Log In Sign Up

Dynamic Group Convolution for Accelerating Convolutional Neural Networks

by   Zhuo Su, et al.

Replacing normal convolutions with group convolutions can significantly increase the computational efficiency of modern deep convolution 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 convolutions 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


Interleaved Group Convolutions for Deep Neural Networks

In this paper, we present a simple and modularized neural network archit...

Training convolutional neural networks with cheap convolutions and online distillation

The large memory and computation consumption in convolutional neural net...

Merging and Evolution: Improving Convolutional Neural Networks for Mobile Applications

Compact neural networks are inclined to exploit "sparsely-connected" con...

MUXConv: Information Multiplexing in Convolutional Neural Networks

Convolutional neural networks have witnessed remarkable improvements in ...

Exploiting Learned Symmetries in Group Equivariant Convolutions

Group Equivariant Convolutions (GConvs) enable convolutional neural netw...

CondenseNet: An Efficient DenseNet using Learned Group Convolutions

Deep neural networks are increasingly used on mobile devices, where comp...

Dynamic Convolutions: Exploiting Spatial Sparsity for Faster Inference

Modern convolutional neural networks apply the same operations on every ...

Code Repositories


Dynamic Group Convolution for Accelerating Convolutional Neural Networks (ECCV 2020)

view repo