# Fully Learnable Group Convolution for Acceleration of Deep Neural Networks

arXiv: https://arxiv.org/abs/1904.00346 · HTML: https://mlsanity.com/paper/1904.00346/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 31 Mar 2019.

## Built on by (most cited first, 16 of 16)

- [Lightweight Deep Learning for Resource-Constrained Environments: A Survey](https://mlsanity.com/paper/2404.07236/) (2024)
- [CondenseNet V2: Sparse Feature Reactivation for Deep Networks](https://mlsanity.com/paper/2104.04382/) (2021)
- [DGCNet: An Efficient 3D-Densenet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image Classification](https://mlsanity.com/paper/2307.06667/) (2023)
- [Spatial-Spectral Hyperspectral Classification based on Learnable 3D Group Convolution](https://mlsanity.com/paper/2307.07720/) (2023)
- [Two-level Group Convolution](https://mlsanity.com/paper/2110.05060/) (2021)
- [On Evolving Attention Towards Domain Adaptation](https://mlsanity.com/paper/2103.13561/) (2021)
- [Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution](https://mlsanity.com/paper/2304.06305/) (2023)
- [Easy Ensemble: Simple Deep Ensemble Learning for Sensor-Based Human Activity Recognition](https://mlsanity.com/paper/2203.04153/) (2022)
- [Reverse Convolution and Its Applications to Image Restoration](https://mlsanity.com/paper/2508.09824/) (2025)
- [LearningGroup: A Real-Time Sparse Training on FPGA via Learnable Weight Grouping for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2210.16624/) (2022)
- [Dynamic Shuffle: An Efficient Channel Mixture Method](https://mlsanity.com/paper/2310.02776/) (2023)
- [Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training](https://mlsanity.com/paper/2409.19391/) (2024)
- [Differentiable Neural Architecture Learning for Efficient Neural Network Design](https://mlsanity.com/paper/2103.02126/) (2021)
- [Dynamic Neural Network Architectural and Topological Adaptation and Related Methods -- A Survey](https://mlsanity.com/paper/2108.10066/) (2021)
- [On-Sensor Binarized Fully Convolutional Neural Network with A Pixel Processor Array](https://mlsanity.com/paper/2202.00836/) (2022)
- [Balanced Group Convolution: An Improved Group Convolution Based on Approximability Estimates](https://mlsanity.com/paper/2310.12461/) (2023)

## Abstract (arXiv)

Benefitted from its great success on many tasks, deep learning is increasingly used on low-computational-cost devices, e.g. smartphone, embedded devices, etc. To reduce the high computational and memory cost, in this work, we propose a fully learnable group convolution module (FLGC for short) which is quite efficient and can be embedded into any deep neural networks for acceleration. Specifically, our proposed method automatically learns the group structure in the training stage in a fully end-to-end manner, leading to a better structure than the existing pre-defined, two-steps, or iterative strategies. Moreover, our method can be further combined with depthwise separable convolution, resulting in 5 times acceleration than the vanilla Resnet50 on single CPU. An additional advantage is that in our FLGC the number of groups can be set as any value, but not necessarily 2^k as in most existing methods, meaning better tradeoff between accuracy and speed. As evaluated in our experiments, our method achieves better performance than existing learnable group convolution and standard group convolution when using the same number of groups.