Panda通过自蒸馏学习液氩探测器原始数据的通用表征，大幅减少标注需求并提升重建精度。
Panda: Self-distillation of Reusable Sensor-level Representations for High Energy Physics
- 用分层稀疏3D编码器与多视角原型自蒸馏学习传感器级通用特征
- 仅需1000倍少的标签即超越现有最佳语义分割模型性能
- 冻结Panda输出后用极小预测头即可实现接近顶尖工具的粒子识别
液氩时间投影室（LArTPCs）为粒子相互作用提供密集、高保真的三维测量，是当前及未来中微子和罕见事件实验的基础。物理重建通常依赖复杂的、特定于探测器的处理流程，包含数十个手工设计的模式识别算法，或一系列任务专用神经网络，这些方法需要大量带标签的模拟数据，并且需精心耗时地校准。我们提出 extbf{Panda}，一种直接从原始无标签 LArTPC 数据中学习可复用传感器级表征的模型。Panda 结合分层稀疏3D编码器与多视图、基于原型的自蒸馏目标。在模拟数据集上，Panda 显著提升标签效率与重建质量，以1,000×更少的标签即超越先前最优的语义分割模型。此外，仅使用一个大小为主干网络1/20的集合预测头，且不引入物理先验，在冻结的Panda输出上训练，即可达到与最先进（SOTA）重建工具相当的粒子识别效果。完整微调进一步提升所有任务表现。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。