< Back to Article
Deep convolutional networks do not classify based on global object shape
Fig 23
Stimuli used in Experiment 5a.
Top row: the original silhouette images, all correctly classified by VGG-19 (appearing in top-five). Bottom row: Scrambled images on which the network was tested.
doi: https://doi.org/10.1371/journal.pcbi.1006613.g023