Designing By Training: Acceleration Neural Network For Fast High-Dimensional Convolution

Authors:
Longquan Dai Nanjing University of Science and Technology
Liang Tang CASA Environmental Technology Co., Ltd and CASA EM&EW; IOT Research Center
Yuan Xie Chinese Academy of Sciences
Jinhui Tang Nanjing University of Science and Technology

Introduction:

The high-dimensional convolution is widely used in various disciplines but has a serious performance problem due to its high computational complexity.Over the decades, people took a handmade approach to design fast algorithms for the Gaussian convolution.

Abstract:

The high-dimensional convolution is widely used in various disciplines but has a serious performance problem due to its high computational complexity. Over the decades, people took a handmade approach to design fast algorithms for the Gaussian convolution. Recently, requirements for various non-Gaussian convolutions have emerged and are continuously getting higher. However, the handmade acceleration approach is no longer feasible for so many different convolutions since it is a time-consuming and painstaking job. Instead, we propose an Acceleration Network (AccNet) which turns the work of designing new fast algorithms to training the AccNet. This is done by: 1, interpreting splatting, blurring, slicing operations as convolutions; 2, turning these convolutions to $g$CP layers to build AccNet. After training, the activation function $g$ together with AccNet weights automatically define the new splatting, blurring and slicing operations. Experiments demonstrate AccNet is able to design acceleration algorithms for a ton of convolutions including Gaussian/non-Gaussian convolutions and produce state-of-the-art results.

You may want to know: