Hetconv: Heterogeneous kernel-based convolutions for deep cnns

Pravendra Singh, Vinay Kumar Verma, Piyush Rai, Vinay P. Namboodiri

Research output: Chapter or section in a book/report/conference proceedingChapter in a published conference proceeding

89 Citations (SciVal)
116 Downloads (Pure)

Abstract

We present a novel deep learning architecture in which the convolution operation leverages heterogeneous kernels. The proposed HetConv (Heterogeneous Kernel-Based Convolution) reduces the computation (FLOPs) and the number of parameters as compared to standard convolution operation while still maintaining representational efficiency. To show the effectiveness of our proposed convolution, we present extensive experimental results on the standard convolutional neural network (CNN) architectures such as VGG and ResNet. We find that after replacing the standard convolutional filters in these architectures with our proposed HetConv filters, we achieve 3X to 8X FLOPs based improvement in speed while still maintaining (and sometimes improving) the accuracy. We also compare our proposed convolutions with group/depth wise convolutions and show that it achieves more FLOPs reduction with significantly higher accuracy.

Original languageEnglish
Title of host publicationProceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
PublisherIEEE
Pages4830-4839
Number of pages10
ISBN (Electronic)9781728132938
DOIs
Publication statusPublished - 9 Jan 2020
Event32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, USA United States
Duration: 16 Jun 201920 Jun 2019

Publication series

NameProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume2019-June
ISSN (Print)1063-6919

Conference

Conference32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019
Country/TerritoryUSA United States
CityLong Beach
Period16/06/1920/06/19

Keywords

  • Categorization
  • Computer Vision Theory
  • Deep Learning
  • Recognition: Detection
  • Retrieval

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Fingerprint

Dive into the research topics of 'Hetconv: Heterogeneous kernel-based convolutions for deep cnns'. Together they form a unique fingerprint.

Cite this