用自回归分块方法提升天文图像中微弱天体的检测精度
Neural Posterior Estimation with Autoregressive Tiling for Detecting Objects in Astronomical Images
- 基于棋盘式分块的自回归变分分布，模拟后验依赖结构
- 在斯隆数字巡天数据上达到当前最佳检测效果
- 特别适合处理重叠微弱天体，适合天文学图像分析
未来天文巡天将生成海量高分辨率夜空图像，包含数十亿恒星与星系信息。从中检测并表征天体是天文学核心任务，但因多数天体微弱且常相互重叠而极具挑战。本文提出一种摊销变分推断方法解决小物体检测问题。核心创新是引入一组空间自回归变分分布，按K色棋盘模式分割并排序潜在空间。该分布的条件独立性结构与真实后验一致。通过神经后验估计（NPE）优化，最小化前向KL散度。在斯隆数字巡天（SDSS）图像上，该方法取得当前最优性能，并显著改善后验校准效果。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。