MeerKAT 宽场连续谱图像上的自监督学习
Self-Supervised Learning on MeerKAT Wide-Field Continuum Images
AI总结：
本文研究如何将自监督学习直接应用于 MeerKAT 宽场连续谱图像，无需提取单星系切块，通过 DINO 框架训练 ResNet50 和 ViT 模型，在射电星系形态分类和致密源数量预测上达到或超越现有最先进方法，并显著降低数据准备成本。
摘要：
应用于自然图像的自监督学习（SSL）已展现出在没有标签的情况下学习有意义、低维表示的卓越能力，从而产生可适应许多不同任务的模型。迄今为止，SSL 在天文图像上的应用仅限于 Galaxy Zoo 数据集，这些数据集需要大量预处理来准备以单个星系为中心的稀疏图像。在 Square Kilometer Array（SKA）时代，宽场巡天仪器处于前沿地位，这种收集训练数据的方法是不切实际的。我们证明，来自 MeerKAT Galactic Cluster Legacy Survey（MGCLS）等巡天的连续谱图像可以成功地用于 SSL，而无需提取单星系切块。使用 SSL 框架 DINO，我们实验了各种预处理步骤、数据增强和架构，以确定针对此类数据的最佳方法。我们训练了 ResNet50 和 Vision Transformer（ViT）两种骨干网络。我们的模型在 FRI/FRII 形态分类上达到了与最先进结果（在 Radio Galaxy Zoo 上训练）相当的性能。此外，它们通过线性回归预测致密源数量时具有更高的准确率。然而，在多类别形态分类上，微调后我们的模型、最先进模型和开源模型之间表现相似。利用宽场图像中富含源的裁剪块来训练多用途模型是一种易于扩展的方法，可显著减少数据准备时间。对于本工作中评估的任务，两万个裁剪块足以作为训练数据，使模型产生与最先进方法相似的结果。未来，诸如源检测与表征等复杂任务，以及领域特定任务，应当能够展示使用射电天文数据训练模型相对于自然图像基础模型的真正优势。
英文摘要：
Self-supervised learning (SSL) applied to natural images has demonstrated a remarkable ability to learn meaningful, low-dimension representations without labels, resulting in models that are adaptable to many different tasks. Until now, applications of SSL to astronomical images have been limited to Galaxy Zoo datasets, which require a significant amount of pre-processing to prepare sparse images centered on a single galaxy. With wide-field survey instruments at the forefront of the Square Kilometer Array (SKA) era, this approach to gathering training data is impractical. We demonstrate that continuum images from surveys like the MeerKAT Galactic Cluster Legacy Survey (MGCLS) can be successfully used with SSL, without extracting single-galaxy cutouts. Using the SSL framework DINO, we experiment with various preprocessing steps, augmentations, and architectures to determine the optimal approach for this data. We train both ResNet50 and Vision Transformer (ViT) backbones. Our models match state-of-the-art results (trained on Radio Galaxy Zoo) for FRI/FRII morphology classification. Furthermore, they predict the number of compact sources via linear regression with much higher accuracy. However, fine-tuning results in similar performance between our models, the state-of-the-art, and open-source models on multi-class morphology classification. Using source-rich crops from wide-field images to train multi-purpose models is an easily scalable approach that significantly reduces data preparation time. For the tasks evaluated in this work, twenty thousand crops is sufficient training data for models that produce results similar to state-of-the-art. In the future, complex tasks like source detection and characterization, together with domain-specific tasks, ought to demonstrate the true advantages of training models with radio astronomy data over natural-image foundation models.
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。
