The model actually produces five polygons: init, coarse, final1, final2, and final3.
Coarse is refined using the proposed global deformation module, while **final*** are refined using the circular convolution module.
What if we use all global deformation modules or circular convolution modules for all the polygon refinement?
Fine segmentation results require more attention to local information, if only global deformation is used, the predicted results may have poor contour detail quality.
The model actually produces five polygons: init, coarse, final1, final2, and final3. Coarse is refined using the proposed global deformation module, while **final*** are refined using the circular convolution module. What if we use all global deformation modules or circular convolution modules for all the polygon refinement?