U.S. flag

An official website of the United States government, Department of Justice.

NCJRS Virtual Library

The Virtual Library houses over 235,000 criminal justice resources, including all known OJP works.
Click here to search the NCJRS Virtual Library

Accelerating Convolutional Neural Network via Structured Gaussian Scale Mixture Models: A Joint Grouping and Pruning Approach

NCJ Number
308374
Author(s)
Tao Huang; Jinshan Liu; Weisheng Dong; Fangfang Wu; Guangming Shi; Xin Li
Date Published
2020
Length
11 pages
Annotation

This publication offers a hybrid network compression technique for exploiting the prior knowledge of network parameters by Gaussian scale mixture (GSM) models.

Abstract

In this paper, the authors propose a hybrid network compression technique for exploiting the prior knowledge of network parameters by Gaussian scale mixture (GSM) models. Specifically, the collection of network parameters are characterized by GSM models and network pruning is formulated as a maximum a posteriori (MAP) estimation problem with a sparsity prior. The key novel insight brought by this work is that groups of parameters associated with the same channel are similar, which is analogous to the grouping of similar patches in natural images. Such observation inspires us to leverage powerful structured sparsity prior from image restoration to network compression - i.e., to develop a flexible filter-grouping strategy that not only promotes structured sparsity but also can be seamlessly integrated with the existing network pruning framework. Extensive experimental results on several popular DCNN models including VGGNet, ResNet and DenseNet have shown that the proposed GSM-based joint grouping and pruning method convincingly outperforms other competing approaches (including both pruning and non-pruning based methods). (Published Abstract Provided)