Аннотация:We propose a novel approach to reduce the computational cost of evaluation of
convolutional neural networks, a factor that has hindered their deployment in low-
power devices such as mobile phones. Inspired by the loop perforation technique
from source code optimization, we speed up the bottleneck convolutional layers by
skipping their evaluation in some of the spatial positions. We propose and analyze
several strategies of choosing these positions. We demonstrate that perforation
can accelerate modern convolutional networks such as AlexNet and VGG-16 by a
factor of
2
×
-
4
×
. Additionally, we show that perforation is complementary to the
recently proposed acceleration method of Zhang et al. [28].