search

zorzi-s / PolyWorldPretrainedNetwork

PolyWorld: Polygonal Building Extraction with Graph Neural Networks in Satellite Images
Other
180 stars 28 forks source link

Segmentation mask #20

Closed henokyen closed 1 year ago

henokyen commented 1 year ago

Hello There,

Thank you for sharing your work.

In your paper, it was indicated that corner detection is modeled as a segmentation task using weighted binary cross-entropy loss. It is also indicated that training the corner detection part needs polygonal annotations. My question is what are these polygonal annotations? Do they represent each corner as a single pixel with a value of 1 and leave other pixes with a value of 0? or are they just a binary polygon, meaning pixels on and inside the polygon are 1?

Thanks

zorzi-s commented 1 year ago

@henokyen the ground truth segmentation mask is simply a sparse array of zeros with each corner represented as a single pixel with value of 1 (see Section 4 subsection Detection, and Figure 6 in the supplementary)

henokyen commented 1 year ago

Thanks