Related papers: MAGIC: Microlensing Analysis Guided by Intelligent…
Composed Image Retrieval (CIR) enables image search by combining a reference image with modification text. Intrinsic noise in CIR triplets incurs intrinsic uncertainty and threatens the model's robustness. Probabilistic learning approaches…
Ongoing and future surveys with repeat imaging in multiple bands are producing (or will produce) time-spaced measurements of brightness, resulting in the identification of large numbers of variable sources in the sky. A large fraction of…
In contrast to human vision, common recognition algorithms often fail on partially occluded images. We propose characterizing, empirically, the algorithmic limits by finding a minimal recognizable patch (MRP) that is by itself sufficient to…
Unfolding is an important procedure in particle physics experiments which corrects for detector effects and provides differential cross section measurements that can be used for a number of downstream tasks, such as extracting fundamental…
Due to the high efficiency of planet detections, current microlensing planet searches focus on high-magnification events. High-magnification events are sensitive to remote binary companions as well and thus a sample of wide-separation…
Accurate uncertainty quantification is critical for reliable predictive modeling. Existing methods typically address either aleatoric uncertainty due to measurement noise or epistemic uncertainty resulting from limited data, but not both in…
We present a two-component Machine Learning (ML) based approach for classifying astronomical images by data-quality via an examination of sources detected in the images and image pixel values from representative sources within those images.…
Gravitational microlensing events produced by lenses composed of binary masses are important because they provide a major channel to determine physical parameters of lenses. In this work, we analyze the light curves of two binary-lens…
The development of synoptic sky surveys has led to a massive amount of data for which resources needed for analysis are beyond human capabilities. To process this information and to extract all possible knowledge, machine learning…
Conventional image processing for particle shadow image is usually time-consuming and suffers degraded image segmentation when dealing with the images consisting of complex-shaped and clustered particles with varying backgrounds. In this…
Method for a mosaic image representation (MIR) is proposed for a selective treatment of image fragments of different transition frequency. MIR method is based on piecewise-constant image approximation on a non-uniform orthogonal grid…
Photonic computation started to shape the future of fast, efficient and accessible computation. The advantages brought by light based Diffractive Deep Neural Networks (D2NN), are shown to be overwhelmingly advantageous especially in…
Deep unrolling is an emerging deep learning-based image reconstruction methodology that bridges the gap between model-based and purely deep learning-based image reconstruction methods. Although deep unrolling methods achieve…
In the process of analyzing an observed light curve, one often confronts various scenarios that can mimic the planetary signals causing difficulties in the accurate interpretation of the lens system. In this paper, we present the analysis…
Timing analysis is a powerful tool used to determine periodic features of physical phenomena. Here we review two applications of timing analysis to gravitational microlensing events. The first one, in particular cases, allows the estimation…
The primary aim of this research is to evaluate several convolutional neural network-based object detection algorithms for identifying oscillation-like patterns in light curves of eclipsing binaries. This involves creating a robust…
Multi-aspect controllable text generation aims to control the generated texts in attributes from multiple aspects (e.g., "positive" from sentiment and "sport" from topic). For ease of obtaining training samples, existing works neglect…
The existence of galaxy intrinsic clustering severely hampers the weak lensing reconstruction from cosmic magnification. In paper I \citep{Yang2011}, we proposed a minimal variance estimator to overcome this problem. By utilizing the…
Collective insights from a group of experts have always proven to outperform an individual's best diagnostic for clinical tasks. For the task of medical image segmentation, existing research on AI-based alternatives focuses more on…
This work addresses image restoration tasks through the lens of inverse problems using unpaired datasets. In contrast to traditional approaches -- which typically assume full knowledge of the forward model or access to paired degraded and…