Instance Segmentation Models

CenterMask

Introduced by Lee et al. in CenterMask : Real-Time Anchor-Free Instance Segmentation

CenterMask is an anchor-free instance segmentation method that adds a novel spatial attention-guided mask (SAG-Mask) branch to anchor-free one stage object detector (FCOS) in the same vein with Mask R-CNN. Plugged into the FCOS object detector, the SAG-Mask branch predicts a segmentation mask on each detected box with the spatial attention map that helps to focus on informative pixels and suppress noise.

Source: CenterMask : Real-Time Anchor-Free Instance Segmentation

Papers


Paper Code Results Date Stars

Categories