ResoSeg：使用Transformer和分割模型的共振态标记器
ResoSeg: Resonance Tagger using Transformer and Segment Model
浏览论文内容
中文总结 AI 辅助
ResoSeg是一种基于Transformer和分割模型的深度学习框架，首次在BESIII实现共振态标记的粒子级分割与事件级分类联合，效率较传统方法提升一倍以上，且具备跨能量点泛化与迁移能力。
中文摘要 AI 辅助
深度学习已广泛应用于实验高能物理的许多领域，然而现有模型仅处理事件级分类或对象标记，因此仍需要针对每个衰变通道定制的重建算法。我们首次将分割技术应用于BESIII的共振态标记，并引入ResoSeg，这是一种深度学习模型，联合执行粒子级分割和事件级分类，能够对共振态到任意粒子的衰变进行一次性分析，同时精确重建相关共振态性质。我们演示了通过$e^+e^-\to\pi^+\pi^-h_c$、$h_c\to\gamma\eta_c$、$\eta_c\to\text{anything}$过程对$\eta_c$的重建。该模型在BESIII-$\eta_c$数据集上训练，该数据集通过真值匹配算法获得每径迹真标签。实验结果表明，在4.19至4.60\\,GeV的能量点范围内，ResoSeg的平均组合效率是传统16通道方法的两倍以上。该模型能泛化到未见过的能量点，通过迁移学习适应其他$\eta_c$产生模式，并对$\eta_c$质量、宽度和分支比的变化保持鲁棒性，提供了一个超越$\eta_c$和BESIII的通用、共振态感知模型。源代码可在该https URL获取。
英文摘要
Deep learning has been widely applied across many areas of experimental high-energy physics, yet existing models address only event-level classification or object tagging and therefore still require reconstruction algorithms tailored to each decay channel. We present the first application of segmentation to resonance tagging at BESIII and introduce ResoSeg, a deep learning model that jointly performs particle-level segmentation and event-level classification, enabling a one-pass analysis of resonance to anything decays while precisely reconstructing the relevant resonance properties. We demonstrate the reconstruction of $η_c$ with $e^+e^-\toπ^+π^-h_c$, $h_c\toγη_c$, $η_c\to\text{anything}$. The model is trained on BESIII-$η_c$ dataset, which is constructed with per-track true labels obtained via a Truth-Matching Algorithm. Experimental results show that the average combined efficiency of ResoSeg is more than double that of the conventional 16-channel approach across energy points from 4.19 to 4.60\,GeV. The model generalizes to unseen energy points, adapts to other $η_c$ production modes through transfer learning, and remains robust against variations in the $η_c$ mass, width, and branching fractions, providing a general, resonance-aware model applicable beyond $η_c$ and BESIII. The source code is available at https://github.com/oashen/ResoSeg.
发表机构
- Nankai University（南开大学）
- Institute of High Energy Physics, Chinese Academy of Sciences（中国科学院高能物理研究所）
- University of Chinese Academy of Sciences（中国科学院大学）
机构由 AI 辅助整理，请以论文原文为准。
