让分割模型理解物体前后顺序，点击更准更快。
Order-aware Interactive Segmentation
- 用深度顺序图引导点击注意力，提升定位精度。
- 单次点击下HQSeg44K上mIoU提升7.61，DAVIS提升1.32。
- 支持稀疏和密集点击，推理速度翻倍，适合交互式分割场景。
交互式分割旨在通过最少用户操作精准分割目标物体。然而，现有方法常因对场景中物体相对深度（顺序）理解不足，难以将目标与背景有效分离。为此，我们提出OIS：一种有序感知的交互式分割方法，通过显式编码物体间的相对深度生成顺序图。引入新型有序感知注意力机制，使用户点击（以点击形式输入）能无缝引导模型关注图像特征。进一步设计对象感知注意力模块，结合强对象级理解，更好区分相似深度的物体。本方法支持稀疏与密集点击融合，显著提升准确率与效率。实验表明，OIS在单次点击下于HQSeg44K数据集上实现mIoU提升7.61，在DAVIS数据集上提升1.32，超越此前最优方法SegNext；同时推理速度相较当前领先方法提升一倍。
原文摘要 · Abstract (English)
Interactive segmentation aims to accurately segment target objects with minimal user interactions. However, current methods often fail to accurately separate target objects from the background, due to a limited understanding of order, the relative depth between objects in a scene. To address this issue, we propose OIS: order-aware interactive segmentation, where we explicitly encode the relative depth between objects into order maps. We introduce a novel order-aware attention, where the order maps seamlessly guide the user interactions (in the form of clicks) to attend to the image features. We further present an object-aware attention module to incorporate a strong object-level understanding to better differentiate objects with similar order. Our approach allows both dense and sparse integration of user clicks, enhancing both accuracy and efficiency as compared to prior works. Experimental results demonstrate that OIS achieves state-of-the-art performance, improving mIoU after one click by 7.61 on the HQSeg44K dataset and 1.32 on the DAVIS dataset as compared to the previous state-of-the-art SegNext, while also doubling inference speed compared to current leading methods. The project page is https://ukaukaaaa.github.io/projects/OIS/index.html
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。