Deep convolutional neural networks (DCNNs) don’t see objects the way humans do — using configural shape perception — and that could be dangerous in real-world AI applications. The study employed novel visual stimuli called ‘Frankensteins’ to explore how the human brain and DCNNs process holistic, configural object properties.
Even smartest AI models don’t match human visual processing: How deep-network models take potentially dangerous ‘shortcuts’ in solving complex recognition tasks
