Influencer Loss: End-to-end Geometric Representation Learning for Track Reconstruction

被引:0
|
作者
Murnane, Daniel [1 ]
机构
[1] Lawrence Berkeley Natl Lab, Berkeley, CA 94720 USA
来源
26TH INTERNATIONAL CONFERENCE ON COMPUTING IN HIGH ENERGY AND NUCLEAR PHYSICS, CHEP 2023 | 2024年 / 295卷
关键词
D O I
10.1051/epjconf/202429509016
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
Significant progress has been made in applying graph neural networks (GNNs) and other geometric ML ideas to the track reconstruction problem. State-of-the-art results are obtained using approaches such as the Exatrkx pipeline, which currently applies separate edge construction, classification and segmentation stages. One can also treat the problem as an object condensation task, and cluster hits into tracks in a single stage, such as in the GravNet architecture. However, condensation with such an architecture may still require non-differentiable operations, and arbitrary post-processing. In this work, I extend the ideas of geometric attention to the task of fully geometric (and therefore fully differentiable) end-to-end track reconstruction in a single step. To realize this goal, I introduce a novel condensation loss function called Influencer Loss, which allows an embedded representation of tracks to be learned in tandem with the most representative hit(s) in each track. This loss has global optima that formally match the task of track reconstruction, namely smooth condensation of tracks to a single point, and I demonstrate this empirically on the TrackML dataset. The model not only significantly outperforms the physics performance of the baseline model, it is up to an order of magnitude faster in inference.
引用
收藏
页数:8
相关论文
共 50 条
  • [1] End-to-End Learning for Digital Hologram Reconstruction
    Xu, Zhimin
    Zuo, Si
    Lam, Edmund Y.
    HIGH-SPEED BIOMEDICAL IMAGING AND SPECTROSCOPY III: TOWARD BIG DATA INSTRUMENTATION AND MANAGEMENT, 2018, 10505
  • [2] End-to-End Learning of Motion Representation for Video Understanding
    Fan, Lijie
    Huang, Wenbing
    Gan, Chuang
    Ermon, Stefano
    Gong, Boqing
    Huang, Junzhou
    2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR), 2018, : 6016 - 6025
  • [3] End-to-End Learning of Joint Geometric and Probabilistic Constellation Shaping
    Aref, Vahid
    Chagnon, Mathieu
    2022 OPTICAL FIBER COMMUNICATIONS CONFERENCE AND EXHIBITION (OFC), 2022,
  • [4] Joint discriminative representation learning for end-to-end person search
    Zhang, Pengcheng
    Yu, Xiaohan
    Bai, Xiao
    Wang, Chen
    Zheng, Jin
    Ning, Xin
    PATTERN RECOGNITION, 2024, 147
  • [5] End-to-end representation learning for Correlation Filter based tracking
    Valmadre, Jack
    Bertinetto, Luca
    Henriques, Joao
    Vedaldi, Andrea
    Torr, Philip H. S.
    30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017), 2017, : 5000 - 5008
  • [6] Learning reinforced attentional representation for end-to-end visual tracking
    Gao, Peng
    Zhang, Qiquan
    Wang, Fei
    Xiao, Liyi
    Fujita, Hamido
    Zhang, Yan
    INFORMATION SCIENCES, 2020, 517 : 52 - 67
  • [7] End-to-end deep learning framework for digital holographic reconstruction
    Zhenbo Ren
    Zhimin Xu
    Edmund Y.Lam
    Advanced Photonics, 2019, (01) : 76 - 87
  • [8] End-to-end deep learning framework for digital holographic reconstruction
    Ren, Zhenbo
    Xu, Zhimin
    Lam, Edmund Y.
    ADVANCED PHOTONICS, 2019, 1 (01):
  • [9] End-to-End Rationale Reconstruction
    Dhaouadi, Mouna
    Oakes, Bentley James
    Famelis, Michalis
    PROCEEDINGS OF THE 37TH IEEE/ACM INTERNATIONAL CONFERENCE ON AUTOMATED SOFTWARE ENGINEERING, ASE 2022, 2022,
  • [10] Spatial and temporal learning representation for end-to-end recording device identification
    Chunyan Zeng
    Dongliang Zhu
    Zhifeng Wang
    Minghu Wu
    Wei Xiong
    Nan Zhao
    EURASIP Journal on Advances in Signal Processing, 2021