arXiv 2202.044992022-02-09hep-excs.LG

轻型喷注重建和识别作为目标检测任务

Lightweight Jet Reconstruction and Identification as an Object Detection Task

European Organization for Nuclear Research (CERN)（欧洲核子研究组织（CERN））；Princeton University（普林斯顿大学）；CEVA Inc.（CEVA公司）；Institute of Physics Belgrade（贝尔格莱德物理研究所）；Fermi National Accelerator Laboratory（费米国家加速器实验室）

Adrian Alan Pol, Thea Aarrestad, Ekaterina Govorkova, Roi Halily, Anat Klempner, Tal Kopetz, Vladimir Loncar, Jennifer Ngadiuba, Maurizio Pierini, Olya Sirkin, Sioni Summers

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

摘要：

我们将基于深度卷积块的对象检测技术应用于CERN大型强子对撞机（LHC）遇到的端到端喷流识别和重建任务。碰撞事件产生的大型强子对撞机，并表示为一个图像组成的热量计和跟踪细胞作为一个输入到一个Single Shot检测网络。该算法名为PFJet-SSD，同时执行定位，分类和回归任务，以聚类射流并重建其特征。这种一体化的单前馈通道在执行时间和提高的精度w.r.t.方面具有优势。传统的基于规则的方法。从网络瘦身、均匀量化和优化的运行时间获得进一步的增益，以满足典型实时处理环境的存储器和延迟约束。我们使用8位和三进制量化进行实验，将其精度和推理延迟与单精度浮点进行基准测试。我们表明，三元网络密切配合其全精度等效的性能，并优于最先进的基于规则的算法。最后，我们报告了不同硬件平台上的推理延迟，并讨论了未来的应用。

英文摘要：

We apply object detection techniques based on deep convolutional blocks to end-to-end jet identification and reconstruction tasks encountered at the CERN Large Hadron Collider (LHC). Collision events produced at the LHC and represented as an image composed of calorimeter and tracker cells are given as an input to a Single Shot Detection network. The algorithm, named PFJet-SSD performs simultaneous localization, classification and regression tasks to cluster jets and reconstruct their features. This all-in-one single feed-forward pass gives advantages in terms of execution time and an improved accuracy w.r.t. traditional rule-based methods. A further gain is obtained from network slimming, homogeneous quantization, and optimized runtime for meeting memory and latency constraints of a typical real-time processing environment. We experiment with 8-bit and ternary quantization, benchmarking their accuracy and inference latency against a single-precision floating-point. We show that the ternary network closely matches the performance of its full-precision equivalent and outperforms the state-of-the-art rule-based algorithm. Finally, we report the inference latency on different hardware platforms and discuss future applications.

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。

摘要：

英文摘要：

相关论文