Update README.md
Browse files
README.md
CHANGED
|
@@ -17,6 +17,8 @@ pipeline_tag: object-detection
|
|
| 17 |
|
| 18 |
A YOLO11s model fine-tuned to detect UI elements in desktop screenshots. Trained on GroundCUA (55K screenshots, 3.56M human-verified annotations) with SAHI-style tiling (640x640, 20% overlap). Built for the [uitag](https://github.com/swaylenhayes/uitag) SoM pipeline, where it runs alongside Apple Vision to provide combined 90.8% detection coverage on ScreenSpot-Pro.
|
| 19 |
|
|
|
|
|
|
|
| 20 |
## What it detects
|
| 21 |
|
| 22 |
Nine element classes derived from GroundCUA's annotation taxonomy:
|
|
|
|
| 17 |
|
| 18 |
A YOLO11s model fine-tuned to detect UI elements in desktop screenshots. Trained on GroundCUA (55K screenshots, 3.56M human-verified annotations) with SAHI-style tiling (640x640, 20% overlap). Built for the [uitag](https://github.com/swaylenhayes/uitag) SoM pipeline, where it runs alongside Apple Vision to provide combined 90.8% detection coverage on ScreenSpot-Pro.
|
| 19 |
|
| 20 |
+
Experimental version for homework.
|
| 21 |
+
|
| 22 |
## What it detects
|
| 23 |
|
| 24 |
Nine element classes derived from GroundCUA's annotation taxonomy:
|