.png){kind=icon}
.png){kind=icon}
Return
Multi-scale Vision Mamba-UNet: A Mamba-based method for retinal vessel segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.bspc.2025.108435.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We apply multi-scale attention to Mamba before linear iteration to refine features. • The attention mechanism improves the quality of the input feature map. • We fuse high-level and low-level features to enrich the input for linear iteration.
Keywords:
multi-scale attention
feature refinement
high-level and low-level feature fusion
linear iteration
input feature quality
Journal
IF:
4.9
Papers:
9.8K
Citations:
2.4W