Dynamic group convolution for accelerating convolutional neural networks |
|
Author: | Su, Zhuo1; Fang, Linpu2; Kang, Wenxiong2; |
Organizations: |
1Center for Machine Vision and Signal Analysis, University of Oulu, Finland 2South China University of Technology, China 3National University of Defense Technology, China |
Format: | article |
Version: | accepted version |
Access: | open |
Online Access: | PDF Full Text (PDF, 4.1 MB) |
Persistent link: | http://urn.fi/urn:nbn:fi-fe202102154783 |
Language: | English |
Published: |
Springer Nature,
2020
|
Publish Date: | 2021-02-15 |
Description: |
AbstractReplacing 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. see all
|
Series: |
Lecture notes in computer science |
ISSN: | 0302-9743 |
ISSN-E: | 1611-3349 |
ISSN-L: | 0302-9743 |
ISBN: | 978-3-030-58539-6 |
ISBN Print: | 978-3-030-58538-9 |
Pages: | 138 - 155 |
DOI: | 10.1007/978-3-030-58539-6_9 |
OADOI: | https://oadoi.org/10.1007/978-3-030-58539-6_9 |
Host publication: |
Computer Vision – ECCV 2020. ECCV 2020 |
Host publication editor: |
Vedaldi, A. Bischof, H. Brox, T. Frahm, J. |
Conference: |
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 |
Subjects: | |
Funding: |
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 |
Detailed Information: |
331883 (Academy of Finland Funding decision) |
Copyright information: |
© 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. |