MP-PolarMask: A Faster and Finer Instance Segmentation for Concave Images

TL;DR

MP-PolarMask enhances instance segmentation by using multiple polar coordinate systems to better represent complex shapes, especially concave objects, resulting in significant accuracy improvements over PolarMask.

Contribution

It introduces MP-PolarMask, a novel multi-polar system approach that effectively models concave and convex shapes, addressing limitations of the original PolarMask.

Findings

13.69% AP_L improvement on COCO dataset

7.23% AP improvement over PolarMask with 36 rays

Effective representation of complex shapes including concave objects

Abstract

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.