基于轮廓的交互式分割
Contour-based Interactive Segmentation
AI总结：
本文提出基于松散轮廓的交互式分割方法，以替代多次点击输入，并在标准基准及新数据集上验证单个轮廓即可达到与多次点击相当的精度，显著减少用户交互量。
摘要：
交互式分割（IS）的最新进展极大地加速并简化了图像编辑与标注。现代 IS 方法大多以点击形式接受用户输入。然而，使用点击可能需要过多的用户交互，尤其是在选择小目标、目标的细小部分或一组同类目标时。本文考虑一种自然的用户交互形式——松散轮廓，并提出一种基于轮廓的 IS 方法。我们在标准分割基准、新提出的 UserContours 数据集及其包含困难分割案例的子集 UserContours-G 上对所提方法进行了评估。通过实验，我们证明单个轮廓可达到与多次点击相同的精度，从而减少所需的用户交互量。
英文摘要：
Recent advances in interactive segmentation (IS) allow speeding up and simplifying image editing and labeling greatly. The majority of modern IS approaches accept user input in the form of clicks. However, using clicks may require too many user interactions, especially when selecting small objects, minor parts of an object, or a group of objects of the same type. In this paper, we consider such a natural form of user interaction as a loose contour, and introduce a contour-based IS method. We evaluate the proposed method on the standard segmentation benchmarks, our novel UserContours dataset, and its subset UserContours-G containing difficult segmentation cases. Through experiments, we demonstrate that a single contour provides the same accuracy as multiple clicks, thus reducing the required amount of user interactions.
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。
