
Deep Convolutional Networks do not Make Classifications Based on Global Object Shape
Author(s) -
Nicholas Baker,
Hongjing Lu,
Gennady Erlikhman,
Philip J. Kellman
Publication year - 2018
Publication title -
journal of vision
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.126
H-Index - 113
ISSN - 1534-7362
DOI - 10.1167/18.10.904
Subject(s) - silhouette , artificial intelligence , pattern recognition (psychology) , object (grammar) , computer science , context (archaeology) , ellipse , minimum bounding box , computer vision , convolutional neural network , cuboid , enhanced data rates for gsm evolution , image (mathematics) , mathematics , geometry , geography , archaeology