VOILA performs universal CT segmentation by contrastively aligning voxels with text prompts and training on complexity-graded samples, achieving competitive Dice scores with far fewer trainable parameters.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
VOILA: Complexity-Aware Universal Segmentation of CT images by Voxel Interacting with Language
VOILA performs universal CT segmentation by contrastively aligning voxels with text prompts and training on complexity-graded samples, achieving competitive Dice scores with far fewer trainable parameters.