On the Sample Complexity of End-to-end Training vs. Semantic Abstraction Training

We compare the end-to-end training approach to a modular approach in which a is decomposed into semantically meaningful components. We focus on the complexity aspect, in the regime where an extremely high accuracy is, as is the case in autonomous driving applications. We demonstrate in which the number of training examples required by the end-to-end is exponentially larger than the number of examples required by the abstraction approach.