Enregistré dans:
Détails bibliographiques
Auteurs principaux: Young, Samuel, Terao, Kazuhiro
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2512.01324
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866909937649582080
author Young, Samuel
Terao, Kazuhiro
author_facet Young, Samuel
Terao, Kazuhiro
contents Liquid argon time projection chambers (LArTPCs) provide dense, high-fidelity 3D measurements of particle interactions and underpin current and future neutrino and rare-event experiments. Physics reconstruction typically relies on complex detector-specific pipelines that use tens of hand-engineered pattern recognition algorithms or cascades of task-specific neural networks that require extensive, labeled simulation that requires a careful, time-consuming calibration process. We introduce \textbf{Panda}, a model that learns reusable sensor-level representations directly from raw unlabeled LArTPC data. Panda couples a hierarchical sparse 3D encoder with a multi-view, prototype-based self-distillation objective. On a simulated dataset, Panda substantially improves label efficiency and reconstruction quality, beating the previous state-of-the-art semantic segmentation model with 1,000$\times$ fewer labels. We also show that a single set-prediction head 1/20th the size of the backbone with no physical priors trained on frozen outputs from Panda can result in particle identification that is comparable with state-of-the-art (SOTA) reconstruction tools. Full fine-tuning further improves performance across all tasks.
format Preprint
id arxiv_https___arxiv_org_abs_2512_01324
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Panda: Self-distillation of Reusable Sensor-level Representations for High Energy Physics
Young, Samuel
Terao, Kazuhiro
High Energy Physics - Experiment
Computer Vision and Pattern Recognition
Liquid argon time projection chambers (LArTPCs) provide dense, high-fidelity 3D measurements of particle interactions and underpin current and future neutrino and rare-event experiments. Physics reconstruction typically relies on complex detector-specific pipelines that use tens of hand-engineered pattern recognition algorithms or cascades of task-specific neural networks that require extensive, labeled simulation that requires a careful, time-consuming calibration process. We introduce \textbf{Panda}, a model that learns reusable sensor-level representations directly from raw unlabeled LArTPC data. Panda couples a hierarchical sparse 3D encoder with a multi-view, prototype-based self-distillation objective. On a simulated dataset, Panda substantially improves label efficiency and reconstruction quality, beating the previous state-of-the-art semantic segmentation model with 1,000$\times$ fewer labels. We also show that a single set-prediction head 1/20th the size of the backbone with no physical priors trained on frozen outputs from Panda can result in particle identification that is comparable with state-of-the-art (SOTA) reconstruction tools. Full fine-tuning further improves performance across all tasks.
title Panda: Self-distillation of Reusable Sensor-level Representations for High Energy Physics
topic High Energy Physics - Experiment
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2512.01324