.png){kind=icon}
Return
Decoupled decoder with Gaussian prototypes for weakly-supervised semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.eswa.2026.134478.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• We propose a decoupled decoder to reduce interference between CLIP and DINO features.
• We design a novel Gaussian Prototype Module to model class-wise feature distributions.
• We present a novel single-stage framework for weakly supervised semantic segmentation.
Keywords:
Weakly supervised semantic segmentation
CLIP
DINO
Gaussian prototype
Decoupled decoder
Journal
IF:
7.5
Papers:
3.0W
Citations:
10.2W
Organization
No organization information available
Cited Papers
No cited papers available