MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images
This work addresses instance segmentation for concave images, offering incremental improvements for real-time applications in computer vision.
The authors tackled the problem of PolarMask's inability to represent concave objects and inefficiency in ray regression by proposing MP-PolarMask, which uses multiple Polar systems to handle convex-and-concave-mixed shapes, resulting in improvements of 13.69% in AP_L and 7.23% in AP over PolarMask on the COCO dataset.
While there are a lot of models for instance segmentation, PolarMask stands out as a unique one that represents an object by a Polar coordinate system. With an anchor-box-free design and a single-stage framework that conducts detection and segmentation at one time, PolarMask is proved to be able to balance efficiency and accuracy. Hence, it can be easily connected with other downstream real-time applications. In this work, we observe that there are two deficiencies associated with PolarMask: (i) inability of representing concave objects and (ii) inefficiency in using ray regression. We propose MP-PolarMask (Multi-Point PolarMask) by taking advantage of multiple Polar systems. The main idea is to extend from one main Polar system to four auxiliary Polar systems, thus capable of representing more complicated convex-and-concave-mixed shapes. We validate MP-PolarMask on both general objects and food objects of the COCO dataset, and the results demonstrate significant improvement of 13.69% in AP_L and 7.23% in AP over PolarMask with 36 rays.