ChannelNets: Compact and Efficient Convolutional Neural Networks via Channel-Wise Convolutions

TL;DR

ChannelNets introduce a novel, lightweight CNN architecture using channel-wise convolutions to significantly reduce model size and computational cost while maintaining accuracy, especially compressing the classification layer.

Contribution

This work presents the first compression of the fully-connected classification layer using channel-wise convolutions, creating efficient CNNs called ChannelNets.

Findings

Achieve fewer parameters and lower computational cost than prior mobile CNNs.

Maintain accuracy comparable to larger models on ImageNet.

First to successfully compress the classification layer in CNNs.

Abstract

Convolutional neural networks (CNNs) have shown great capability of solving various artificial intelligence tasks. However, the increasing model size has raised challenges in employing them in resource-limited applications. In this work, we propose to compress deep models by using channel-wise convolutions, which re- place dense connections among feature maps with sparse ones in CNNs. Based on this novel operation, we build light-weight CNNs known as ChannelNets. Channel- Nets use three instances of channel-wise convolutions; namely group channel-wise convolutions, depth-wise separable channel-wise convolutions, and the convolu- tional classification layer. Compared to prior CNNs designed for mobile devices, ChannelNets achieve a significant reduction in terms of the number of parameters and computational cost without loss in accuracy. Notably, our work represents the first attempt to compress the fully-connected classification layer, which usually accounts for about 25% of total parameters in compact CNNs. Experimental results on the ImageNet dataset demonstrate that ChannelNets achieve consistently better performance compared to prior methods.