Peters, B. and Kriegeskorte, N. (2021) Capturing the objects of vision with neural networks. Nature Human Behaviour, 5(9), pp. 1127-1144. (doi: 10.1038/s41562-021-01194-6) (PMID:34545237)
Full text not currently available from Enlighten.
Abstract
Human visual perception carves a scene at its physical joints, decomposing the world into objects, which are selectively attended, tracked and predicted as we engage our surroundings. Object representations emancipate perception from the sensory input, enabling us to keep in mind that which is out of sight and to use perceptual content as a basis for action and symbolic cognition. Human behavioural studies have documented how object representations emerge through grouping, amodal completion, proto-objects and object files. By contrast, deep neural network models of visual object recognition remain largely tethered to sensory input, despite achieving human-level performance at labelling objects. Here, we review related work in both fields and examine how these fields can help each other. The cognitive literature provides a starting point for the development of new experimental tasks that reveal mechanisms of human object perception and serve as benchmarks driving the development of deep neural network models that will put the object into object recognition.
Item Type: | Articles |
---|---|
Additional Information: | B.P. has received funding from the EU Horizon 2020 research and innovation programme under the Marie Skłodowska-Curie grant agreement no. 841578. |
Status: | Published |
Refereed: | Yes |
Glasgow Author(s) Enlighten ID: | Peters, Dr Benjamin |
Authors: | Peters, B., and Kriegeskorte, N. |
College/School: | College of Medical Veterinary and Life Sciences > School of Psychology & Neuroscience |
Journal Name: | Nature Human Behaviour |
Publisher: | Nature Research |
ISSN: | 2397-3374 |
ISSN (Online): | 2397-3374 |
University Staff: Request a correction | Enlighten Editors: Update this record