I am using Mask-RCNN neural network. I retrained my network to detect and mask wheels of die-cast toy cars. I am using images, which present the side of the car (left or right).
Sometimes the cars have different sizes of the wheels like presented on the image below. The front wheels are much smaller than rear ones. I want to detect front ones as "front wheels" and rear one as "rear wheels". If there is only one wheel on the photo (caused by bad cropping), then I want to detect this wheel just as a "wheel".
What should I do to mask 2 wheels (and assing proper labels to them) if image contains two wheels, which looks similiar?