Saved in:
Bibliographic Details
Main Authors: Marriott-Clarke, Max, Novakovic, Lazar, Ratzer, Elizabeth, Bainbridge, Robert J., Gouskos, Loukas, Maier, Benedikt
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.23356
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915887578087424
author Marriott-Clarke, Max
Novakovic, Lazar
Ratzer, Elizabeth
Bainbridge, Robert J.
Gouskos, Loukas
Maier, Benedikt
author_facet Marriott-Clarke, Max
Novakovic, Lazar
Ratzer, Elizabeth
Bainbridge, Robert J.
Gouskos, Loukas
Maier, Benedikt
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_23356
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors
Marriott-Clarke, Max
Novakovic, Lazar
Ratzer, Elizabeth
Bainbridge, Robert J.
Gouskos, Loukas
Maier, Benedikt
High Energy Physics - Experiment
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
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.
title Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors
topic High Energy Physics - Experiment
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2603.23356