用视觉Transformer实现高精度、快速的粒子探测器模拟
A universal vision transformer for fast calorimeter simulations
- 基于视觉Transformer构建通用模拟框架，适配规则与不规则探测器几何结构
- 生成电磁与强子簇射与真实仿真偏差极小，单卡生成时间仅10-100毫秒
- 预训练+微调策略显著提升数据效率，适合实际物理实验部署
高维复杂的探测器结构使快速量热器模拟成为现代生成式机器学习的理想应用场景。视觉变换器（ViTs）能够以前所未有的精度模拟Geant4响应，且不受限于规则几何结构。基于CaloDREAM架构，我们验证了ViTs在规则与不规则几何结构及多种探测器上的鲁棒性与可扩展性。结果表明，ViTs在多个评估指标下生成的电磁与强子簇射与Geant4结果几乎无偏差，同时保持单卡生成时间在10-100毫秒量级。此外，通过大规模数据集预训练并针对目标几何结构微调，显著降低训练成本并提升数据效率，或直接提高生成簇射的真实性。
原文摘要 · Abstract (English)
The high-dimensional complex nature of detectors makes fast calorimeter simulations a prime application for modern generative machine learning. Vision transformers (ViTs) can emulate the Geant4 response with unmatched accuracy and are not limited to regular geometries. Starting from the CaloDREAM architecture, we demonstrate the robustness and scalability of ViTs on regular and irregular geometries, and multiple detectors. Our results show that ViTs generate electromagnetic and hadronic showers with minimal deviations from Geant4 in multiple evaluation metrics, while maintaining the generation time in the $\mathcal{O}(10-100)$ ms on a single GPU. Furthermore, we show that pretraining on a large dataset and fine-tuning on the target geometry leads to reduced training costs and higher data efficiency, or altogether improves the fidelity of generated showers.
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。