SAM-Mix couples a GradCAM classifier to SAM through auto-generated box prompts, reaching 0.948 Dice on liver segmentation from 50 labeled CT slices.
Data We validate our proposed SAM-Mix method with the pub- licly available Liver Tumor Segmentation (LiTS) Benchmark [16]
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
-
Annotation-Efficient Task Guidance for Medical Segment Anything
SAM-Mix couples a GradCAM classifier to SAM through auto-generated box prompts, reaching 0.948 Dice on liver segmentation from 50 labeled CT slices.