# VarGNet: Variable Group Convolutional Neural Network for Efficient Embedded Computing

arXiv: https://arxiv.org/abs/1907.05653 · HTML: https://mlsanity.com/paper/1907.05653/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 12 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [MixFaceNets: Extremely Efficient Face Recognition Networks](https://mlsanity.com/paper/2107.13046/) (2021)
- [PocketNet: Extreme Lightweight Face Recognition Network using Neural Architecture Search and Multi-Step Knowledge Distillation](https://mlsanity.com/paper/2108.10710/) (2021)
- [EdgeFace: Efficient Face Recognition Model for Edge Devices](https://mlsanity.com/paper/2307.01838/) (2023)
- [QuantFace: Towards Lightweight Face Recognition by Synthetic Data Low-bit Quantization](https://mlsanity.com/paper/2206.10526/) (2022)
- [EFaR 2023: Efficient Face Recognition Competition](https://mlsanity.com/paper/2308.04168/) (2023)
- [Deep Network Pruning: A Comparative Study on CNNs in Face Recognition](https://mlsanity.com/paper/2405.18302/) (2024)
- [SqueezerFaceNet: Reducing a Small Face Recognition CNN Even More Via Filter Pruning](https://mlsanity.com/paper/2307.10697/) (2023)

## Abstract (arXiv)

In this paper, we propose a novel network design mechanism for efficient embedded computing. Inspired by the limited computing patterns, we propose to fix the number of channels in a group convolution, instead of the existing practice that fixing the total group numbers. Our solution based network, named Variable Group Convolutional Network (VarGNet), can be optimized easier on hardware side, due to the more unified computing schemes among the layers. Extensive experiments on various vision tasks, including classification, detection, pixel-wise parsing and face recognition, have demonstrated the practical value of our VarGNet.