Deep convolutional neural networks (DCNNs) do not see objects in the same way that humans do, according to researchers, and this could be dangerous in real-world artificial intelligence (Al) applications.
DCNNs are the most commonly used type for detecting patterns in images and videos.
“Our results explain why deep AI models fail under certain conditions and point to the need to consider tasks beyond object recognition in order to understand visual processing in the brain,” said researcher James Elder from York University in Toronto.
“These deep models tend to take ‘shortcuts’ when solving complex recognition tasks. While these shortcuts may work in many cases, they can be dangerous in some of the real-world AI applications we are currently working on with our industry and government partners,” Elder added.
The team used novel visual stimuli called “Frankensteins” in the study, which was published in the journal iScience, to investigate how the human brain and DCNNs process holistic, configural object properties.
“Frankensteins are simply objects that have been taken apart and put back together the wrong way around. As a result, they have all the right local features, but in the wrong places,” Elder said.
The researchers discovered that while Frankensteins confuse the human visual system, DCNNs do not, revealing an insensitivity to configural object properties.
According to the researchers, changes to training and architecture intended to make networks more brain-like did not result in configural processing, and none of the networks could accurately predict trial-by-trial human object judgements.
“We speculate that to match human configural sensitivity, networks must be trained to solve a broader range of object tasks beyond category recognition,” Elder noted.
