Skip to main content
Search

# In-Context Segmentation

1 related articles

Subscribe to updates
  1. arXiv

    Frozen features can still segment biomedical images: CAST skips training and beats the strongest baseline by 12.34 Dice points across eight benchmarks

    In biomedical images, adjacent structures look alike, so patch-by-patch matching on frozen visual features can rank anatomically wrong regions above correct correspondences. CAST adds two tests to a frozen DINOv3 backbone: a stability test that uses feature variation under geometric transformations for global debiasing and patch-specific calibration, and a coherence test that checks candidate matches against neighborhood feature contrast and layout consistency. Across eight biomedical benchmarks spanning 2D and 3D, cross-subject and cross-modality transfer, CAST reaches 72.39% average Dice, 12.34 percentage points above the strongest baseline SegGPT at 60.05%, and ranks first in all six volumetric settings.

You’re all caught up