Related papers: Empirical Uncertainty Estimators for Astrometry fr…

The ability to acknowledge the inevitable uncertainty in their knowledge and reasoning is a prerequisite for AI systems to be truly truthful and reliable. In this paper, we present a taxonomy of uncertainty specific to vision-language AI…

Deep learning methods for unsupervised registration often rely on objectives that assume a uniform noise level across the spatial domain (e.g. mean-squared error loss), but noise distributions are often heteroscedastic and input-dependent…

Decomposing prediction uncertainty into aleatoric (irreducible) and epistemic (reducible) components is critical for the reliable deployment of machine learning systems. While the mutual information between the response variable and model…

When comparing modern fundamental reference frames in the radio (International Celestial Reference Frame) and optical (Gaia), a couple of bright radio reference sources appear to have very large radio-optical offsets, from tens up to…

In recent years, machine learning has witnessed extensive adoption across various sectors, yet its application in medical image-based disease detection and diagnosis remains challenging due to distribution shifts in real-world data. In…

Context. We present a celestial reference frame (CRF) based on the combination of independent, multifrequency radio source position catalogs using nearly 40 years of Very Long Baseline Interferometry observations at the standard geodetic…

We develop estimators of agreement and disagreement between correlated cosmological data sets. These account for data correlations when computing the significance of both tensions and excess confirmation while remaining statistically…

A set of novel approaches for estimating epistemic uncertainty in deep neural networks with a single forward pass has recently emerged as a valid alternative to Bayesian Neural Networks. On the premise of informative representations, these…

A new international Pilot Project for the re-determination of the ICRF was initiated by the International VLBI Service for Geodesy and Astrometry (IVS) in January 2005. The purpose of this project is to compare the individual CRF solutions…

Stereo matching plays a crucial role in various applications, where understanding uncertainty can enhance both safety and reliability. Despite this, the estimation and analysis of uncertainty in stereo matching have been largely overlooked.…

We report on the expected astrometric performance of the Thirty Meter Telescope's InfraRed Imaging Spectrometer (IRIS) as determined using simulated images of the Galactic center. This region of the Galaxy harbors a supermassive black hole…

Instance segmentation has witnessed promising advancements through deep neural network-based algorithms. However, these models often exhibit incorrect predictions with unwarranted confidence levels. Consequently, evaluating prediction…

To estimate real accuracy of EOP prediction real-time predictions made by the IERS Subbureau for Rapid Service and Prediction (USNO) and at the Institute of Applied Astronomy (IAA) EOP Service are analyzed. Methods of a priory estimate of…

Uncertainty estimation bears the potential to make deep learning (DL) systems more reliable. Standard techniques for uncertainty estimation, however, come along with specific combinations of strengths and weaknesses, e.g., with respect to…

Identifying and disentangling sources of predictive uncertainty is essential for trustworthy supervised learning. We argue that widely used second-order methods that disentangle aleatoric and epistemic uncertainty are fundamentally…

The uncertainty quantification of prediction models (e.g., neural networks) is crucial for their adoption in many robotics applications. This is arguably as important as making accurate predictions, especially for safety-critical…

Being uncertain when facing the unknown is key to intelligent decision making. However, machine learning algorithms lack reliable estimates about their predictive uncertainty. This leads to wrong and overly-confident decisions when…

Reliable estimation of predictive uncertainty is crucial for machine learning applications, particularly in high-stakes scenarios where hedging against risks is essential. Despite its significance, there is no universal agreement on how to…

Observations of gravitational waves emitted by merging compact binaries have provided tantalising hints about stellar astrophysics, cosmology, and fundamental physics. However, the physical parameters describing the systems, (mass, spin,…

Observations of present and future X-ray telescopes include a large number of serendipidious sources of unknown types. They are a rich source of knowledge about X-ray dominated astronomical objects, their distribution, and their evolution.…