基于Few-Shot学习的星系形态分类
Classifying Galaxy Morphologies with Few-Shot Learning
摘要：
星系形态的分类在天体物理学中是至关重要的，因为星系的形态特征是星系演化的有力标志。随着即将到来的大规模成像调查，数十亿个星系图像挑战天文学家通过应用传统方法或人工检查来完成分类任务。因此，机器学习，特别是有监督的深度学习，由于其出色的自动化，效率和准确性，最近已被广泛用于对星系形态进行分类。然而，监督式深度学习需要大量的训练集，这会导致相当大的工作量;而且，结果强烈依赖于训练集的特征，这可能会导致有偏见的结果。在这项研究中，我们尝试Few-Shot学习绕过这两个问题。我们的研究采用了来自Kaggle上的Galaxy Zoo Challenge Project的数据集，并根据相应的真值表将其分为五类。通过使用基于Siamese Networks的Few-Shot学习和基于AlexNet、VGG_16和ResNet_50的监督深度学习对上述数据集进行分类，我们发现，在大多数情况下，Few-Shot学习的准确率最高，当训练集包含1000张图像时，与AlexNet相比，$21\%$的改进最显著。此外，为了保证准确率不低于90\%，Few-Shot学习需要$\sim$ 6300张图像进行训练，而ResNet_50需要13000张图像。考虑到上述优点，Few-Shot学习适用于星系形态的分类，甚至适用于识别罕见的天体物理对象，尽管只有有限的训练集由观测数据组成。
英文摘要：
The taxonomy of galaxy morphology is critical in astrophysics as the morphological properties are powerful tracers of galaxy evolution. With the upcoming Large-scale Imaging Surveys, billions of galaxy images challenge astronomers to accomplish the classification task by applying traditional methods or human inspection. Consequently, machine learning, in particular supervised deep learning, has been widely employed to classify galaxy morphologies recently due to its exceptional automation, efficiency, and accuracy. However, supervised deep learning requires extensive training sets, which causes considerable workloads; also, the results are strongly dependent on the characteristics of training sets, which leads to biased outcomes potentially. In this study, we attempt Few-shot Learning to bypass the two issues. Our research adopts the dataset from Galaxy Zoo Challenge Project on Kaggle, and we divide it into five categories according to the corresponding truth table. By classifying the above dataset utilizing few-shot learning based on Siamese Networks and supervised deep learning based on AlexNet, VGG_16, and ResNet_50 trained with different volumes of training sets separately, we find that few-shot learning achieves the highest accuracy in most cases, and the most significant improvement is $21\%$ compared to AlexNet when the training sets contain 1000 images. In addition, to guarantee the accuracy is no less than 90\%, few-shot learning needs $\sim$6300 images for training, while ResNet_50 requires 13000 images. Considering the advantages stated above, foreseeably, few-shot learning is suitable for the taxonomy of galaxy morphology and even for identifying rare astrophysical objects, despite limited training sets consisting of observational data only.
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。
