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

arXiv: https://arxiv.org/abs/1809.01330 · HTML: https://mlsanity.com/paper/1809.01330/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Sep 2018.

## Built on by (most cited first, 10 of 10)

- [Enabling Design Methodologies and Future Trends for Edge AI: Specialization and Co-design](https://mlsanity.com/paper/2103.15750/) (2021)
- [DMSANet: Dual Multi Scale Attention Network](https://mlsanity.com/paper/2106.08382/) (2021)
- [FalconNet: Factorization for the Light-weight ConvNets](https://mlsanity.com/paper/2306.06365/) (2023)
- [Self-Distribution Binary Neural Networks](https://mlsanity.com/paper/2103.02394/) (2021)
- [Learning Versatile Convolution Filters for Efficient Visual Recognition](https://mlsanity.com/paper/2109.09310/) (2021)
- [Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution](https://mlsanity.com/paper/2304.06305/) (2023)
- [The Evolution of the Interplay Between Input Distributions and Linear Regions in Networks](https://mlsanity.com/paper/2310.18725/) (2023)
- [Cooperative Learning for Cost-Adaptive Inference](https://mlsanity.com/paper/2312.08532/) (2023)
- [Training-Time Batch Normalization Reshapes Local Partition Geometry in Piecewise-Affine Networks](https://mlsanity.com/paper/2605.04946/) (2026)
- [IR2Net: Information Restriction and Information Recovery for Accurate Binary Neural Networks](https://mlsanity.com/paper/2210.02637/) (2022)

## Abstract (arXiv)

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.