Related papers: Real-time Light Curve Classification Framework for…
Automatic classification methods applied to sky surveys have revolutionized the astronomical target selection process. Most surveys generate a vast amount of time series, or \quotes{lightcurves}, that represent the brightness variability of…
We present a unique method that allows the LSST to scan the sky for stellar variability on short timescales. The operational component of the strategy requires LSST to take star trail images. The image processing component uses deep…
We study semi-supervised learning (SSL) for vision transformers (ViT), an under-explored topic despite the wide adoption of the ViT architectures to different tasks. To tackle this problem, we propose a new SSL pipeline, consisting of first…
The Large Synoptic Survey Telescope (LSST) is a wide-field imaging system of unprecedented etendue. The initial goal of the project is to carry out a ten year imaging survey in six broad passbands (ugrizy) that cover $350 nm < \lambda < 1.1…
Sequential sensor data is generated in a wide variety of practical applications. A fundamental challenge involves learning effective classifiers for such sequential data. While deep learning has led to impressive performance gains in recent…
The requiring of large amounts of annotated training data has become a common constraint on various deep learning systems. In this paper, we propose a weakly supervised scene text detection method (WeText) that trains robust and accurate…
In recent years, weakly supervised object detection (WSOD) has attracted much attention due to its low labeling cost. The success of recent WSOD models is often ascribed to the two-stage multi-class classification (MCC) task, i.e., multiple…
Nighttime light (NTL) remote sensing observation serves as a unique proxy for quantitatively assessing progress toward meeting a series of Sustainable Development Goals (SDGs), such as poverty estimation, urban sustainable development, and…
In this work, we present a framework for estimating and evaluating uncertainty in deep-attention-based classifiers for light curves for variable stars. We implemented three techniques, Deep Ensembles (DEs), Monte Carlo Dropout (MCD) and…
Strong gravitationally lensed supernovae (LSNe) are rare but extremely valuable probes of cosmology and astrophysics. Prompt identification within the alert streams of time-domain surveys such as the Rubin Legacy Survey of Space and Time…
Self-supervised contrastive learning is an effective approach for addressing the challenge of limited labelled data. This study builds upon the previously established two-stage patch-level, multi-label classification method for…
Network traffic classification (NTC) is vital for efficient network management, security, and performance optimization, particularly with 5G/6G technologies. Traditional methods, such as deep packet inspection (DPI) and port-based…
The ability to automatically and robustly self-verify periodicity present in time-series astronomical data is becoming more important as data sets rapidly increase in size. The age of large astronomical surveys has rendered manual…
LSST will open new vistas for cosmology in the next decade, but it cannot reach its full potential without data from other telescopes. Cosmological constraints can be greatly enhanced using wide-field ($>20$ deg$^2$ total survey area),…
Object detection is a cornerstone of environmental perception in advanced driver assistance systems(ADAS). However, most existing methods rely on RGB cameras, which suffer from significant performance degradation under low-light conditions…
With the rapid development of time-domain surveys, the availability of massive light curve data offers new opportunities for studying stellar evolution and variable star classification, while simultaneously posing challenges for feature…
Labeling data is often expensive and time-consuming, especially for tasks such as object detection and instance segmentation, which require dense labeling of the image. While few-shot object detection is about training a model on novel…
This work proposes a hybrid unsupervised and supervised learning method to pre-train models applied in Earth observation downstream tasks when only a handful of labels denoting very general semantic concepts are available. We combine a…
Due to the high cost of annotating accurate pixel-level labels, semi-supervised learning has emerged as a promising approach for cloud detection. In this paper, we propose CloudMatch, a semi-supervised framework that effectively leverages…
Network traffic classification, which has numerous applications from security to billing and network provisioning, has become a cornerstone of today's computer networks. Previous studies have developed traffic classification techniques…