YOLOv11 - Generic page detection

The generic page detection model predicts single pages from document images.

Model description

The model has been trained using the YOLOv11 library on multiple datasets. It has been trained on images with their dimensions equal to 640 pixels, starting from the YOLOv11l checkpoint.

Evaluation results

The model achieves the following results:

Set	Images	Instances	Box-P	Box-R	Box-mAP@50	Box-mAP@[50-95]	Mask-P	Mask-R	Mask-mAP@50	Mask-mAP@[50-95]
train	1579	2210	0.999	0.996	0.995	0.994	0.999	0.996	0.995	0.993
val	146	208	0.986	0.995	0.989	0.985	0.986	0.995	0.989	0.985
test	144	215	0.995	1.00	0.995	0.994	0.995	1.00	0.995	0.991

How to use?

Download the weights of this model;
Refer to the Ultralytics documentation to use this model.