fpn instance segmentation idea

[dongluyang]

could you explain much details about the logic for fpn instance segmentation as below. what is MLP, and what does figure 4
mean?
Figure 4. FPN for object segment proposals. The feature pyramid is constructed with identical structure as for object detection. We apply a small MLP on 5×5 windows to generate dense object segments with output dimension of 14×14. Shown in orange are the size of the image regions the mask corresponds to for each pyramid level (levels P 3−5 are shown here). Both the corresponding image region size (light orange) and canonical object size (dark orange) are shown. Half octaves are handled by an MLP on 7x7 windows ($7 ≈ 5 \sqrt 2$), not shown here. Details are in the appendix