Why computers are so bad at comparing objects - Futurity

You are free to share this article under the Attribution 4.0 International license. New research sheds light on why computers are so bad at a class of tasks that even young children have no problem with: determining whether two objects in an image are the same or different. "There's a lot of excitement about what computer vision has been able to achieve…" Computer vision algorithms have come a long way in the past decade. They've been shown to be as good or better than people at tasks like categorizing dog or cat breeds, and they have the remarkable ability to identify specific faces out of a sea of millions. In a paper they presented last week at the annual meeting of the Cognitive Science Society, the team examines why computer vision algorithms fail at comparison tasks and suggests avenues toward smarter systems.