Perturbation Tolerance of Deep Neural Networks and Humans in Material Recognition
Perturbation Tolerance of Deep Neural Networks and Humans in Material Recognition is a scholarly work, published in 2018 in ''Journal of Vision''. The main subjects of the publication include convolutional neural network, deep learning, categorization, artificial intelligence, computer vision, artificial neural network, pattern recognition, and computer science. The authors previously (Liu et al., VSS2016) showed that a convolutional neural network (CNN) could recognize material categories of Flickr Material Database (FMD; Sharan et al., 2013) as accurately as humans.