.png){kind=icon}
.png){kind=icon}
Return
Cross-layer context boundary guided network for crack segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.conbuildmat.2025.143975.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A dual-encoder network fusing transformers and CNNs for crack segmentation is proposed. • A bidirectional fusion module is proposed to explore cross-layer context. • A boundary-guided Interaction module is proposed to enhance object boundary awareness. • Experiments were conducted to verify our performance on three public datasets. • Ablation experiments were performed to validate the effectiveness of each component.
Journal
IF:
8
Papers:
4.5W
Citations:
27.9W