Exploring Highly Efficient Compact Neural Networks for Image Classification

Xukai Xie, Yuan Zhou, Sun Yuan Kung

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Scopus citations

Abstract

Group convolution works well with many lightweight convolutional neural networks (CNNs) that can effectively reduce the number of parameters and computational cost. However, feature maps of different groups cannot communicate, which restricts their representation capability. To address this issue, in this work, we propose a novel convolution operation named Hierarchical Group Convolution (HGC) for creating computationally efficient neural networks. Different from standard group convolution which blocks the inter-group information exchange and induces the severe performance degradation, HGC hierarchically fuses the feature maps from each group and leverages the inter-group information effectively. Taking advantage of the proposed operation, we introduce an efficient compact network named HGCNet. Extensive experimental results on image classification task demonstrate that HGCNet obtain significant reduction of computational cost and the number of parameters, while achieving comparable performance over the prior CNN architectures designed for mobile devices.

Original languageEnglish (US)
Title of host publication2020 IEEE International Conference on Image Processing, ICIP 2020 - Proceedings
PublisherIEEE Computer Society
Pages2930-2934
Number of pages5
ISBN (Electronic)9781728163956
DOIs
StatePublished - Oct 2020
Externally publishedYes
Event2020 IEEE International Conference on Image Processing, ICIP 2020 - Virtual, Abu Dhabi, United Arab Emirates
Duration: Sep 25 2020Sep 28 2020

Publication series

NameProceedings - International Conference on Image Processing, ICIP
Volume2020-October
ISSN (Print)1522-4880

Conference

Conference2020 IEEE International Conference on Image Processing, ICIP 2020
Country/TerritoryUnited Arab Emirates
CityVirtual, Abu Dhabi
Period9/25/209/28/20

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Vision and Pattern Recognition
  • Signal Processing

Keywords

  • Lightweight network
  • group convolution
  • inter-group information exchange

Fingerprint

Dive into the research topics of 'Exploring Highly Efficient Compact Neural Networks for Image Classification'. Together they form a unique fingerprint.

Cite this