Multi-Task Architecture with Attention for Imaging Atmospheric Cherenkov Telescope Data Analysis

Mikaël Jacquemont, Mikaël Jacquemont, Thomas Vuillaume, Alexandre Benoit, Gilles Maurin, Patrick Lambert

2021

Abstract

Gamma-ray reconstruction from Cherenkov telescope data is multi-task by nature in astrophysics. The image recorded in the Cherenkov camera pixels relates to the type, energy, incoming direction and distance of a particle from a telescope observation. We propose γ-PhysNet, a physically inspired multi-task deep neural network for gamma/proton particle classification, and gamma energy and direction reconstruction. We compare its performance with single task networks on Monte Carlo simulated data and demonstrate the interest of reconstructing the impact point as an auxiliary task. We also show that γ-PhysNet outperforms a widespread analysis method for gamma-ray reconstruction. Finally, we study attention methods to solve relevant use cases. All the experiments are conducted in the context of single telescope analysis for the Cherenkov Telescope Array data analysis.

Paper Citation

in Harvard Style

Jacquemont M., Vuillaume T., Benoit A., Maurin G. and Lambert P. (2021). Multi-Task Architecture with Attention for Imaging Atmospheric Cherenkov Telescope Data Analysis. In Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP; ISBN 978-989-758-488-6, SciTePress, pages 534-544. DOI: 10.5220/0010297405340544

in Bibtex Style

@conference{visapp21,
author={Mikaël Jacquemont and Thomas Vuillaume and Alexandre Benoit and Gilles Maurin and Patrick Lambert},
title={Multi-Task Architecture with Attention for Imaging Atmospheric Cherenkov Telescope Data Analysis},
booktitle={Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP},
year={2021},
pages={534-544},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0010297405340544},
isbn={978-989-758-488-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 16th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISIGRAPP 2021) - Volume 5: VISAPP
TI - Multi-Task Architecture with Attention for Imaging Atmospheric Cherenkov Telescope Data Analysis
SN - 978-989-758-488-6
AU - Jacquemont M.
AU - Vuillaume T.
AU - Benoit A.
AU - Maurin G.
AU - Lambert P.
PY - 2021
SP - 534
EP - 544
DO - 10.5220/0010297405340544
PB - SciTePress