Is (pre-trained) DeepLabV3 model only trained to recognize people?

I have set up a project using DeepLabV3 for image semantic segmentation using the pre-trained DeepLabV3 model from Apple.

This works consistently well for delineating (creating a black/white mask) the main object in a given image, but only as long as that main object is a person.

When I try other random objects (coffee cups, tractor, stapler), with very clear outline/contrast, I get very poor results, if not a completely black mask.

Is the pre-trained DeepLabV3 model just for people?

If I need to do something (re-training, config, etc), what is it?

Thanks, Neal