Related papers: DELOS: Detecting Shallow Transits in Kepler Photom…
The training paradigm of DETRs is heavily contingent upon pre-training their backbone on the ImageNet dataset. However, the limited supervisory signals provided by the image classification task and one-to-one matching strategy result in an…
Rotation detection serves as a fundamental building block in many visual applications involving aerial image, scene text, and face etc. Differing from the dominant regression-based approaches for orientation estimation, this paper explores…
In the era of photometry with space-based telescopes, such as CHEOPS (CHaracterizing ExOPlanets Satellite), JWST (James Webb Space Telescope), PLATO (PLAnetary Transits and Oscillations of stars), and ARIEL (Atmospheric Remote-sensing…
Weak lensing by large-scale structure is a powerful probe of cosmology and of the dark universe. This cosmic shear technique relies on the accurate measurement of the shapes and redshifts of background galaxies and requires precise control…
Co-rotating spots at different latitudes on the stellar surface generate periodic photometric variability and can be useful proxies to detect Differential Rotation (DR). DR is a major ingredient of the solar dynamo but observations of…
Non-line-of-sight (NLOS) imaging relies on collecting light that is rendered incoherent from the multiple scattering events and is then post-processed to provide an estimate of the hidden scene. Here we employ coherent phase control of the…
DEEP is a multi-institutional program designed to undertake a major spectroscopic survey of 10,000+ field galaxies to I ~ 23 with a new instrument (DEIMOS) on the Keck II 10-m telescope. The scientific goals include exploring galaxy…
Inverted bottleneck layers, which are built upon depthwise convolutions, have been the predominant building blocks in state-of-the-art object detection models on mobile devices. In this work, we investigate the optimality of this design…
The existing approaches for salient motion segmentation are unable to explicitly learn geometric cues and often give false detections on prominent static objects. We exploit multiview geometric constraints to avoid such shortcomings. To…
Addressing the spatial uncertainty and spectral blending challenges in CSST slitless spectroscopy, we present a deep learning-driven, end-to-end framework based on the You Only Look Once (YOLO) models. This approach directly detects,…
We carry out a comparative analysis of the performance of three algorithms widely used to identify significant periodicities in radial-velocity (RV) datasets: the Generalised Lomb-Scargle Periodogram (GLS), its modified version based on…
Active imaging systems sample the Transient Light Transport Matrix (TLTM) for a scene by sequentially illuminating various positions in this scene using a controllable light source, and then measuring the resulting spatiotemporal light…
We describe a new method (\textsc{CompaSO}) for identifying groups of particles in cosmological $N$-body simulations. \textsc{CompaSO} builds upon existing spherical overdensity (SO) algorithms by taking into consideration the tidal radius…
We present DELIGHT, or Deep Learning Identification of Galaxy Hosts of Transients, a new algorithm designed to automatically and in real-time identify the host galaxies of extragalactic transients. The proposed algorithm receives as input…
Recently, self-supervised methods show remarkable achievements in image-level representation learning. Nevertheless, their image-level self-supervisions lead the learned representation to sub-optimal for dense prediction tasks, such as…
We present the first detection of weak gravitational lensing around spectroscopically confirmed dwarf galaxies, using the large overlap between DESI DR1 spectroscopic data and DECADE/DES weak lensing catalogs. A clean dwarf galaxy sample…
All transiting planets are at risk of contamination by blends with nearby, unresolved stars. Blends dilute the transit signal, causing the planet to appear smaller than it really is, or produce a false positive detection when the target…
Deep learning models achieve state-of-the-art performance across domains but face scalability challenges in real-time or resource-constrained scenarios. To address this, we propose Correlation of Loss Differences (CLD), a simple and…
The healthcare industry generates troves of unlabelled physiological data. This data can be exploited via contrastive learning, a self-supervised pre-training method that encourages representations of instances to be similar to one another.…
Non-line-of-sight (NLOS) imaging, recovering the hidden volume from indirect reflections, has attracted increasing attention due to its potential applications. Despite promising results, existing NLOS reconstruction approaches are…