zhang-tao-whu / DVIS

DVIS: Decoupled Video Instance Segmentation Framework

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Is the COCO dataset only used for training segmentation models? Do tracking datasets require separate annotations?

DongLZY opened this issue · comments

commented
commented

Hello Mr. Zhang, I would like to perform instance tracking for fruits. Is it possible to achieve this using DVIS? I have already created a dataset for image segmentation and can train instance segmentation models. Do I need to annotate the tracking training dataset additionally, or is it possible to generate it directly?

Yes, DVIS can handle this task. You can try training DVIS using only an image segmentation dataset, but its performance may not be optimal for complex occlusion scenarios. The best advice is to combine your fruit image segmentation dataset with an OVIS dataset for joint training.

commented

Thank you for your answer. Can I use other segmener like yolact? I need to improve the processing speed of the model.

I think it's okay, but I haven't tried it.