Related papers: Image patch analysis and clustering of sunspots: a…
Many vision-related tasks benefit from reasoning over multiple modalities to leverage complementary views of data in an attempt to learn robust embedding spaces. Most deep learning-based methods rely on a late fusion technique whereby…
We have developed a method that maps large astronomical images onto a two-dimensional map and clusters them. A combination of various state-of-the-art machine learning (ML) algorithms is used to develop a fully unsupervised image quality…
Subjective visual interpretation is a challenging yet important topic in computer vision. Many approaches reduce this problem to the prediction of adjective- or attribute-labels from images. However, most of these do not take attribute…
Several papers provide evidences that the most probable sites of flare onset are the regions of high horizontal magnetic field gradients in solar active regions. Besides the localization of flare producing areas the present work intends to…
We use recently digitized sunspot drawings from Mount Wilson Observatory to investigate the latitudinal dependence of tilt angles of active regions and its change with solar cycle. The drawings cover the period from 1917 to present and…
Weakly supervised text-to-person image matching, as a crucial approach to reducing models' reliance on large-scale manually labeled samples, holds significant research value. However, existing methods struggle to predict complex one-to-many…
The analyses of sunspot observations revealed a fundamental magnetic property of the umbral boundary, the invariance of the vertical component of the magnetic field. We aim to analyse the magnetic properties of the umbra-penumbra boundary…
Multi-view subspace clustering aims to divide a set of multisource data into several groups according to their underlying subspace structure. Although the spectral clustering based methods achieve promotion in multi-view clustering, their…
A new approach to the study of the large-scale stellar cluster distribution in the Galaxy based on two-point correlation techniques is presented. The basic formalism for this method is outlined and its applications are then investigated by…
Image clustering is an important and open-challenging task in computer vision. Although many methods have been proposed to solve the image clustering task, they only explore images and uncover clusters according to the image features, thus…
The aim of the present study is to show the varying asymmetries during the decay of sunspot groups. The source of input data is the SoHO/MDI-Debrecen Database (SDD) sunspot catalog that contains the magnetic polarity data for time interval…
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…
We present a detailed study of the morphological features of 22 rich galaxy clusters. Our sample is constructed from a cross-correlation of optical (Abell+APM) data with X-ray (0.1 - 2.4) keV ROSAT pointed observations. We systematically…
Clustering in image analysis is a central technique that allows to classify elements of an image. We describe a simple clustering technique that uses the method of similarity matrices. We expand upon recent results in spectral analysis for…
(abridged) We use a theoretical model to predict the clustering properties of galaxy clusters. Our technique accounts for past light-cone effects on the observed clustering and follows the non-linear evolution of the dark matter correlation…
Despite tremendous advancements in Artificial Intelligence, learning from large sets of data in an unsupervised manner remains a significant challenge. Classical clustering algorithms often fail to discover complex dependencies in large…
We propose a self-supervised framework that learns to group visual entities based on their rate of co-occurrence in space and time. To model statistical dependencies between the entities, we set up a simple binary classification problem in…
Cluster interpretation after dimensionality reduction (DR) is a ubiquitous part of exploring multidimensional datasets. DR results are frequently represented by scatterplots, where spatial proximity encodes similarity among data samples. In…
Cluster analysis of very high dimensional data can benefit from the properties of such high dimensionality. Informally expressed, in this work, our focus is on the analogous situation when the dimensionality is moderate to small, relative…
Recent dedicated Hinode polar region campaigns revealed the presence of concentrated kilogauss patches of magnetic field in the polar regions of the Sun which are also shown to be correlated with facular bright points at the photospheric…