MFAFNet: A Lightweight and Efficient Network with Multi-Level Feature Adaptive Fusion for Real-Time Semantic Segmentation

Currently, real-time semantic segmentation networks are intensely demanded in resource-constrained practical applications, such as mobile devices, drones and autonomous driving systems. However, most of the current popular approaches have difficulty in obtaining sufficiently large receptive fields,...

Full description

Saved in:
Bibliographic Details
Published inSensors (Basel, Switzerland) Vol. 23; no. 14; p. 6382
Main Authors Lu, Kai, Cheng, Jieren, Li, Hua, Ouyang, Tianyu
Format Journal Article
LanguageEnglish
Published Switzerland MDPI AG 13.07.2023
MDPI
Subjects
Accuracy
Deep learning
feature fusion
lightweight model
Mobile devices
real time
semantic segmentation
Semantics
feature fusion
semantic segmentation
real time
lightweight model
Online AccessGet full text

Cover

More Information
Summary:Currently, real-time semantic segmentation networks are intensely demanded in resource-constrained practical applications, such as mobile devices, drones and autonomous driving systems. However, most of the current popular approaches have difficulty in obtaining sufficiently large receptive fields, and they sacrifice low-level details to improve inference speed, leading to decreased segmentation accuracy. In this paper, a lightweight and efficient multi-level feature adaptive fusion network (MFAFNet) is proposed to address this problem. Specifically, we design a separable asymmetric reinforcement non-bottleneck module, which designs a parallel structure to extract short- and long-range contextual information and use optimized convolution to increase the inference speed. In addition, we propose a feature adaptive fusion module that effectively balances feature maps with multiple resolutions to reduce the loss of spatial detail information. We evaluate our model with state-of-the-art real-time semantic segmentation methods on the Cityscapes and Camvid datasets. Without any pre-training and post-processing, our MFAFNet has only 1.27 M parameters, while achieving accuracies of 75.9% and 69.9% mean IoU with speeds of 60.1 and 82.6 FPS on the Cityscapes and Camvid test sets, respectively. The experimental results demonstrate that the proposed method achieves an excellent trade-off between inference speed, segmentation accuracy and model size.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1424-8220
1424-8220
DOI:10.3390/s23146382