计算机科学
分割
计算
边界(拓扑)
偏移量(计算机科学)
人工智能
图像分割
活动轮廓模型
等高线
分类器(UML)
算法
计算机视觉
数学
数学分析
气象学
物理
程序设计语言
作者
Chengzhang Zhu,Xuanye Zhang,Yanran Li,Liangdong Qiu,Kai Han,Xiaodong Han
出处
期刊:Cornell University - arXiv
日期:2022-03-24
标识
DOI:10.48550/arxiv.2203.13312
摘要
Excellent performance has been achieved on instance segmentation but the quality on the boundary area remains unsatisfactory, which leads to a rising attention on boundary refinement. For practical use, an ideal post-processing refinement scheme are required to be accurate, generic and efficient. However, most of existing approaches propose pixel-wise refinement, which either introduce a massive computation cost or design specifically for different backbone models. Contour-based models are efficient and generic to be incorporated with any existing segmentation methods, but they often generate over-smoothed contour and tend to fail on corner areas. In this paper, we propose an efficient contour-based boundary refinement approach, named SharpContour, to tackle the segmentation of boundary area. We design a novel contour evolution process together with an Instance-aware Point Classifier. Our method deforms the contour iteratively by updating offsets in a discrete manner. Differing from existing contour evolution methods, SharpContour estimates each offset more independently so that it predicts much sharper and accurate contours. Notably, our method is generic to seamlessly work with diverse existing models with a small computational cost. Experiments show that SharpContour achieves competitive gains whilst preserving high efficiency
科研通智能强力驱动
Strongly Powered by AbleSci AI