This model is designed to detect question regions in exam booklets, worksheets, and PDF page renders. It works best on dense educational pages with clear question boundaries.

Release notes

This release checkpoint is a cleaned fine-tune of a previously trained YOLO26M run, finalized without mosaic augmentation.

Test results

Old held-out test set

Model	Precision	Recall	mAP50	mAP50-95
YOLO26M Question Segmentation	0.990	0.982	0.988	0.920

Combined held-out test set

Model	Precision	Recall	mAP50	mAP50-95
YOLO26M Question Segmentation	0.987	0.978	0.992	0.957

Usage

python

from ultralytics import YOLO

model = YOLO("hf://samil24/yolo26m-question-segmentation")
results = model("page.png", imgsz=1280, conf=0.25)

Included files

best.pt: release checkpoint
metrics_summary.json: test-set metrics for this release
confidence_sweep_summary.json: confidence sweep outputs used during evaluation
comparison_examples/: side-by-side qualitative examples

Data note

Some of the training data comes from public Roboflow projects used in earlier versions of this question-segmentation pipeline:

PDF Soru Cikarma (tanimazsinu): Link
WholeQuestionDetection (Gazi University): Link
ExamBuddy (ExamBuddy): Link
Questions (Terry Li): Link
Question Parsing from Document (Sefa): Link
Question Dedector (Nur Etinkaya): Link
Sorukes (Sorualgilama): Link
Question Detection (Cognizen): Link
Questions2 (Fiver): Link
Question-New (Question): Link

License

This release is published under CC-BY-4.0.