PerforatedCNNs: Acceleration through Elimination of Redundant Convolutions
This addresses deployment challenges for low-power devices like mobile phones, offering an incremental improvement that complements existing methods.
The paper tackled the problem of high computational cost in convolutional neural networks (CNNs) by proposing perforation to skip convolutions at some spatial positions, achieving 2x-4x acceleration on networks like AlexNet and VGG-16.
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 2x - 4x. Additionally, we show that perforation is complementary to the recently proposed acceleration method of Zhang et al.