arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2603.23356hep-excs.AIcs.CVcs.LG
收藏

基于对比度度量学习的点云分割方法用于高粒度探测器

Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors

Blackett Laboratory, Imperial College London, UK(帝国理工学院伦敦学院布莱克特实验室);Brown Center for Theoretical Physics and Innovation (BCTPI), Brown University, USA(布朗大学理论物理与创新中心)

Max Marriott-Clarke, Lazar Novakovic, Elizabeth Ratzer, Robert J. Bainbridge, Loukas Gouskos, Benedikt Maier

AI总结:

本文提出基于监督对比度度量学习的点云分割方法,通过学习潜在表示实现点云分割,相比传统方法更稳定且分离度更高,提升重建效率和纯度。

摘要:

我们提出了一种基于监督对比度度量学习(CML)的新型点云分割方法。该方法不预测聚类标签或物体中心变量,而是学习一个潜在表示,在其中同一物体的点被嵌入在一起,而无关点被分离。然后使用基于密度的读取器重建聚类,将表示学习与聚类形成解耦,实现灵活推理。该方法在高粒度 calorimeter 的模拟数据上进行评估,任务是分离高度重叠的粒子 shower,表示为 calorimeter 击中集合。通过使用相同的图神经网络骨干和相同的潜在维度,与物体凝结(OC)进行直接比较,隔离了学习目标的影响。CML 方法在电磁和强子粒子 shower 中产生更稳定和可分离的嵌入几何,导致局部邻域一致性提高,重叠 shower 分离更可靠,且在扩展到未见过的多重性和能量时泛化性更好。这直接转化为更高的重建效率和纯度,特别是在高多重性区域,以及改进的能量分辨率。在混合粒子环境中,CML 保持强性能,表明稳健学习 shower 形态,而 OC 显示显著退化。这些结果表明,基于相似度的表示学习结合基于密度的聚合是点云分割在高粒度探测器中的一种有前途的替代方法。

英文摘要:

We propose a novel clustering approach for point-cloud segmentation based on supervised contrastive metric learning (CML). Rather than predicting cluster assignments or object-centric variables, the method learns a latent representation in which points belonging to the same object are embedded nearby while unrelated points are separated. Clusters are then reconstructed using a density-based readout in the learned metric space, decoupling representation learning from cluster formation and enabling flexible inference. The approach is evaluated on simulated data from a highly granular calorimeter, where the task is to separate highly overlapping particle showers represented as sets of calorimeter hits. A direct comparison with object condensation (OC) is performed using identical graph neural network backbones and equal latent dimensionality, isolating the effect of the learning objective. The CML method produces a more stable and separable embedding geometry for both electromagnetic and hadronic particle showers, leading to improved local neighbourhood consistency, a more reliable separation of overlapping showers, and better generalization when extrapolating to unseen multiplicities and energies. This translates directly into higher reconstruction efficiency and purity, particularly in high-multiplicity regimes, as well as improved energy resolution. In mixed-particle environments, CML maintains strong performance, suggesting robust learning of the shower topology, while OC exhibits significant degradation. These results demonstrate that similarity-based representation learning combined with density-based aggregation is a promising alternative to object-centric approaches for point cloud segmentation in highly granular detectors.

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。

↑