Related papers: Learning novel representations of variable sources…
Generative models (GMs) such as Generative Adversary Network (GAN) and Variational Auto-Encoder (VAE) have thrived these years and achieved high quality results in generating new samples. Especially in Computer Vision, GMs have been used in…
Understanding the latent spaces learned by deep learning models is crucial in exploring how they represent and generate complex data. Autoencoders (AEs) have played a key role in the area of representation learning, with numerous…
Modern generative models are usually designed to match target distributions directly in the data space, where the intrinsic dimension of data can be much lower than the ambient dimension. We argue that this discrepancy may contribute to the…
The manifold hypothesis states that high-dimensional data can be modeled as lying on or near a low-dimensional, nonlinear manifold. Variational Autoencoders (VAEs) approximate this manifold by learning mappings from low-dimensional latent…
Recently there has been an increased interest in unsupervised learning of disentangled representations using the Variational Autoencoder (VAE) framework. Most of the existing work has focused largely on modifying the variational cost…
Learning disentangled and interpretable representations is an important step towards accomplishing comprehensive data representations on the manifold. In this paper, we propose a novel representation learning algorithm which combines the…
Making use of strong correlations between closely separated multiple or double sources and photometric and astrometric metadata in Gaia EDR3, we generate a catalog of candidate double and multiply imaged lensed quasars and AGNs, comprising…
With the development of deep learning techniques, the combination of deep learning with image compression has drawn lots of attention. Recently, learned image compression methods had exceeded their classical counterparts in terms of…
In this letter, we have carried out an independent validation of the Gaia EDR3 photometry using about 10,000 Landolt standard stars from Clem & Landolt (2013). Using a machine learning technique, the UBVRI magnitudes are converted into the…
We propose a new method for unsupervised generative continual learning through realignment of Variational Autoencoder's latent space. Deep generative models suffer from catastrophic forgetting in the same way as other neural structures.…
Gaia Data Release 3 (DR3) provides extensive information on the astrophysical properties of stars, such as effective temperature, surface gravity, metallicity, and luminosity, for over 470 million objects. However, as Gaia's stellar…
VAEs (Variational AutoEncoders) have proved to be powerful in the context of density modeling and have been used in a variety of contexts for creative purposes. In many settings, the data we model possesses continuous attributes that we…
The ability to extract generative parameters from high-dimensional fields of data in an unsupervised manner is a highly desirable yet unrealized goal in computational physics. This work explores the use of variational autoencoders (VAEs)…
Purpose: Handling heterogeneous and mixed data types has become increasingly critical with the exponential growth in real-world databases. While deep generative models attempt to merge diverse data views into a common latent space, they…
This thesis is a proof of concept for the potential of Variational Auto-Encoder (VAE) on representation learning of real-world Knowledge Graphs (KG). Inspired by successful approaches to the generation of molecular graphs, we evaluate the…
We develop Riemannian approaches to variational autoencoders (VAEs) for PDE-type ambient data with regularizing geometric latent dynamics, which we refer to as VAE-DLM, or VAEs with dynamical latent manifolds. We redevelop the VAE framework…
The Gaia DR3 Catalogue contains for the first time about eight hundred thousand solutions with either orbital elements or trend parameters for astrometric, spectroscopic and eclipsing binaries, and combinations of them. This paper aims to…
Two-stage object detectors generate object proposals and classify them to detect objects in images. These proposals often do not contain the objects perfectly but overlap with them in many possible ways, exhibiting great variability in the…
The present work aims to build a new statistical distance scale for planetary nebulae (PNe) based on a rigorous calibration sample. The distances of the calibration sample are derived from the trigonometric parallax method using the recent…
The third data release (DR3) of Gaia has provided a five-fold increase in the number of radial velocity measurements of stars, as well as a stark improvement in parallax and proper motion measurements. To help with studies that seek to test…