YOLOv11 uses multiple heads(classification+segmentation) during training

Discussion
, ,
1

I want to train YOLOv11 on my dataset in a multi-head setup, so that during training it learns both classification and segmentation.
Specifically, when it learns segmentation, it should also learn the class of the segmented region.

I also have another task where I want it to learn classification and object detection simultaneously.

What changes do I need to make in the code to achieve this?

2

Instance segmentation model already learns both the segmentation mask and the class.