arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2103.06509cs.CVhep-ex
收藏

用于LHC单次共形跟踪的实例分割GNN

Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC

Princeton Institute for Computational Science and Engineering(普林斯顿计算科学与工程研究所);Princeton University(普林斯顿大学);Department of Physics(物理系)

Savannah Thais, Gage DeZoort

摘要:

三维实例分割一直是计算机视觉中一个具有挑战性的问题。在对撞机(如LHC)上的粒子跟踪可以被概念化为一个实例分割任务:从粒子检测器中的点云开始,算法必须识别哪些命中属于单个粒子轨迹并提取轨迹属性。图神经网络(GNN)在标准实例分割任务上表现出了良好的性能。在这项工作中,我们证明了实例分割GNN架构对粒子跟踪的适用性;此外,我们重新想象了传统的笛卡尔空间寻迹方法,而是在保形几何中工作,允许GNN在Single Shot中识别轨迹并提取参数。

英文摘要:

3D instance segmentation remains a challenging problem in computer vision. Particle tracking at colliders like the LHC can be conceptualized as an instance segmentation task: beginning from a point cloud of hits in a particle detector, an algorithm must identify which hits belong to individual particle trajectories and extract track properties. Graph Neural Networks (GNNs) have shown promising performance on standard instance segmentation tasks. In this work we demonstrate the applicability of instance segmentation GNN architectures to particle tracking; moreover, we re-imagine the traditional Cartesian space approach to track-finding and instead work in a conformal geometry that allows the GNN to identify tracks and extract parameters in a single shot.

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。

↑