Su Z., Fang L., Kang W., Hu D., Pietikäinen M., Liu L. (2020) Dynamic Group Convolution for Accelerating Convolutional Neural Networks. In: Vedaldi A., Bischof H., Brox T., Frahm JM. (eds) Computer Vision – ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol 12351. Springer, Cham. https://doi.org/10.1007/978-3-030-58539-6_9
Dynamic group convolution for accelerating convolutional neural networks
|Author:||Su, Zhuo1; Fang, Linpu2; Kang, Wenxiong2;|
1Center for Machine Vision and Signal Analysis, University of Oulu, Finland
2South China University of Technology, China
3National University of Defense Technology, China
|Online Access:||PDF Full Text (PDF, 4.1 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe202102154783
|Publish Date:|| 2021-02-15
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.
Lecture notes in computer science
|Pages:||138 - 155|
Computer Vision – ECCV 2020. ECCV 2020
|Host publication editor:||
European Conference on Computer Vision
|Type of Publication:||
A4 Article in conference proceedings
|Field of Science:||
113 Computer and information sciences
213 Electronic, automation and communications engineering, electronics
This work was partially supported by the Academy of Finland under grant 331883 and the National Natural Science Foundation of China under Grant 61872379. The authors also wish to acknowledge CSC IT Center for Science, Finland, for computational resources.
|Academy of Finland Grant Number:||
331883 (Academy of Finland Funding decision)
© Springer Nature Switzerland AG 2020. This is a post-peer-review, pre-copyedit version of an article published in Computer Vision – ECCV 2020. ECCV 2020. The final authenticated version is available online at: https://doi.org/10.1007/978-3-030-58539-6_9.