Interactive segmentation enables users to extract masks by providing simple annotations to indicate the target, such as boxes, clicks, or scribbles. Among these interaction formats, scribbles are the most flexible as they can be of arbitrary shapes and sizes. This enables scribbles to provide more indications of the target object. However, previous works mainly focus on click-based configuration, and the scribble-based setting is rarely explored. In this work, we attempt to formulate a standard protocol for scribble-based interactive segmentation. Basically, we design diversified strategies to simulate scribbles for training, propose a deterministic scribble generator for evaluation, and construct a challenging benchmark. Besides, we build a strong framework ScribbleSeg, consisting of a Prototype Adaption Module(PAM) and a Corrective Refine Module (CRM), for the task. Extensive experiments show that ScribbleSeg performs notably better than previous click-based methods. We hope this could serve as a more powerful and general solution for interactive segmentation. Our code will be made available.

翻译：交互式分割允许用户通过提供简单的标注（如边界框、点击或涂鸦）来指示目标区域，从而提取掩码。在这些交互形式中，涂鸦因其形状和尺寸的任意性而最为灵活，能为目标对象提供更丰富的指示信息。然而，以往的工作主要关注基于点击的配置，而基于涂鸦的设置鲜有探索。本研究试图为基于涂鸦的交互式分割制定标准协议：我们设计了多样化策略以模拟训练用涂鸦，提出了确定性的涂鸦生成器用于评估，并构建了具有挑战性的基准测试集。此外，我们针对该任务构建了强大框架ScribbleSeg，该框架包含原型适配模块（PAM）与修正精炼模块（CRM）。大量实验表明，ScribbleSeg的性能显著优于以往的基于点击的方法。期望该方法能成为交互式分割领域更强大且通用的解决方案。我们的代码将开源。