A novel deep-learning paradigm for synthesis imaging by radio interferometry in astronomy was recently proposed, dubbed “Residual-to-Residual DNN series for high-Dynamic range imaging” (R2D2). In this work, we start by shedding light on R2D2's algorithmic structure, interpreting it as a learned version of CLEAN with minor cycles substituted with a deep neural network (DNN) whose training is iteration-specific. We then proceed with R2D2's first demonstration on real data, for monochromatic intensity imaging of the radio galaxy Cygnus A from S-band observations with the Very Large Array. We show that the modeling power of R2D2's learning approach enables delivering high-precision imaging, superseding the resolution of CLEAN, and matching the precision of modern optimization and plug-and-play algorithms, respectively uSARA and AIRI. Requiring few major-cycle iterations only, R2D2 provides a much faster reconstruction than uSARA and AIRI, known to be highly iterative, and is at least as fast as CLEAN.

中文翻译：

---

使用 R2D2 深度快速地清洁 Cygnus A

最近提出了一种用于天文学中射电干涉测量合成成像的新型深度学习范式，被称为“用于高动态范围成像的残差到残差 DNN 系列”（R2D2）。在这项工作中，我们首先阐明 R2D2 的算法结构，将其解释为 CLEAN 的学习版本，其中较小的循环被深度神经网络 (DNN) 取代，而深度神经网络 (DNN) 的训练是特定于迭代的。然后，我们继续进行 R2D2 对真实数据的首次演示，用于来自射电星系天鹅座 A 的单色强度成像S使用甚大阵列进行波段观测。我们证明，R2D2 学习方法的建模能力能够提供高精度成像，取代 CLEAN 的分辨率，并与现代优化和即插即用算法（分别为 uSARA 和 AIRI）的精度相匹配。 R2D2 仅需要很少的主周期迭代，提供比 uSARA 和 AIRI 更快的重建速度，众所周知，uSARA 和 AIRI 具有高度迭代性，并且至少与 CLEAN 一样快。