# Dynamic Group Convolution for Accelerating Convolutional Neural Networks

arXiv: https://arxiv.org/abs/2007.04242 · HTML: https://mlsanity.com/paper/2007.04242/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Jul 2020.

## Built on by (most cited first, 15 of 15)

- [Pixel Difference Networks for Efficient Edge Detection](https://mlsanity.com/paper/2108.07009/) (2021)
- [Revisiting Dynamic Convolution via Matrix Decomposition](https://mlsanity.com/paper/2103.08756/) (2021)
- [MicroNet: Improving Image Recognition with Extremely Low FLOPs](https://mlsanity.com/paper/2108.05894/) (2021)
- [Lightweight Pixel Difference Networks for Efficient Visual Representation Learning](https://mlsanity.com/paper/2402.00422/) (2024)
- [E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation](https://mlsanity.com/paper/2312.04727/) (2023)
- [Rapid Salient Object Detection with Difference Convolutional Neural Networks](https://mlsanity.com/paper/2507.01182/) (2025)
- [DGCNet: An Efficient 3D-Densenet based on Dynamic Group Convolution for Hyperspectral Remote Sensing Image Classification](https://mlsanity.com/paper/2307.06667/) (2023)
- [Progressive Channel-Shrinking Network](https://mlsanity.com/paper/2304.00280/) (2023)
- [Boosting Convolutional Neural Networks with Middle Spectrum Grouped Convolution](https://mlsanity.com/paper/2304.06305/) (2023)
- [Reverse Convolution and Its Applications to Image Restoration](https://mlsanity.com/paper/2508.09824/) (2025)
- [Dynamic Shuffle: An Efficient Channel Mixture Method](https://mlsanity.com/paper/2310.02776/) (2023)
- [MODIPHY: Multimodal Obscured Detection for IoT using PHantom Convolution-Enabled Faster YOLO](https://mlsanity.com/paper/2402.07894/) (2024)
- [Multi-Scale Tensorial Summation and Dimensional Reduction Guided Neural Network for Edge Detection](https://mlsanity.com/paper/2504.15770/) (2025)
- [Mixture of Channel Experts: Static Sparse Supports with Input-Adaptive Mixing for Pointwise Projections](https://mlsanity.com/paper/2608.23794/) (2026)
- [Overcoming Kernel Redundancy for Scaling Logic Gate Networks](https://mlsanity.com/paper/2610.01069/) (2026)

## Abstract (arXiv)

Replacing normal convolutions with group convolutions can significantly increase the computational efficiency of modern deep convolutional networks, which has been widely adopted in compact network architecture designs. However, existing group convolutions undermine the original network structures by cutting off some connections permanently resulting in significant accuracy degradation. In this paper, we propose dynamic group convolution (DGC) that adaptively selects which part of input channels to be connected within each group for individual samples on the fly. Specifically, we equip each group with a small feature selector to automatically select the most important input channels conditioned on the input images. Multiple groups can adaptively capture abundant and complementary visual/semantic features for each input image. The DGC preserves the original network structure and has similar computational efficiency as the conventional group convolution simultaneously. Extensive experiments on multiple image classification benchmarks including CIFAR-10, CIFAR-100 and ImageNet demonstrate its superiority over the existing group convolution techniques and dynamic execution methods. The code is available at https://github.com/zhuogege1943/dgc.