.png){kind=icon}
.png){kind=icon}
Return
Causal unsupervised semantic segmentation
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2025.112173.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• Unsupervised framework for discretized pixel-level semantic groups without annotations. • Causal inference-based two-step intervention for controllable semantic segmentation. • Concept prototypes as mediators, trained via concept-wise self-supervised learning. • State-of-the-art results on five public datasets with extensive experiments.
Keywords:
Unsupervised learning
Causal inference
Semantic segmentation
Concept prototypes
Self-supervised learning
Journal
IF:
7.6
Papers:
1.3W
Citations:
4.5W
Organization
No organization information available