Drop hand-crafted from the feature description
Browse files
README.md
CHANGED
|
@@ -17,7 +17,7 @@ pipeline_tag: image-classification
|
|
| 17 |
Trained model weights for RootScope.
|
| 18 |
|
| 19 |
RootScope takes a raw confocal root-tip cross-section TIFF, segments every cell
|
| 20 |
-
with Cellpose-SAM, describes each cell with
|
| 21 |
features plus fine-tuned DINOv2 embeddings, and classifies it into one of nine
|
| 22 |
anatomical cell types using an iterative tree-based ensemble.
|
| 23 |
|
|
|
|
| 17 |
Trained model weights for RootScope.
|
| 18 |
|
| 19 |
RootScope takes a raw confocal root-tip cross-section TIFF, segments every cell
|
| 20 |
+
with Cellpose-SAM, describes each cell with morpho-topological
|
| 21 |
features plus fine-tuned DINOv2 embeddings, and classifies it into one of nine
|
| 22 |
anatomical cell types using an iterative tree-based ensemble.
|
| 23 |
|