arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.00693hep-phcs.CVstat.ML
收藏

PE-GAN:用于Belle II中PXD图像的先验嵌入GAN

PE-GAN: Prior Embedding GAN for PXD images at Belle II

Faculty of Physics(物理学院);Ludwig Maximilians University of Munich(慕尼黑大学)

Baran Hashemi, Nikolai Hartmann, Thomas Kuhr, Martin Ritter, Matej srebre

AI总结:

针对Belle II探测器PXD背景噪声样本存储需求大且需避免系统偏差的问题,提出基于条件GAN与对比学习的按需PXD背景生成器PE-GAN,以提升图像保真度并生成依赖传感器的击中图。

摘要:

像素顶点探测器(PXD)是Belle II探测器记录粒子位置的重要组成部分。来自PXD和其他传感器的数据使我们能够重建粒子径迹和衰变顶点。通过将测量或模拟的背景击中模式添加到模拟信号粒子产生的击中中,来模拟背景击中对径迹重建的影响。该模型需要大量统计独立的PXD背景噪声样本,以避免重建径迹的系统偏差。然而,来自细粒度PXD的数据需要大量存储空间。作为一种高效的背景噪声生成方式,我们探索了使用带有对比学习的条件生成对抗网络(GAN)构建按需PXD背景生成器的想法,并根据PXD传感器的数量进行调整,以同时提高图像保真度并生成依赖传感器的PXD击中图。

英文摘要:

The pixel vertex detector (PXD) is an essential part of the Belle II detector recording particle positions. Data from the PXD and other sensors allow us to reconstruct particle tracks and decay vertices. The effect of background hits on track reconstruction is simulated by adding measured or simulated background hit patterns to the hits produced by simulated signal particles. This model requires a large set of statistically independent PXD background noise samples to avoid a systematic bias of reconstructed tracks. However, data from the fine-grained PXD requires a substantial amount of storage. As an efficient way of producing background noise, we explore the idea of an on-demand PXD background generator using conditional Generative Adversarial Networks (GANs) with contrastive learning, adapted by the number of PXD sensors in order to both increase the image fidelity and produce sensor-dependent PXD hitmaps.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑