A Real-Time Semantic Segmentation Algorithm Based on Improved Lightweight Network

Cheng, Liu; Gao, Hongxia; Chen, An

doi:10.1109/isas49493.2020.9378857

Cited by 10 publications

(4 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared with the excellent real-time semantic segmentation methods in recent years, our MFAFNet achieved a more superior performance. Specifically, compared with MIFNet [ 12 ], DSANet [ 32 ], LightSeg [ 33 ], and CSRNet-light [ 34 ], the proposed MFAFNet not only has a more lightweight network structure and faster inference speed but also has a higher segmentation accuracy. Our method was also

and

higher than LRDNet [ 14 ] and LAANet [ 15 ] in MIOU.…”

Section: Resultsmentioning

confidence: 99%

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

Cheng

et al. 2023

Sensors

View full text Add to dashboard Cite

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.

show abstract

and

higher than LRDNet [ 14 ] and LAANet [ 15 ] in MIOU.…”

Section: Resultsmentioning

confidence: 99%

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

Cheng

et al. 2023

Sensors

View full text Add to dashboard Cite

show abstract

“…For example, MADNet [49] is a dense lightweight network designed to achieve stronger multiscale feature expression and feature correlation learning. In terms of feature extraction, Liu et al [50] constructed a network with expanded convolutions and attention modules, using pooling operations of different sizes to encode surrounding semantic information.…”

Section: Lightweight Networkmentioning

confidence: 99%

SDD-YOLO: A Lightweight, High-Generalization Methodology for Real-Time Detection of Strip Surface Defects

Wu,

Chen,

et al. 2024

Metals

View full text Add to dashboard Cite

Flat-rolled steel sheets are one of the major products of the metal industry. Strip steel’s production quality is crucial for the economic and safety aspects of humanity. Addressing the challenges of identifying the surface defects of strip steel in real production environments and low detection efficiency, this study presents an approach for strip defect detection based on YOLOv5s, termed SDD-YOLO. Initially, this study designs the Convolution-GhostNet Hybrid module (CGH) and Multi-Convolution Feature Fusion block (MCFF), effectively reducing computational complexity and enhancing feature extraction efficiency. Subsequently, CARAFE is employed to replace bilinear interpolation upsampling to improve image feature utilization; finally, the Bidirectional Feature Pyramid Network (BiFPN) is introduced to enhance the model’s adaptability to targets of different scales. Experimental results demonstrate that, compared to the baseline YOLOv5s, this method achieves a 6.3% increase in mAP50, reaching 76.1% on the Northeastern University Surface Defect Database for Detection (NEU-DET), with parameters and FLOPs of only 3.4MB and 6.4G, respectively, and FPS reaching 121, effectively identifying six types of defects such as Crazing and Inclusion. Furthermore, under the conditions of strong exposure, insufficient brightness, and the addition of Gaussian noise, the model’s mAP50 still exceeds 70%, demonstrating the model’s strong robustness. In conclusion, the proposed SDD-YOLO in this study features high accuracy, efficiency, and lightweight characteristics, making it applicable in actual production to enhance strip steel production quality and efficiency.

show abstract

“…Zhou Q et al [ 36 ] designed a lightweight encoder–decoder network for the real-time semantic segmentation of autonomous driving images. Liu C et al [ 37 ] constructed a network with extended convolution and attention modules as the backbone network for feature extraction and used pooling operations of different sizes to encode the surrounding semantic information on the extended pyramid pooling module ASPP. Liang H et al [ 38 ] proposed a lightweight end-to-end road damage detection network, which can quickly, automatically and accurately identify and classify various types of road damage.…”

Section: Related Workmentioning

confidence: 99%

Strip Surface Defect Detection Algorithm Based on YOLOv5

et al. 2023

View full text Add to dashboard Cite

In order to improve the detection accuracy of the surface defect detection of industrial hot rolled strip steel, the advanced technology of deep learning is applied to the surface defect detection of strip steel. In this paper, we propose a framework for strip surface defect detection based on a convolutional neural network (CNN). In particular, we propose a novel multi-scale feature fusion module (ATPF) for integrating multi-scale features and adaptively assigning weights to each feature. This module can extract semantic information at different scales more fully. At the same time, based on this module, we build a deep learning network, CG-Net, that is suitable for strip surface defect detection. The test results showed that it achieved an average accuracy of 75.9 percent (mAP50) in 6.5 giga floating-point operation (GFLOPs) and 105 frames per second (FPS). The detection accuracy improved by 6.3% over the baseline YOLOv5s. Compared with YOLOv5s, the reference quantity and calculation amount were reduced by 67% and 59.5%, respectively. At the same time, we also verify that our model exhibits good generalization performance on the NEU-CLS dataset.

show abstract

A Real-Time Semantic Segmentation Algorithm Based on Improved Lightweight Network

Cited by 10 publications

References 8 publications

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

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

SDD-YOLO: A Lightweight, High-Generalization Methodology for Real-Time Detection of Strip Surface Defects

Strip Surface Defect Detection Algorithm Based on YOLOv5

Contact Info

Product

Resources

About