Related papers: Cosmic Ray Rejection with Attention Augmented Deep…
Subsurface delaminations in concrete bridge decks remain undetectable through conventional visual inspection, necessitating automated non-destructive evaluation methods. This work introduces a deep learning framework that integrates Ground…
Deep Learning models have been increasingly exploited in astrophysical studies, yet such data-driven algorithms are prone to producing biased outputs detrimental for subsequent analyses. In this work, we investigate two major forms of…
Recently, the attention mechanism has been successfully applied in convolutional neural networks (CNNs), significantly boosting the performance of many computer vision tasks. Unfortunately, few medical image recognition approaches…
We demonstrate that the energy spectra of Ultra High Energy Cosmic rays (UHECR) as observed by AGASA, Fly's Eye, HiRes and Yakutsk detectors, have the imprints of UHE proton interaction with the CMB radiation in the form of the dip at…
The origin of cosmic rays (CRs) has puzzled scientists since the pioneering discovery by Victor Hess in 1912. In the last decade, however, modern supercomputers have opened a new window on the processes regulating astrophysical…
Deep learning has become a powerful tool for medical image analysis; however, conventional Convolutional Neural Networks (CNNs) often fail to capture the fine-grained and complex features critical for accurate diagnosis. To address this…
The main objective of the Cosmic-Ray Extremely Distributed Observatory (CREDO) is the detection and analysis of extended cosmic ray phenomena, so-called super-preshowers (SPS), using existing as well as new infrastructure (cosmic-ray…
We present a method for detecting cosmic rays in single images. The algorithm is based on simple analysis of the histogram of the image data and does not use any modeling of the picture of the object. It does not require a good signal to…
Data augmentation is a critical component of training deep learning models. Although data augmentation has been shown to significantly improve image classification, its potential has not been thoroughly investigated for object detection.…
We present a new procedure rooted in deep learning to construct science images from data cubes collected by astronomical instruments using HxRG detectors in low-flux regimes. It improves on the drawbacks of the conventional algorithms to…
Current neural networks-based object detection approaches processing LiDAR point clouds are generally trained from one kind of LiDAR sensors. However, their performances decrease when they are tested with data coming from a different LiDAR…
Magnification bias offers a uniquely powerful and independent route to cosmological information. As a gravitational-lensing observable, it probes galaxy-matter correlations without relying on galaxy shapes, PSF modelling, or…
Unmanned Aerial Vehicles (UAV) have been standing out due to the wide range of applications in which they can be used autonomously. However, they need intelligent systems capable of providing a greater understanding of what they perceive to…
Quasars experiencing strong lensing offer unique viewpoints on subjects related to the cosmic expansion rate, the dark matter profile within the foreground deflectors, and the quasar host galaxies. Unfortunately, identifying them in…
Deep learning models have great potential in medical imaging, including orthodontics and skeletal maturity assessment. However, applying a model to data different from its training set can lead to unreliable predictions that may impact…
Low-energy cosmic-rays (CRs) control the thermo-chemical state and the coupling between gas and magnetic fields in dense molecular clouds, the sites of star-formation. However, current estimates of the low-energy CR spectrum ($E \lesssim 1$…
As AI-generated images become increasingly photorealistic, distinguishing them from natural images poses a growing challenge. This paper presents a robust detection framework that leverages multiple uncertainty measures to decide whether to…
Learning powerful discriminative features for remote sensing image scene classification is a challenging computer vision problem. In the past, most classification approaches were based on handcrafted features. However, most recent…
Multi-view 3D object detection systems often struggle with generating precise predictions due to the challenges in estimating depth from images, increasing redundant and incorrect detections. Our paper presents Ray Denoising, an innovative…
We present a method for automatic detection and classification of galaxies which includes a novel data-augmentation procedure to make trained models more robust against the data taken from different instruments and contrast-stretching…