Instance Segmentation Modules

PolarMask is an anchor-box free and single-shot instance segmentation method. Specifically, PolarMask takes an image as input and predicts the distance from a sampled positive location (ie a candidate object's center) with respect to the object's contour at each angle, and then assembles the predicted points to produce the final mask. There are several benefits to the system: (1) The polar representation unifies instance segmentation (masks) and object detection (bounding boxes) into a single framework (2) Two modules are designed (i.e. soft polar centerness and polar IoU loss) to sample high-quality center examples and optimize polar contour regression, making the performance of PolarMask does not depend on the bounding box prediction results and more efficient in training. (3) PolarMask is fully convolutional and can be embedded into most off-the-shelf detection methods.

Source: PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond


Paper Code Results Date Stars


Task Papers Share
Instance Segmentation 2 28.57%
Semantic Segmentation 2 28.57%
Cell Segmentation 1 14.29%
Object Detection 1 14.29%
Text Detection 1 14.29%


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign