Flow group convolution: group convolution with channels information interaction

Bohan Li; Zuguo He; Xiang Ye; Fengnan Li; Yong Li

doi:10.1117/12.2589375

27 January 2021 Flow group convolution: group convolution with channels information interaction

Bohan Li, Zuguo He, Xiang Ye, Fengnan Li, Yong Li

Proceedings Volume 11720, Twelfth International Conference on Graphics and Image Processing (ICGIP 2020); 117202H (2021) https://doi.org/10.1117/12.2589375
Event: Twelfth International Conference on Graphics and Image Processing, 2020, Xi'an, China

Abstract

Group convolution can significantly reduce the computational cost by dividing the feature map channels into groups and then convolution operation is applied within each group. However, evenly dividing channels will cause the isolation between divided groups, i.e., no interaction between groups. To address the channel isolation problem, we proposed flow group convolution (FGConv) that utilizes different but overlapped input channels to compute output channels and enhance the interaction of different groups. FGConv can be easily applied to the existing networks and reduce their computational cost. We replace the original convolution with FGConv in ResNets and validate them on CIFAR-10 and CIFAR-100 benchmarks. Experiments results demonstrate that FGConv performs better than existing group convolution techniques.

Citation Download Citation

Bohan Li, Zuguo He, Xiang Ye, Fengnan Li, and Yong Li "Flow group convolution: group convolution with channels information interaction", Proc. SPIE 11720, Twelfth International Conference on Graphics and Image Processing (ICGIP 2020), 117202H (27 January 2021); https://doi.org/10.1117/12.2589375

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available