# Feature Evaluation of Deep Convolutional Neural Networks for Object Recognition and Detection

25 Sep 2015Hirokatsu KataokaKenji IwataYutaka Satoh

In this paper, we evaluate convolutional neural network (CNN) features using the AlexNet architecture and very deep convolutional network (VGGNet) architecture. To date, most CNN researchers have employed the last layers before output, which were extracted from the fully connected feature layers... (read more)

PDF Abstract