PolarMask: Single Shot Instance Segmentation With Polar Representation

Enze Xie, Peize Sun, Xiaoge Song, Wenhai Wang, Xuebo Liu, Ding Liang, Chunhua Shen, Ping Luo; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020, pp. 12193-12202


In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as predicting contour of instance through instance center classification and dense distance regression in a polar coordinate. Moreover, we propose two effective approaches to deal with sampling high-quality center examples and optimization for dense distance regression, respectively, which can significantly improve the performance and simplify the training process. Without any bells and whistles, PolarMask achieves 32.9% in mask mAP with single-model and single-scale training/testing on the challenging COCO dataset. For the first time, we show that the complexity of instance segmentation, in terms of both design and computation complexity, can be the same as bounding box object detection and this much simpler and flexible instance segmentation framework can achieve competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation task.

Related Material

[pdf] [arXiv]
author = {Xie, Enze and Sun, Peize and Song, Xiaoge and Wang, Wenhai and Liu, Xuebo and Liang, Ding and Shen, Chunhua and Luo, Ping},
title = {PolarMask: Single Shot Instance Segmentation With Polar Representation},
booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
month = {June},
year = {2020}