Deep learning models fail to capture the configural nature of human shape perception
Summary: A hallmark of human object perception is sensitivity to the holistic configuration of the local shape features of an object. Deep convolutional neural networks (DCNNs) are currently the dominant models for object recognition processing in the visual cortex, but do they capture this configur...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2022-09-01
|
| Series: | iScience |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2589004222011853 |