research data . Dataset . 2018

No title available

Open Access
  • Published: 26 Dec 2018
Abstract
<div><p>Deep convolutional networks (DCNNs) are achieving previously unseen performance in object classification, raising questions about whether DCNNs operate similarly to human vision. In biological vision, shape is arguably the most important cue for recognition. We tested the role of shape information in DCNNs trained to recognize objects. In Experiment 1, we presented a trained DCNN with object silhouettes that preserved overall shape but were filled with surface texture taken from other objects. Shape cues appeared to play some role in the classification of artifacts, but little or none for animals. In Experiments 2–4, DCNNs showed no ability to classify g...
Subjects
free text keywords: Neuroscience, Ecology, Sociology, Science Policy, 69999 Biological Sciences not elsewhere classified, shape information, object shape Deep convolutional networks, Deep convolutional networks, DCNN
Communities
Science and Innovation Policy Studies
Download from
figshare
Dataset . 2018
Provider: figshare
Any information missing or wrong?Report an Issue