Fine-tuning tutorial for image segmentation & video segmentation

Hi,

Thank you for the great project!

I would like to ask whether there is any official demo, tutorial, or example code for fine-tuning the model on a **image segmentation dataset** or a **video segmentation dataset**. I notice that current tutorial is designed for **object detection dataset**.

Start by locating the repository's existing fine-tuning tutorial for object detection, which the issue identifies as the current entry point. Determine how image- and video-segmentation datasets differ from that example, then document official tutorials or runnable examples for both workflows. Done means newcomers can find and follow the examples for each dataset type.

Written by the indexing model from the issue text.