Related papers: Optical Wavelength Guided Self-Supervised Feature …
Galaxy morphology is a fundamental quantity, that is essential not only for the full spectrum of galaxy-evolution studies, but also for a plethora of science in observational cosmology. While a rich literature exists on…
Sclera segmentation is crucial for developing automatic eye-related medical computer-aided diagnostic systems, as well as for personal identification and verification, because the sclera contains distinct personal features. Deep…
The classification of galaxy morphologies is an important step in the investigation of theories of hierarchical structure formation. While human expert visual classification remains quite effective and accurate, it cannot keep up with the…
Most of the achievements in artificial intelligence so far were accomplished by supervised learning which requires numerous annotated training data and thus costs innumerable manpower for labeling. Unsupervised learning is one of the…
Upcoming large astronomical surveys are expected to capture an unprecedented number of strong gravitational lensing systems. Deep learning is emerging as a promising practical tool for the detection and quantification of these galaxy-scale…
Accurate relative spectrophotometry is critical for many science applications. Small wavelength scale residuals in the flux calibration can significantly impact the measurements of weak emission and absorption features in the spectra. Using…
Recent advances in appearance-based models have shown improved eye tracking performance in difficult scenarios like occlusion due to eyelashes, eyelids or camera placement, and environmental reflections on the cornea and glasses. The key…
The primary observational goals of the Sloan Digital Sky Survey are to obtain CCD imaging of 10,000 deg^2 of the north Galactic cap in five passbands, with a limiting magnitude in the r-band of 22.5, to obtain spectroscopic redshifts of…
The lack of large labeled medical imaging datasets, along with significant inter-individual variability compared to clinically established disease classes, poses significant challenges in exploiting medical imaging information in a…
Quantitative morphological classification of galaxies is important for understanding the origin of type frequency and correlations with environment. But galaxy morphological classification is still mainly done visually by dedicated…
Classification will be an important first step for upcoming surveys that will detect billions of new sources such as LSST and Euclid, as well as DESI, 4MOST and MOONS. The application of traditional methods of model fitting and…
This work proposes a self-supervised learning system for segmenting rigid objects in RGB images. The proposed pipeline is trained on unlabeled RGB-D videos of static objects, which can be captured with a camera carried by a mobile robot. A…
Self-supervised learning (SSL) methods targeting scene images have seen a rapid growth recently, and they mostly rely on either a dedicated dense matching mechanism or a costly unsupervised object discovery module. This paper shows that…
In this paper we present a new statistic for quantifying galaxy morphology based on measurements of the Gini coefficient of galaxy light distributions. This statistic is easy to measure and is commonly used in econometrics to measure how…
Image clustering is a very useful technique that is widely applied to various areas, including remote sensing. Recently, visual representations by self-supervised learning have greatly improved the performance of image clustering. To…
Depth estimation from light field (LF) images is a fundamental step for numerous applications. Recently, learning-based methods have achieved higher accuracy and efficiency than the traditional methods. However, it is costly to obtain…
Context. Existing samples of strong lenses have been assembled by giving priority to sample size, at the cost of having a complex selection function. With the advent of the next generation of wide-field photometric surveys, however, it…
Gravitational lensing magnification modifies the observed spatial distribution of galaxies and can severely bias cosmological probes of large-scale structure if not accurately modelled. Standard approaches to modelling this magnification…
Estimating perceptual attributes of materials directly from images is a challenging task due to their complex, not fully-understood interactions with external factors, such as geometry and lighting. Supervised deep learning models have…
Cluster catalogs selected by optical properties are subject to selection biases, primarily arising from unresolved systems along the line of sight. These biases affect key observables for cluster cosmology, such as the lensing signal and…