- Featured in Physics
- Open Access
Contrastive Metric Learning for Point Cloud Segmentation in Highly Granular Detectors
PRX Intelligence 1, 013004 – Published 28 July, 2026
DOI: https://doi.org/10.1103/tsc6-gn3r
Abstract
We propose a 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 neighborhood 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 stable learning of the shower topology across particle types, 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.
Physics Subject Headings (PhySH)
Research News
Unpacking Particle Showers with Machine Learning
A new AI-powered event-processing algorithm is being readied to cope with the torrent of data that will stream from the Large Hadron Collider upgrade.
See more in Physics
Article Text
References (27)
- CMS Collaboration, The Phase-2 Upgrade of the CMS Endcap Calorimeter, Technical Report (CERN, Geneva, 2017), https://cds.cern.ch/record/2293646.
- X. Ju et al., Graph neural networks for particle reconstruction in high energy physics detectors, arXiv:2003.11603.
- L. Ehrke, J. A. Raine, K. Zoch, M. Guth, T. Golling, Topological reconstruction of particle physics processes using graph neural networks, Phys. Rev. D 107, 116019 (2023).
- J. Duarte and J.-R. Vlimant, Graph neural networks for particle tracking and reconstruction, in Artificial Intelligence for High Energy Physics, edited by P. Calafiura, D. Rousseau, and K. Terao (World Scientific, Singapore, 2022), pp. 387–436.
- J. Kieseler, Object condensation: One-stage grid-free multi-object reconstruction in physics detectors, graph, and image data, Eur. Phys. J. C 80, 886 (2020).
- G. Matousek and A. Vossen, AI-assisted object condensation clustering for calorimeter shower reconstruction at CLAS12, Nucl. Instrum. Methods Phys. Res. A 1082, 170990 (2026).
- S. R. Qasim, K. Long, J. Kieseler, M. Pierini, and R. Nawaz, Multi-particle reconstruction in the High Granularity Calorimeter using object condensation and graph neural networks, EPJ Web Conf. 251, 03072 (2021).
- S. Gardner, R. Tyson, D. Glazier, and K. Livingston, Object condensation for track building in a backward electron tagger at the EIC, J. Instrum. 19, C05052 (2024).
- R. Hadsell, S. Chopra, and Y. LeCun, Dimensionality reduction by learning an invariant mapping, in Proccedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'06) (IEEE Computer Society, 2006), pp. 1735–1742.
- Y. Wang, Y. Sun, Z. Liu, S. E. Sarma, M. M. Bronstein, and J. M. Solomon, Dynamic graph CNN for learning on point clouds, ACM Trans. Graph. 38, 146 (2019).
- A. van den Oord, Y. Li, and O. Vinyals, Representation learning with contrastive predictive coding, arXiv:1807.03748.
- T. Chen, S. Kornblith, M. Norouzi, and G. Hinton, A simple framework for contrastive learning of visual representations, in Proceedings of the 37th International Conference on Machine Learning (ICML 2020) (PMLR, 2020), Vol. 119, pp. 1597–1607.
- P. Khosla, P. Teterwak, C. Wang, A. Sarna, Y. Tian, P. Isola, A. Maschinot, C. Liu, and D. Krishnan, Supervised contrastive learning, in Advances in Neural Information Processing Systems (NeurIPS, 2020), Vol. 33, pp. 18661–18673.
- P. H. Le-Khac, G. Healy, and A. F. Smeaton, Contrastive representation learning: A framework and review, IEEE Access 8, 193907 (2020).
- Y. Li, P. Hu, Z. Liu, D. Peng, J. T. Zhou, and X. Peng, Contrastive clustering, in Proceedings of the AAAI Conference on Artificial Intelligence (AAAI, 2021), Vol. 35, pp. 8547–8555.
- K. Lieret, G. DeZoort, D. Chatterjee, J. Park, S. Miao, and P. Li, High pileup particle tracking with object condensation, arXiv:2312.03823.
- D. Müllner, Modern hierarchical, agglomerative clustering algorithms, arXiv:1109.2378.
- M. Ester, H.-P. Kriegel, J. Sander, and X. Xu, A density-based algorithm for discovering clustersin large spatial databases with noise, in Proceedings of the Second International Conference on Knowledge Discovery and Data Mining (AAAI Press, Menlo Park, CA, 1996), pp. 226–231.
- L. McInnes, J. Healy, and S. Astels, hdbscan: Hierarchical density based clustering, J. Open Source Software 2, 205 (2017).
- S. Agostinelli et al., Geant4—A simulation toolkit, Nucl. Instrum. Methods Phys. Res., Sect. A 506, 250 (2003).
- N. Akchurin, Response of a CMS HGCAL Silicon-pad electromagnetic calorimeter prototype to 20–300 GeV positrons, Tech. Rep. (CERN, Geneva, 2021), https://cds.cern.ch/record/2798347.
- B. Acar et al. (CMS Collaboration), Performance of the CMS High Granularity Calorimeter prototype to charged pion beams of 20–300 GeV/c, arXiv:2211.04740.
- D. P. Kingma and J. Ba, Adam: A method for stochastic optimization, Proceedings of the 3rd International Conference on Learning Representations (ICLR, San Diego, CA, 2015).
- D. Zhang, Y. Li, and Z. Zhang, Deep metric learning with spherical embedding, Advances in Neural Information Processing Systems (NeurIPS, 2020), Vol. 33, pp. 18772–18783.
- K. Musgrave, S. Belongie, and S.-N. Lim, A metric learning reality check, Computer Vision, ECCV 2020, Lecture Notes in Computer Science (Springer, Cham, 2020), Vol. 12370, pp. 681–699.
- CMS Collaboration, The iterative clustering (TICL) (v5a) reconstruction at the CMS phase-2 high granularity calorimeter endcap, 2024, https://cds.cern.ch/record/2920448.
- CMS Collaboration, Energy calibration and resolution of the CMS Electromagnetic Calorimeter in pp collisions at , J. Instrum. 8, P09009 (2013).
