ThresholdNet: Pruning Tool for Densely Connected Convolutional Networks

by   Rui-Yang Ju, et al.

Deep neural networks have made significant progress in the field of computer vision. Recent studies have shown that depth, width and shortcut connections of neural network architectures play a crucial role in their performance. One of the most advanced neural network architectures, DenseNet, has achieved excellent convergence rates through dense connections. However, it still has obvious shortcomings in the usage of amount of memory. In this paper, we introduce a new type of pruning tool, threshold, which refers to the principle of the threshold voltage in MOSFET. This work employs this method to connect blocks of different depths in different ways to reduce the usage of memory. It is denoted as ThresholdNet. We evaluate ThresholdNet and other different networks on datasets of CIFAR10. Experiments show that HarDNet is twice as fast as DenseNet, and on this basis, ThresholdNet is 10 rate than HarDNet.



There are no comments yet.


page 1


ThreshNet: An Efficient DenseNet using Threshold Mechanism to Reduce Connections

With the continuous development of neural networks in computer vision ta...

SparseNet: A Sparse DenseNet for Image Classification

Deep neural networks have made remarkable progresses on various computer...

Pruning neural networks: is it time to nip it in the bud?

Pruning is a popular technique for compressing a neural network: a large...

Comprehensive Online Network Pruning via Learnable Scaling Factors

One of the major challenges in deploying deep neural network architectur...

Compact Neural Representation Using Attentive Network Pruning

Deep neural networks have evolved to become power demanding and conseque...

Universal Approximation by a Slim Network with Sparse Shortcut Connections

Over recent years, deep learning has become a mainstream method in machi...

ParaNet - Using Dense Blocks for Early Inference

DenseNets have been shown to be a competitive model among recent convolu...
This week in AI

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