arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2004.11336cs.CV
收藏

天文图像分类的自监督学习

Self-supervised Learning for Astronomical Image Classification

Institute of Mathematics

Ana Martinazzo, Mateus Espadoto, Nina S. T. Hirata

摘要:

在天文学中,每天通过光度测量产生大量的图像数据,这些测量扫描天空以收集来自恒星,星系和其他天体的数据。在本文中,我们提出了一种利用未标记的天文图像来预训练深度卷积神经网络的技术,以便学习特定于域的特征提取器,从而在具有少量标记数据的设置中改善机器学习技术的结果。我们表明,我们的技术产生的结果在许多情况下优于使用ImageNet预训练。

英文摘要:

In Astronomy, a huge amount of image data is generated daily by photometric surveys, which scan the sky to collect data from stars, galaxies and other celestial objects. In this paper, we propose a technique to leverage unlabeled astronomical images to pre-train deep convolutional neural networks, in order to learn a domain-specific feature extractor which improves the results of machine learning techniques in setups with small amounts of labeled data available. We show that our technique produces results which are in many cases better than using ImageNet pre-training.

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。

↑