学习并对齐点击感知形状先验用于交互式非模态实例分割
Learning and Aligning Click-Aware Shape Prior for Interactive Amodal Instance Segmentation
将用户点击作为交互信号，通过三元组损失学习点击感知的形状先验，并用可变形注意力对齐先验与目标实例，为遮挡下的非模态实例分割提供可复用的先验检索与对齐框架。
原文依据 we propose to learn click-aware shape prior with triplet loss, which forces the retrieved shape priors to have higher IoU with the ground-truth of target instance
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论非模态实例分割旨在分割目标实例的可见区域与遮挡区域，由于遮挡下缺乏推理支持而颇具挑战。现有方法大多利用关于物体掩码的先验知识（形状先验）来支持非模态估计，但形状先验在测试阶段并不总是与目标实例兼容。本文探索交互式非模态分割任务，其中少量用户点击可用于更好地分割目标实例的完整掩码。针对该任务，我们提出一种基于学习并对齐点击感知形状先验的新框架（称为 ClickPriorNet）。具体而言，我们提出用三元组损失学习点击感知形状先验，迫使检索到的形状先验与目标实例真值具有更高 IoU，从而能够精确促进预测。此外，考虑到形状先验与目标实例之间不可避免的失配，我们提出用可变形注意力自适应地对齐形状先验。总体而言，我们的模型能够充分利用交互点击来检索并对齐形状先验，从而估计更完整的掩码。在三个基准数据集上的大量实验证明了我们方法的有效性。代码见 https://github.com/chenbys/ClickPriorNet。
英文原文摘要 1355 字符
Amodal instance segmentation aims to segment both visible and occluded regions of object instance, which are challenging due to lacking inference support under occlusion. Most existing methods employ the prior knowledge about object mask (shape prior) to support the amodal estimation, but the shape prior is not always compatible for object instances in the test stage. In this paper, we explore the task of interactive amodal segmentation, where a few user clicks are available for better segmenting the complete masks of object instances. For this task, we propose a novel framework based on learning and aligning click-aware shape prior (termed ClickPriorNet). Specifically, we propose to learn click-aware shape prior with triplet loss, which forces the retrieved shape priors to have higher IoU with the ground-truth of target instance and thus could exactly facilitate the prediction. Besides, considering the inevitable mismatch between shape prior and target instance, we propose to adaptively align the shape prior with deformable attention. Overall, our model could make full use of the interactive clicks to retrieve and align shape priors, and thus could estimate more complete masks. Extensive experiments on three benchmark datasets demonstrate the effectiveness of our method. Code is available at https://github.com/chenbys/ClickPriorNet.