UCP-Net：用于实例分割的非结构轮廓点
UCP-Net: Unstructured Contour Points for Instance Segmentation
摘要：
交互式分割的目标是帮助用户尽可能快速和准确地生成分割掩码。交互必须简单直观，并且产生令人满意的分割掩模所需的交互次数应尽可能少。在本文中，我们提出了一种新的方法，交互式分割的基础上无约束的轮廓点击初始分割和分割细化。我们的方法是类不可知的，并产生准确的分割掩码（IoU > 85%），与流行的分割数据集（COCO MVal，SBD和Berkeley）上的最新方法相比，用户交互次数更少。
英文摘要：
The goal of interactive segmentation is to assist users in producing segmentation masks as fast and as accurately as possible. Interactions have to be simple and intuitive and the number of interactions required to produce a satisfactory segmentation mask should be as low as possible. In this paper, we propose a novel approach to interactive segmentation based on unconstrained contour clicks for initial segmentation and segmentation refinement. Our method is class-agnostic and produces accurate segmentation masks (IoU > 85%) for a lower number of user interactions than state-of-the-art methods on popular segmentation datasets (COCO MVal, SBD and Berkeley).
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
