ThreshNet: An Efficient DenseNet using Threshold Mechanism to Reduce Connections

by   Rui-Yang Ju, et al.

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.



There are no comments yet.


page 1


SpecNet: Spectral Domain Convolutional Neural Network

The memory consumption of most Convolutional Neural Network (CNN) archit...

ThresholdNet: Pruning Tool for Densely Connected Convolutional Networks

Deep neural networks have made significant progress in the field of comp...

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

"Lightweight convolutional neural networks" is an important research top...

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

Learning a particular task from a dataset, samples in which originate fr...

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...

HarDNet: A Low Memory Traffic Network

State-of-the-art neural network architectures such as ResNet, MobileNet,...

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.