Multi Task Learning Clarification

Hi Mentors,

We had doubt in the below statement can u please help to clarify ?

How it is saying car, traffic lights, pedestrians are all having similar features that helping to recognize stop sign ? Is it saying due to all the objects are present on the road ?

One is if your training on a set of tasks that could benefit from having shared low-level features. So for the autonomous driving example, it makes sense that recognizing traffic lights and cars and pedestrians, those should have similar features that could also help you recognize stop signs, because these are all features of roads.

That is correct. If you were to take pictures of roads, you’ll notice these objects.