.png){kind=icon}
.png){kind=icon}
Return
Fine-grained vision–language alignment for medical image segmentation
.png){kind=icon}
PRE
AI
J
Q
H
J
C
DOI：10.1016/j.bspc.2026.111205.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Develop a domain-adaptive vision–language framework for medical image segmentation. • Propose soft multi-positive contrastive learning models one-to-many image–text pairs. • Propose high-level semantic alignment to regularize vision–language representations. • Propose a multi-latent attention-based fusion module to integrate semantic priors.
Journal
IF:
4.9
Papers:
9.7K
Citations:
2.4W
Organization
Cited Papers