Abstract
This paper presents Contourformer, a real-time contour-based instance segmentation algorithm. The method is fully based on the DETR paradigm and achieves end-to-end inference through iterative and progressive mechanisms to optimize contours. To improve efficiency and accuracy, we develop two novel techniques: sub-contour decoupling mechanisms and contour fine-grained distribution this http URL the sub-contour decoupling mechanism, we propose a deformable attention-based module that adaptively selects sampling regions based on the current predicted contour, enabling more effective capturing of object boundary information. Additionally, we design a multi-stage optimization process to enhance segmentation precision by progressively refining sub-contours. The contour fine-grained distribution refinement technique aims to further improve the ability to express fine details of this http URL innovations enable Contourformer to achieve stable and precise segmentation for each instance while maintaining real-time performance. Extensive experiments demonstrate the superior performance of Contourformer on multiple benchmark datasets, including SBD, COCO, and KINS. We conduct comprehensive evaluations and comparisons with existing state-of-the-art methods, showing significant improvements in both accuracy and inference this http URL work provides a new solution for contour-based instance segmentation tasks and lays a foundation for future research, with the potential to become a strong baseline method in this field.
Abstract (translated)
这篇论文提出了Contourformer，一种基于轮廓的实时实例分割算法。该方法完全基于DETR范式，并通过迭代和渐进机制优化轮廓实现端到端推理。为了提高效率和精度，我们开发了两项新技术：子轮廓解耦机制和轮廓细粒度分布细化技术。 在子轮廓解耦机制中，我们提出了一种基于可变形注意力的模块，该模块能够根据当前预测的轮廓自适应地选择采样区域，从而更有效地捕捉物体边界信息。此外，我们设计了一个多阶段优化过程，通过逐步精炼子轮廓来提高分割精度。轮廓细粒度分布细化技术旨在进一步增强对细微细节表达的能力。 这些创新使Contourformer能够为每个实例实现稳定而精确的分割，并保持实时性能。广泛的实验表明，在SBD、COCO和KINS等多个基准数据集上，Contourformer具有优越的表现。我们进行了全面的评估和与现有最新方法的比较，证明了在精度和推理速度方面有显著改进。 这项工作为基于轮廓的实例分割任务提供了新的解决方案，并为未来的研究奠定了基础，有望成为该领域的强大基线方法。
URL
https://arxiv.org/abs/2501.17688
