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 language | English |
---|---|
Title of host publication | Proceedings - 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 |
Publisher | IEEE |
Pages | 4830-4839 |
Number of pages | 10 |
ISBN (Electronic) | 9781728132938 |
DOIs | |
Publication status | Published - 9 Jan 2020 |
Event | 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 - Long Beach, USA United States Duration: 16 Jun 2019 → 20 Jun 2019 |
Publication series
Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
---|---|
Volume | 2019-June |
ISSN (Print) | 1063-6919 |
Conference
Conference | 32nd IEEE/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2019 |
---|---|
Country/Territory | USA United States |
City | Long Beach |
Period | 16/06/19 → 20/06/19 |
Funding
Pravendra Singh acknowledges his travel support from Google. Vinay Verma acknowledges support from Visves-varaya fellowship.
Keywords
- Categorization
- Computer Vision Theory
- Deep Learning
- Recognition: Detection
- Retrieval
ASJC Scopus subject areas
- Software
- Computer Vision and Pattern Recognition