MSCFNet: A Lightweight Network With Multi-Scale Context Fusion for Real-Time Semantic Segmentation

In recent years, how to strike a good trade-off between accuracy, inference speed, and model size has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones. In this study, we devise a nov...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on intelligent transportation systems Vol. 23; no. 12; pp. 25489 - 25499
Main Authors: Gao, Guangwei, Xu, Guoan, Yu, Yi, Xie, Jin, Yang, Jian, Yue, Dong
Format: Journal Article
Language:English
Published: New York IEEE 01.12.2022
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accuracy
Asymmetry
Coders
Context
context fusion
Convolution
Datasets
Ear
Encoders-Decoders
encoder–decoder architecture
Feature extraction
Image segmentation
Lightweight
lightweight network
Modules
Parameters
Real time
Real-time semantic segmentation
Real-time systems
Semantic segmentation
Semantics
Task analysis
ISSN:1524-9050, 1558-0016
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In recent years, how to strike a good trade-off between accuracy, inference speed, and model size has become the core issue for real-time semantic segmentation applications, which plays a vital role in real-world scenarios such as autonomous driving systems and drones. In this study, we devise a novel lightweight network using a multi-scale context fusion (MSCFNet) scheme, which explores an asymmetric encoder-decoder architecture to alleviate these problems. More specifically, the encoder adopts some developed efficient asymmetric residual (EAR) modules, which are composed of factorization depth-wise convolution and dilation convolution. Meanwhile, instead of complicated computation, simple deconvolution is applied in the decoder to further reduce the amount of parameters while still maintaining the high segmentation accuracy. Also, MSCFNet has branches with efficient attention modules from different stages of the network to well capture multi-scale contextual information. Then we combine them before the final classification to enhance the expression of the features and improve the segmentation efficiency. Comprehensive experiments on challenging datasets have demonstrated that the proposed MSCFNet, which contains only 1.15M parameters, achieves 71.9% Mean IoU on the Cityscapes testing dataset and can run at over 50 FPS on a single Titan XP GPU configuration.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1524-9050
1558-0016
DOI:10.1109/TITS.2021.3098355