.png){kind=icon}
.png){kind=icon}
Return
Dense Multiscale Inference Network for Lightweight Salient Object Detection of Strip Steel Surface Defects
.png){kind=icon}
PRE
AI
Y
X
Y
B
J
Z
D
DOI：10.1016/j.patrec.2026.05.002.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Multi-Scale Inference Network (DMINet) is proposed for surface defect detection in strip steel. • A dense multiscale fusion module (DMS) is proposed to aggregate feature. • Dense Multi-scale Correlation (DMC) module is proposed and employ it as the core component of a lightweight decode.
Keywords:
DMINet
DMS
DMC
surface defect detection
lightweight inference
Journal
IF:
3.3
Papers:
7.8K
Citations:
1.6W
Organization
Cited Papers