Aero⁃engine lockwire instance segmentation method based on improved Mask R⁃CNN

Table 1. Tab.1Experimental environment
View table
View in Article
Table 1. Tab.1Experimental environment
名称配置
操作系统 Ubuntu 20.04
CPU Intel Xeon Sliver 4310 CPU @ 2.10 GHz
GPU NVIDIA RTX A5000
显存 24 GB
编程语言 Python 3.9
开发环境 Pytorch 1.10.1 + CUDA11.3

Table 2. Tab.2Results of ablation experiments
View table
View in Article
Table 2. Tab.2Results of ablation experiments
模型
Mask
R⁃CNN
Gamma DSConv CBAM A_AP50 / %
1 √ 76.71
2 √ √ 78.94
3 √ √ √ 80.02
4 √ √ √ 80.91
5 √ √ √ √ 82.54

Table 3. Tab.3Results of contrast experiments
View table
View in Article
Table 3. Tab.3Results of contrast experiments
模型 A_AP50 / %
Mask R⁃CNN 76.71
SOLOv2 69.80
改进Mask R⁃CNN 82.54

Tools

Get Citation

Copy Citation Text

Fengfei ZHANG, Junhua SUN. Aero⁃engine lockwire instance segmentation method based on improved Mask R⁃CNN[J]. Metrology & Measurement Technology, 2025, 45(1): 96

Download Citation

EndNote(RIS)BibTex Plain Text

Set citation alerts for article

Save article for my favorites

Paper Information

Category: Theory and Method

Received: Dec. 1, 2024

Accepted: --

Published Online: Jul. 23, 2025

The Author Email:

DOI:10.11823/j.issn.1674-5795.2025.01.07

Topics

Table 1. Tab.1Experimental environment

Table 1. Tab.1Experimental environment

Table 2. Tab.2Results of ablation experiments

Table 2. Tab.2Results of ablation experiments

Table 3. Tab.3Results of contrast experiments

Table 3. Tab.3Results of contrast experiments