arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.18516astro-ph.IMastro-ph.HE
收藏

用于成像大气切伦科夫望远镜的多视角深度学习

Multi-View Deep Learning for Imaging Atmospheric Cherenkov Telescopes

Hannes Warnhofer, Samuel T. Spencer, Alison M. W. Mitchell

AI总结:

本文研究多视角深度学习在H.E.S.S.切伦科夫望远镜数据中的应用,发现视角信息融合的时机比融合方法对模型性能影响更大。

摘要:

本研究笔记探讨了基于深度学习的多视角成像技术应用于H.E.S.S.成像大气切伦科夫望远镜阵列数据的问题。我们发现,在神经网络中,来自不同视角的层信息融合发生得越早,模型在该数据上的表现就越好。我们的分析表明,网络中不同视角信息被合并的位置对模型性能的重要性,远大于用于合并信息的方法。

英文摘要:

This research note concerns the application of deep-learning-based multi-view-imaging techniques to data from the H.E.S.S. Imaging Atmospheric Cherenkov Telescope array. We find that the earlier the fusion of layer information from different views takes place in the neural network, the better our model performs with this data. Our analysis shows that the point in the network where the information from the different views is combined is far more important for the model performance than the method used to combine the information.

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。

↑