GRASP improves pathology segmentation by injecting anatomical pseudo-labels and transformer-aligned anatomical features into standard segmentation models without retraining the anatomy model.
In: Proceedings of the IEEE conference on computer vision and pattern recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
GRASPing Anatomy to Improve Pathology Segmentation
GRASP improves pathology segmentation by injecting anatomical pseudo-labels and transformer-aligned anatomical features into standard segmentation models without retraining the anatomy model.