A novel method to regenerate an optimal CNN by exploiting redundancy patterns in the network

Sirish Kumar Pasupuleti, Narasinga Rao Miniskar, Vasanthakumar Rajagopal, Raj Narayana Gadde

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Deploying Convolution Neural Networks (CNN) based computer vision applications on low-power embedded devices is challenging due to massive computation and memory bandwidth requirements. Research is on-going on faster algorithms, network pruning, and model compression techniques to produce light-weight networks. In this paper, we propose a novel method which exploits a redundancy pattern in the network to regenerate an efficient and functionally identical CNN for a given network. We identify the pattern based on the layer parameters (kernel size and stride) and data flow analysis among the layers to avoid the redundant processing and memory requirements while maintaining identical accuracy. Our proposed method augments the state-of-the-art pruning and model compression techniques to achieve further performance boost-up. The proposed method is experimented with the Caffe [1] framework for ResNet-50 [2] inference on Samsung smartphone with an octa-core ARM Cortex-A53 processor. The results show an improvement of 4x in performance and memory at layer level, ∼22% performance improvement and 6% memory reduction at network level.

Original languageEnglish
Title of host publication2017 IEEE International Conference on Image Processing, ICIP 2017 - Proceedings
PublisherIEEE Computer Society
Pages4407-4411
Number of pages5
ISBN (Electronic)9781509021758
DOIs
StatePublished - Jul 2 2017
Externally publishedYes
Event24th IEEE International Conference on Image Processing, ICIP 2017 - Beijing, China
Duration: Sep 17 2017Sep 20 2017

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2017-September
ISSN (Print)1522-4880

Conference

Conference24th IEEE International Conference on Image Processing, ICIP 2017
Country/TerritoryChina
CityBeijing
Period09/17/1709/20/17

Keywords

  • Caffe
  • Convolution Neural Networks
  • Deep Neural Networks
  • Light-weight network
  • ResNet

Fingerprint

Dive into the research topics of 'A novel method to regenerate an optimal CNN by exploiting redundancy patterns in the network'. Together they form a unique fingerprint.

Cite this