety of topics. We welcome everyone who wants to participate, so long as you're willing to abide by our code of conduct.