Mask R$-$CNN

Which of the following statements is correct with respect to the Mask R$-$CNN framework? $($Note: More than one option may be correct.$)$

The architecture is built on top of the Faster R$-$CNN framework.

The backbone network is responsible for generating anchor boxes to search for the desired object class.

The RoI Pooling layer normalizes the shape of the anchor boxes for the architecture for further processing.

The first stage of the architecture comprises the backbone and the region proposal network.