Update ScreenParser for ScreenParse v2

Upload detector checkpoint trained on ScreenParse v2 leaf-element annotations and update the model card. The v1 detector remains available on the v1 branch.

README.md

@@ -18,18 +18,22 @@ library_name: ultralytics
 
 # ScreenParser
 
-**ScreenParser** is a YOLO-based UI element detector fine-tuned on [ScreenParse](https://huggingface.co/docling-project/screenparse), a large-scale dataset of 771K web page screenshots with dense annotations across **55 UI element classes**. Given a screenshot, it detects and classifies every visible UI component with bounding boxes and confidence scores.
+**ScreenParser** is a YOLO-based UI element detector fine-tuned on [ScreenParse](https://huggingface.co/datasets/docling-project/screenparse), a large-scale dataset of web page screenshots with dense UI annotations across **55 UI element classes**. Given a screenshot, it detects and classifies visible UI components with bounding boxes and confidence scores.
+
+## News
+
+- **May 2026**: Updated `main` with the detector trained on ScreenParse v2, which contains 1,447,100 high-quality training screenshots, leaf-element annotations, and varied viewport resolutions. The original detector trained on ScreenParse v1 is retained on the `v1` branch.
 
 - **Developed by**: IBM Research - ETH Zurich
 - **Model type**: Object detection (YOLO11-L)
 - **License**: [Apache 2.0](https://www.apache.org/licenses/LICENSE-2.0)
-- **Paper**: [ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing](TODO)
-- **Code**: [GitHub](TODO)
-- **Dataset**: [docling-project/screenparse](https://huggingface.co/docling-project/screenparse)
+- **Paper**: [ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing](https://arxiv.org/abs/2602.14276)
+- **Code**: https://github.com/Saidgurbuz/screenparse
+- **Dataset**: [docling-project/screenparse](https://huggingface.co/datasets/docling-project/screenparse)
 
 ## Model Summary
 
-ScreenParser is a [YOLO11-Large](https://docs.ultralytics.com/models/yolo11/) model (25.4M parameters) fine-tuned at 1280px resolution on ScreenParse.
+ScreenParser is a [YOLO11-Large](https://docs.ultralytics.com/models/yolo11/) model fine-tuned at 1280px resolution on ScreenParse v2. The v2 detector uses the filtered leaf-element annotations released with the current dataset `main` branch.
 
 ### Supported Classes (55)
 
@@ -41,10 +45,8 @@ Table, Column/Browser, Button, Utility Button, App Icon, Navigation Bar, Status
 
 ```python
 from ultralytics import YOLO
-from PIL import Image
 
 model = YOLO("docling-project/ScreenParser")
-
 results = model.predict("screenshot.png", imgsz=1280, conf=0.10, iou=0.10)
 
 for r in results:
@@ -61,21 +63,14 @@ import os
 from ultralytics import YOLO
 
 model = YOLO("docling-project/ScreenParser")
-IMAGE_DIR = "screenshots/"
-
+image_dir = "screenshots/"
 images = sorted(
-    os.path.join(IMAGE_DIR, f) for f in os.listdir(IMAGE_DIR)
+    os.path.join(image_dir, f)
+    for f in os.listdir(image_dir)
     if f.lower().endswith((".png", ".jpg", ".jpeg"))
 )
 
 results = model.predict(images, imgsz=1280, conf=0.10, iou=0.10, batch=16)
-
-for path, r in zip(images, results):
-    print(f"--- {os.path.basename(path)} ({len(r.boxes)} elements) ---")
-    for box, cls_id, conf in zip(r.boxes.xyxy, r.boxes.cls, r.boxes.conf):
-        x1, y1, x2, y2 = box.tolist()
-        label = model.names[int(cls_id)]
-        print(f"  {label:20s}  conf={conf:.2f}  bbox=({int(x1)}, {int(y1)}, {int(x2-x1)}, {int(y2-y1)})")
 ```
 
 ### Save Visualizations
@@ -88,11 +83,16 @@ results = model.predict("screenshot.png", imgsz=1280, conf=0.10, iou=0.10, save=
 # Annotated image saved under runs/detect/predict/
 ```
 
-**Training data**: [ScreenParse](https://huggingface.co/docling-project/screenparse) — 771K web page screenshots with dense annotations across 55 UI element classes. Annotations were generated through automated DOM extraction, IoU-based filtering, and VLM-based refinement.
+## Training Data
+
+The current `main` checkpoint was trained on [ScreenParse v2](https://huggingface.co/datasets/docling-project/screenparse), which provides 1,447,100 high-quality training screenshots and 25,575,213 UI element annotations. The dataset uses filtered leaf-element annotations to reduce noisy nested boxes and includes multiple viewport resolutions.
+
+The original ScreenParser checkpoint trained on ScreenParse v1 remains available with `revision="v1"`.
 
 ## Limitations
 
-- Does not produce text content for detected elements (bounding boxes and labels only) — pair with an OCR model or [ScreenVLM](https://huggingface.co/docling-project/ScreenVLM) for text extraction
+- Produces bounding boxes and element labels only; it does not produce text content for detected elements. Pair it with OCR or [ScreenVLM](https://huggingface.co/docling-project/ScreenVLM) when text extraction is needed.
+- The model is trained on rendered web screenshots, so performance may vary on native desktop, mobile, or application screenshots outside the training distribution.
 
 ## Citation
 

best.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d1d16bb335e6f38280dafbb3d2f2937975b62d8ef68ab3cf474b15b145b73286
-size 51358361
+oid sha256:dbcb4f583ccfdb8100a68e606525c247890a2de4c1a54b14741e0ee29ce0ab88
+size 153259543