Lednet: A Lightweight Encoder-Decoder Network for Real-Time Semantic Segmentation

The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem, namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation....

Full description

Saved in:
Bibliographic Details
Published in:Proceedings - International Conference on Image Processing pp. 1860 - 1864
Main Authors: Wang, Yu, Zhou, Quan, Liu, Jia, Xiong, Jian, Gao, Guangwei, Wu, Xiaofu, Latecki, Longin Jan
Format: Conference Proceeding
Language:English
Published: IEEE 01.09.2019
Subjects:
CNN
Computer architecture
Convolution
Decoding
Encoder-decoder network
Lightweight network
Real-time semantic segmentation
Real-time systems
ResNet
Semantics
Task analysis
Training
ISSN:2381-8549
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem, namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation. More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters, and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset.
ISSN:2381-8549
DOI:10.1109/ICIP.2019.8803154