Mantis Shrimp：探索计算机视觉网络中用于光度红移估计的光度波段利用
Mantis Shrimp: Exploring Photometric Band Utilization in Computer Vision Networks for Photometric Redshift Estimation
AI总结：
本研究提出多巡天深度学习模型Mantis Shrimp，融合多波段图像进行光度红移估计，验证了早晚期融合方法性能相当，证实模型能利用全波段信息，可用于小型星系研究。
摘要：
我们提出了Mantis Shrimp，这是一种用于光度红移估计的多巡天深度学习模型，融合了紫外（GALEX）、光学（PanSTARRS）和红外（UnWISE）图像数据。机器学习目前已是光度红移估计的成熟方法，在光谱证认星系密度较高的区域，其性能普遍被认为优于基于模板的方法。已有多项研究表明，基于图像的卷积神经网络性能能够超过基于表格的颜色/星等模型。与表格模型相比，图像模型存在额外的设计复杂度：目前人们尚不清楚如何融合来自不同仪器、具有不同分辨率或噪声特性的输入数据。Mantis Shrimp模型利用切图图像估计红移的条件密度。其密度估计结果校准良好，在现有光谱证认星系的分布中，点估计表现优异，偏差（bias）为1e-2，散射度（NMAD）为2.44e-2，灾难性异常值率（$η$）为17.53$\%$。我们发现，早期融合方法（例如对不同仪器的图像进行重采样和堆叠）的性能与晚期融合方法（例如拼接潜在空间表征）相当，因此设计选择最终可由用户决定。最后，我们研究了模型如何学习利用跨波段信息，发现有证据表明我们的模型成功整合了所有巡天项目的信息。我们的模型在大样本星系分析中的适用性受限于从外部服务器下载切图的速度；不过，该模型可用于较小规模的研究，例如为恒星族群合成生成红移先验。
英文摘要：
We present Mantis Shrimp, a multi-survey deep learning model for photometric redshift estimation that fuses ultra-violet (GALEX), optical (PanSTARRS), and infrared (UnWISE) imagery. Machine learning is now an established approach for photometric redshift estimation, with generally acknowledged higher performance in areas with a high density of spectroscopically identified galaxies over template-based methods. Multiple works have shown that image-based convolutional neural networks can outperform tabular-based color/magnitude models. In comparison to tabular models, image models have additional design complexities: it is largely unknown how to fuse inputs from different instruments which have different resolutions or noise properties. The Mantis Shrimp model estimates the conditional density estimate of redshift using cutout images. The density estimates are well calibrated and the point estimates perform well in the distribution of available spectroscopically confirmed galaxies with (bias = 1e-2), scatter (NMAD = 2.44e-2) and catastrophic outlier rate ($η$=17.53$\%$). We find that early fusion approaches (e.g., resampling and stacking images from different instruments) match the performance of late fusion approaches (e.g., concatenating latent space representations), so that the design choice ultimately is left to the user. Finally, we study how the models learn to use information across bands, finding evidence that our models successfully incorporates information from all surveys. The applicability of our model to the analysis of large populations of galaxies is limited by the speed of downloading cutouts from external servers; however, our model could be useful in smaller studies such as generating priors over redshift for stellar population synthesis.
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。
