Deep Convolutional Networks do not Make Classifications Based on Global Object Shape
Deep Convolutional Networks do not Make Classifications Based on Global Object Shape is a scholarly work, published in 2018 in ''Journal of Vision''. The main subjects of the publication include image, object, convolutional neural network, Enhanced Data Rates for GSM Evolution, rectangular cuboid, artificial intelligence, ellipse, silhouette, computer vision, minimum bounding box, glossary of archaeology, Bioimage informatics, pattern recognition, and computer science. The authors tested whether DCNNs utilize object shape information.