Abstract:

The visual recognition of objects by humans in everyday life is typically rapid and effortless. Until a decade ago, animate visual systems were the only ones capable of this remarkable computational achievement. However, deep neural networks (DNNs) now achieve human-level classification performance on large sets of images of objects. Furthermore, a growing number of studies report similarities in the way DNNs and the human visual system process objects, suggesting that current DNNs may also be good models of human visual object recognition. In my talk I present psychophysical studies comparing object recognition in humans and DNNs, focusing on robustness, the development of human object recognition as well as the learning of novel objects. Given the reviewed studies and data, I argue that at present DNNs are highly valuable scientific tools but are not yet adequate computational models of human core object recognition behaviour.