CoSAM improves domain generalization in 2D medical image segmentation by using a trained error decoder to correct SAM's prompt-free coarse masks and cyclically refining predictions with point, box, and mask prompts.
Sam-adapter: Adapting segment any- thing in underperformed scenes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CoSAM: Self-Correcting SAM for Domain Generalization in 2D Medical Image Segmentation
CoSAM improves domain generalization in 2D medical image segmentation by using a trained error decoder to correct SAM's prompt-free coarse masks and cyclically refining predictions with point, box, and mask prompts.