采用自回归平铺的神经后验估计用于天文图像中的目标检测
Neural Posterior Estimation with Autoregressive Tiling for Detecting Objects in Astronomical Images
AI总结：
针对天文巡天图像中暗弱且重叠目标的检测难题，提出按 $K$ 色棋盘格组织潜在空间的空间自回归变分分布，并结合 CNN 与 NPE 训练，在 SDSS 上达到 SOTA 并改善后验校准。
摘要：
即将开展的天文巡天将生成拍字节级的夜空高分辨率图像，提供有关数十亿颗恒星和星系的信息。检测并表征这些图像中的天文目标是天文学中的一项基础任务，同时也颇具挑战性，因为其中大多数目标都很暗弱，而且许多目标在视觉上与其他目标相互重叠。我们提出一种摊销变分推断流程，以解决这一小目标检测问题。我们的关键创新是一族空间自回归变分分布，它们按照一种 $K$ 色棋盘格模式对潜在空间进行划分和排序。通过构造，该变分族的条件独立性与后验分布的条件独立性相对应。我们使用神经后验估计（NPE）拟合由卷积神经网络参数化的变分分布，以最小化前向 KL 散度的期望。利用来自 Sloan Digital Sky Survey 的图像，我们的方法取得了最先进的性能。我们进一步证明，所提出的自回归结构显著改善了后验校准。
英文摘要：
Upcoming astronomical surveys will produce petabytes of high-resolution images of the night sky, providing information about billions of stars and galaxies. Detecting and characterizing the astronomical objects in these images is a fundamental task in astronomy -- and a challenging one, as most of these objects are faint and many visually overlap with other objects. We propose an amortized variational inference procedure to solve this instance of small-object detection. Our key innovation is a family of spatially autoregressive variational distributions that partition and order the latent space according to a $K$-color checkerboard pattern. By construction, the conditional independencies of this variational family mirror those of the posterior distribution. We fit the variational distribution, which is parameterized by a convolutional neural network, using neural posterior estimation (NPE) to minimize an expectation of the forward KL divergence. Using images from the Sloan Digital Sky Survey, our method achieves state-of-the-art performance. We further demonstrate that the proposed autoregressive structure greatly improves posterior calibration.
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。
