HetConv: Heterogeneous Kernel-Based Convolutions for Deep CNNs

03/11/2019
by   Pravendra Singh, et al.
0

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 vgg2014very and ResNet 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
11/01/2019

Comb Convolution for Efficient Convolutional Architecture

Convolutional neural networks (CNNs) are inherently suffering from massi...
research
12/03/2020

MelGlow: Efficient Waveform Generative Network Based on Location-Variable Convolution

Recent neural vocoders usually use a WaveNet-like network to capture the...
research
09/28/2020

Kernel Based Progressive Distillation for Adder Neural Networks

Adder Neural Networks (ANNs) which only contain additions bring us a new...
research
02/09/2023

Gaussian Mask Convolution for Convolutional Neural Networks

Square convolution is a default unit in convolutional neural networks as...
research
10/09/2018

Penetrating the Fog: the Path to Efficient CNN Models

With the increasing demand to deploy convolutional neural networks (CNNs...
research
09/30/2018

Benchmarks of ResNet Architecture for Atrial Fibrillation Classification

In this work we apply variations of ResNet architecture to the task of a...
research
05/21/2021

Hyper-Convolution Networks for Biomedical Image Segmentation

The convolution operation is a central building block of neural network ...

Please sign up or login with your details

Forgot password? Click here to reset