CVMar 7, 2018

HENet:A Highly Efficient Convolutional Neural Networks Optimized for Accuracy, Speed and Storage

arXiv:1803.02742v25 citationsHas Code
Originality Incremental advance
AI Analysis

This work addresses the need for faster and more storage-efficient CNNs, particularly for real-time applications, but it appears incremental as it builds on existing architectures.

The authors tackled the problem of improving the efficiency of convolutional neural networks for real-time performance by proposing HENet, a model that combines advantages from ResNet, DenseNet, and ShuffleNet, resulting in efficiency more than 1 times higher than ShuffleNet on datasets like CIFAR-10/100 and SVHN.

In order to enhance the real-time performance of convolutional neural networks(CNNs), more and more researchers are focusing on improving the efficiency of CNN. Based on the analysis of some CNN architectures, such as ResNet, DenseNet, ShuffleNet and so on, we combined their advantages and proposed a very efficient model called Highly Efficient Networks(HENet). The new architecture uses an unusual way to combine group convolution and channel shuffle which was mentioned in ShuffleNet. Inspired by ResNet and DenseNet, we also proposed a new way to use element-wise addition and concatenation connection with each block. In order to make greater use of feature maps, pooling operations are removed from HENet. The experiments show that our model's efficiency is more than 1 times higher than ShuffleNet on many open source datasets, such as CIFAR-10/100 and SVHN.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes