ThreshNet: An Efficient DenseNet using Threshold Mechanism to Reduce Connections

01/09/2022
by   Rui-Yang Ju, et al.
0

With the continuous development of neural networks in computer vision tasks, more and more network architectures have achieved outstanding success. As one of the most advanced neural network architectures, DenseNet shortcuts all feature maps to solve the problem of model depth. Although this network architecture has excellent accuracy at low MACs (multiplications and accumulations), it takes excessive inference time. To solve this problem, HarDNet reduces the connections between feature maps, making the remaining connections resemble harmonic waves. However, this compression method may result in decreasing model accuracy and increasing MACs and model size. This network architecture only reduces the memory access time, its overall performance still needs to be improved. Therefore, we propose a new network architecture using threshold mechanism to further optimize the method of connections. Different numbers of connections for different convolutional layers are discarded to compress the feature maps in ThreshNet. The proposed network architecture used three datasets, CIFAR-10, CIFAR-100, and SVHN, to evaluate the performance for image classifications. Experimental results show that ThreshNet achieves up to 60 DenseNet, and up to 35 compared to HarDNet on these datasets.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

05/27/2019

SpecNet: Spectral Domain Convolutional Neural Network

The memory consumption of most Convolutional Neural Network (CNN) archit...
08/28/2021

ThresholdNet: Pruning Tool for Densely Connected Convolutional Networks

Deep neural networks have made significant progress in the field of comp...
04/29/2021

Condensation-Net: Memory-Efficient Network Architecture with Cross-Channel Pooling Layers and Virtual Feature Maps

"Lightweight convolutional neural networks" is an important research top...
06/24/2020

Feature-dependent Cross-Connections in Multi-Path Neural Networks

Learning a particular task from a dataset, samples in which originate fr...
02/16/2019

RES-SE-NET: Boosting Performance of Resnets by Enhancing Bridge-connections

One of the ways to train deep neural networks effectively is to use resi...
09/03/2019

HarDNet: A Low Memory Traffic Network

State-of-the-art neural network architectures such as ResNet, MobileNet,...
11/05/2020

Conflicting Bundles: Adapting Architectures Towards the Improved Training of Deep Neural Networks

Designing neural network architectures is a challenging task and knowing...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.