Structured Convolutions for Efficient Neural Network Design release_ps4p56bginaork2dvmr2voh76q

by Yash Bhalgat, Yizhe Zhang, Jamie Lin, Fatih Porikli

Released as a article .

2020  

Abstract

In this work, we tackle model efficiency by exploiting redundancy in the implicit structure of the building blocks of convolutional neural networks. We start our analysis by introducing a general definition of Composite Kernel structures that enable the execution of convolution operations in the form of efficient, scaled, sum-pooling components. As its special case, we propose Structured Convolutions and show that these allow decomposition of the convolution operation into a sum-pooling operation followed by a convolution with significantly lower complexity and fewer weights. We show how this decomposition can be applied to 2D and 3D kernels as well as the fully-connected layers. Furthermore, we present a Structural Regularization loss that promotes neural network layers to leverage on this desired structure in a way that, after training, they can be decomposed with negligible performance loss. By applying our method to a wide range of CNN architectures, we demonstrate "structured" versions of the ResNets that are up to 2× smaller and a new Structured-MobileNetV2 that is more efficient while staying within an accuracy loss of 1 We also show similar structured versions of EfficientNet on ImageNet and HRNet architecture for semantic segmentation on the Cityscapes dataset. Our method performs equally well or superior in terms of the complexity reduction in comparison to the existing tensor decomposition and channel pruning methods.
In text/plain format

Archived Files and Locations

application/pdf  1.1 MB
file_txjbg3thgnfqlpobjl6g5fjfe4
arxiv.org (repository)
web.archive.org (webarchive)
Read Archived PDF
Preserved and Accessible
Type  article
Stage   submitted
Date   2020-08-06
Version   v1
Language   en ?
arXiv  2008.02454v1
Work Entity
access all versions, variants, and formats of this works (eg, pre-prints)
Catalog Record
Revision: 1f100b27-d44c-498a-b4a2-cab25f791bff
API URL: JSON