arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.00897eess.IVastro-ph.GAcs.AIcs.CVcs.LG
收藏

VisRec:一种用于射电干涉测量数据重建的半监督方法

VisRec: A Semi-Supervised Approach to Radio Interferometric Data Reconstruction

HKUST(GZ)(香港科技大学(广州));SYSU(中山大学);HKUST(香港科技大学);GZHU(广州大学)

Ruoqi Wang, Haitao Wang, Qiong Luo, Feng Wang, Hejun Wu

AI总结:

针对射电干涉可见度数据标注稀缺问题,提出模型无关的半监督框架 VisRec,通过监督增强与无标签伪标签训练提升重建质量、鲁棒性和跨配置泛化能力。

摘要:

射电望远镜会产生关于天体的可见度数据,但这些数据稀疏且含有噪声。因此,基于原始可见度数据生成的图像质量较低。近期研究已使用深度学习模型重建可见度数据,以获得更干净的图像。然而,这些方法依赖大量带标签训练数据,需要射电天文学家投入大量标注工作。为应对这一挑战,我们提出 VisRec,这是一种与模型无关的半监督学习方法,用于可见度数据重建。具体而言,VisRec 同时包含监督学习模块和无监督学习模块。在监督学习模块中,我们引入一组数据增强函数,以生成多样化的训练样本。相比之下,VisRec 中的无监督学习模块对无标签数据进行增强,并使用来自未增强可见度数据的重建结果作为训练伪标签。这种混合方法使 VisRec 能够有效利用带标签和无标签数据。通过这种方式,即使带标签数据稀缺,VisRec 也能表现良好。我们的评估结果表明,VisRec 在重建质量、对常见观测扰动的鲁棒性,以及对不同望远镜配置的泛化能力方面,均优于所有基线方法。

英文摘要:

Radio telescopes produce visibility data about celestial objects, but these data are sparse and noisy. As a result, images created on raw visibility data are of low quality. Recent studies have used deep learning models to reconstruct visibility data to get cleaner images. However, these methods rely on a substantial amount of labeled training data, which requires significant labeling effort from radio astronomers. Addressing this challenge, we propose VisRec, a model-agnostic semi-supervised learning approach to the reconstruction of visibility data. Specifically, VisRec consists of both a supervised learning module and an unsupervised learning module. In the supervised learning module, we introduce a set of data augmentation functions to produce diverse training examples. In comparison, the unsupervised learning module in VisRec augments unlabeled data and uses reconstructions from non-augmented visibility data as pseudo-labels for training. This hybrid approach allows VisRec to effectively leverage both labeled and unlabeled data. This way, VisRec performs well even when labeled data is scarce. Our evaluation results show that VisRec outperforms all baseline methods in reconstruction quality, robustness against common observation perturbation, and generalizability to different telescope configurations.

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。

↑