Related papers: MODEL&CO: Exoplanet detection in angular different…
Among the research efforts to segment the retinal vasculature from fundus images, deep learning models consistently achieve superior performance. However, this data-driven approach is very sensitive to domain shifts. For fundus images, such…
Most current high contrast imaging point spread function (PSF) subtraction algorithms use some form of a least-squares noise minimization to find exoplanets that are, before post-processing, often hidden below the instrumental speckle…
A new class of high-contrast image analysis algorithms that empirically fit and subtract systematic noise has lead to recent discoveries of faint exoplanet /substellar companions and scattered light images of circumstellar disks. These…
The exoplanet detection is the most exciting and challenging field of astronomy. The discovery of many exoplanets has revolutionized our understanding of the formation and evolution of planetary systems and has showed new ways to search for…
Many unsupervised visual anomaly detection methods train an auto-encoder to reconstruct normal samples and then leverage the reconstruction error map to detect and localize the anomalies. However, due to the powerful modeling and…
Radial velocity surveys for extra-solar planets generally require substantial amounts of large telescope time in order to monitor a sufficient number of stars. Two of the aspects which can limit such surveys are the single-object…
The characterization of nearby rocky exoplanets will become feasible with the next generation of telescopes, such as the Extremely Large Telescope (ELT) and the mission concept Habitable Worlds Observatory (HWO). Using an improved model…
It is widely recognized that deep neural networks are sensitive to bias in the data. This means that during training these models are likely to learn spurious correlations between data and labels, resulting in limited generalization…
One of the top remaining science challenges in astronomical optics is the direct imaging and characterization of extrasolar planets and planetary systems. Directly imaging exoplanets from ground-based observatories requires combining…
In this paper we present a two-step neural network model to separate detections of solar system objects from optical and electronic artifacts in data obtained with the "Asteroid Terrestrial-impact Last Alert System" (ATLAS), a near-Earth…
As next-generation imaging instruments and interferometers search for planets closer to their stars, they must contend with increasing orbital motion and longer integration times. These compounding effects make it difficult to detect faint…
Object detection, as a fundamental computer vision task, has achieved a remarkable progress with the emergence of deep neural networks. Nevertheless, few works explore the adversarial robustness of object detectors to resist adversarial…
Effective image post-processing algorithms are vital for the successful direct imaging of exoplanets. Standard PSF subtraction methods use techniques based on a low-rank approximation to separate the rotating planet signal from the…
Over the past decade, hundreds of nights have been spent on the worlds largest telescopes to search for and directly detect new exoplanets using high-contrast imaging (HCI). Thereby, two scientific goals are of central interest: First, to…
Measurement noise is an integral part while collecting data of a physical process. Thus, noise removal is necessary to draw conclusions from these data, and it often becomes essential to construct dynamical models using these data. We…
Anomaly detection is to identify samples that do not conform to the distribution of the normal data. Due to the unavailability of anomalous data, training a supervised deep neural network is a cumbersome task. As such, unsupervised methods…
Extra-solar planets have not been imaged directly with existing ground or space telescopes because they are too faint to be seen against the halo of the nearby bright star. Most techniques being explored to suppress the halo are achromatic,…
Reliably detecting anomalies in a given set of images is a task of high practical relevance for visual quality inspection, surveillance, or medical image analysis. Autoencoder neural networks learn to reconstruct normal images, and hence…
Owing to technological advances, the number of exoplanets discovered has risen dramatically in the last few years. However, when trying to observe Earth analogs, it is often difficult to test the veracity of detection. We have developed a…
Distance-based anomaly detection methods rely on compact in-distribution (ID) embeddings that are well separated from anomalies. However, conventional contrastive learning strategies often struggle to achieve this balance, either promoting…