PolarMask: Single Shot Instance Segmentation with Polar Representation
CVPR(2020)
摘要
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 as a mask prediction module for instance segmentation, by easily embedding it into most off-the-shelf detection methods. Our method, termed PolarMask, formulates the instance segmentation problem as 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 challenging COCO dataset. For the first time, we demonstrate a much simpler and flexible instance segmentation framework achieving competitive accuracy. We hope that the proposed PolarMask framework can serve as a fundamental and strong baseline for single shot instance segmentation tasks. Code is available at: github.com/xieenze/PolarMask.
更多查看译文
关键词
polar representation,off-the-shelf detection methods,instance center classification,dense distance regression,high-quality center examples,optimization,single-scale training,flexible instance segmentation framework,PolarMask framework,single shot instance segmentation task,anchor-box free segmentation method,mask mAP,COCO dataset,instance segmentation complexity
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络