If you can identify what’s in these images, you’re smarter than AI | Artificial Intelligence - The Verge

James Vincent, cover machines with brains for The Verge, despite being a human without one reports, Researchers collect confusing images to expose the weak spots in AI vision.

From top to bottom and left to right, these images are misidentified as “digital clock,” “lighthouse,” “organ”, “syringe,” “toucan,” “Persian cat.”

Computer vision has improved massively in recent years, but it’s still capable of making serious errors. So much so that there’s a whole field of research dedicated to studying pictures that are routinely misidentified by AI, known as “adversarial images.” Think of them as optical illusions for computers. While you see a cat up a tree, the AI sees a squirrel.

There’s a great need to study these images. As we put machine vision systems at the heart of new technology like AI security cameras and self driving cars, we’re trusting that computers see the world the same way we do. Adversarial images prove that they don’t.

But while a lot attention in this field is focused on pictures that have been specifically designed to fool AI (like this 3D printed turtle which Google’s algorithms mistakes for a gun), these sorts of confusing visuals occur naturally as well. This category of images is, if anything, more worrying, as it shows that vision systems can make unforced errors...

Some research suggests that rather than looking at images holistically, considering the overall shape and content, algorithms focus in on specific textures and detail. The findings presented in this dataset seem to support this interpretation, when, for example, pictures that show clear shadows on a brightly-lit surface are misidentified as sundials. AI is essentially missing the wood for the trees. 

Read more... 

Source: The Verge