Add project page link and model description
Browse filesThis PR improves the model card by adding the project page link and a short description of the SegWithU framework. The existing metadata is already appropriate, so no changes are needed there.
README.md
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- en
|
|
|
|
| 5 |
pipeline_tag: image-segmentation
|
| 6 |
---
|
| 7 |
|
|
@@ -9,4 +9,6 @@ pipeline_tag: image-segmentation
|
|
| 9 |
|
| 10 |
[Preprint](https://huggingface.co/papers/2604.15271)
|
| 11 |
|
| 12 |
-
|
|
|
|
|
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
+
license: apache-2.0
|
| 5 |
pipeline_tag: image-segmentation
|
| 6 |
---
|
| 7 |
|
|
|
|
| 9 |
|
| 10 |
[Preprint](https://huggingface.co/papers/2604.15271)
|
| 11 |
|
| 12 |
+
SegWithU is a post-hoc framework for uncertainty estimation in medical image segmentation. It augments a frozen pretrained segmentation backbone with a lightweight uncertainty head, modeling uncertainty as perturbation energy with rank-1 posterior probes. It produces voxel-wise uncertainty maps for calibration and error detection in a single forward pass.
|
| 13 |
+
|
| 14 |
+
This page is only used to distribute the checkpoints. For code and docs please visit our [GitHub repository](https://github.com/ProjectNeura/SegWithU) or the [project page](https://segwithu.projectneura.org).
|