Modelpedia
Work in progress
About
Findings
Models
Concepts
Methods
Datasets
Sources
Light
Dark
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
2024-01-16
· ICLR 2024 poster ·
anchor
Findings
IC-1618
SAM alone has limited generalization for semantic segmentation, producing ambiguous multi-mask outputs without semantic categories
IC-1619
DINOv2's patch-level features outperform CLIP and MAE for cross-image semantic feature matching