Search Results for author:
Found 2 papers, 2 papers with code
CenterDisks: Real-time instance segmentation with disk covering
In the learning phase, we consider the radius as proportional to a standard deviation in order to compute the error to propagate on a set of two-dimensional Gaussian functions rather than disks.
Real-time instance segmentation with polygons using an Intersection-over-Union loss
In this paper, we improve over CenterPoly by enhancing the classical regression L1 loss with a novel region-based loss and a novel order loss, as well as with a new training process for the vertices prediction head.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
