"The Region Proposal Network (RPN) runs a lightweight binary classifier on a lot of boxes (anchors) over the image and returns object/no-object scores. Anchors with high *objectness* score (positive anchors) are passed to the stage two to be classified.\n",
"\n",
"Often, even positive anchors don't cover objects fully. So the RPN also regresses a refinement (a delta in location and size) to be applied to the anchros to shift it and resize it a bit to the correct boundaries of the object."
"Often, even positive anchors don't cover objects fully. So the RPN also regresses a refinement (a delta in location and size) to be applied to the anchors to shift it and resize it a bit to the correct boundaries of the object."