LightSeg: a light-weight network for real-time semantic segmentation

Run Ye; Benhui Li; Bin Yan; Zhiyong Li

doi:10.1117/12.2601022

30 June 2021 LightSeg: a light-weight network for real-time semantic segmentation

Run Ye, Benhui Li, Bin Yan, Zhiyong Li

Proceedings Volume 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021); 118780N (2021) https://doi.org/10.1117/12.2601022
Event: Thirteenth International Conference on Digital Image Processing, 2021, Singapore, Singapore

Abstract

Semantic segmentation is an intensive prediction task with a wide range of applications, such as mobile phones, robots, autonomous driving and other mobile devices. The computing power of these mobile devices is often very limited, which limits the application of semantic segmentation. This paper designs a simple and efficient end-to-end real-time segmentation algorithm. Our algorithm model is an asymmetric encoder-decoder structure, which is composed of two parts: the first part is a lightweight encoder, which consists of a dual-path fast downsampling module and a lightweight three-stage feature extractor; the second part is an asymmetric decoding classifier, which consists of a mutual attention feature fusion module, a lightweight atrous spatial pyramid pooling module, and a classifier. Our method has only 0.64M parameters, and achieves 68.4% mIoU, 67.5 FPS with an image of 10242048 resolutions, also reachs 203.8 FPS, 61.9% mIoU with 5121024 resolutions, on the Cityscapes test set on GTX1080Ti. Comprehensive experiments show that our method can reach the state-of-the-art level on the Cityscapes dataset in terms of accuracy and speed.

Citation Download Citation

Run Ye, Benhui Li, Bin Yan, and Zhiyong Li "LightSeg: a light-weight network for real-time semantic segmentation", Proc. SPIE 11878, Thirteenth International Conference on Digital Image Processing (ICDIP 2021), 118780N (30 June 2021); https://doi.org/10.1117/12.2601022

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