December 12, 2019 02:20 pm
Six example images that fool AI from the ObjectNet dataset. | Image: MIT
Original Link: https://www.theverge.com/2019/12/12/21012410/machine-vision-ai-adversarial-images-dataset-objectnet-mit-algorithms
The mind-bending confusion of hammer on a bed shows computer vision is far from solved
Six example images that fool AI from the ObjectNet dataset. | Image: MIT
Machine vision has been one of the biggest success stories of the AI boom, enabling everything from automated medical scans to self-driving cars. But while the accuracy of all-seeing algorithms has improved massively, these systems can still be confused by images that humans have no problem deciphering.
Just look at the collage at the top of this story. None of these pictures are particularly confusing, right? You can see hammers, oven gloves, and although the top middle image is a bit tricky to decipher, it doesn’t take long to work out it’s a chair viewed from above. A cutting-edge machine vision algorithm, meanwhile, would probably only identify one or two of these objects. That’s a huge downgrade for systems that are supposed to...
Original Link: https://www.theverge.com/2019/12/12/21012410/machine-vision-ai-adversarial-images-dataset-objectnet-mit-algorithms
Share this article:
Tweet
View Full Article
The Verge
The Verge is an ambitious multimedia effort founded in 2011More About this Source Visit The Verge