Related papers: A Generative Model for Disentangling Galaxy Photom…
Segment Anything Models (SAMs), known for their exceptional zero-shot segmentation performance, have garnered significant attention in the research community. Nevertheless, their performance drops significantly on severely degraded,…
This paper shows that masked autoencoders (MAE) are scalable self-supervised learners for computer vision. Our MAE approach is simple: we mask random patches of the input image and reconstruct the missing pixels. It is based on two core…
In this work, we provide an efficient and realistic data-driven approach to simulate astronomical images using deep generative models from machine learning. Our solution is based on a variant of the generative adversarial network (GAN) with…
Images acquired with a telescope are blurred and corrupted by noise. The blurring is usually modeled by a convolution with the Point Spread Function and the noise by Additive Gaussian Noise. Recovering the observed image is an ill-posed…
In order to continuously represent molecules, we propose a generative model in the form of a VAE which is operating on the 2D-graph structure of molecules. A side predictor is employed to prune the latent space and help the decoder in…
Periodic graphs are graphs consisting of repetitive local structures, such as crystal nets and polygon mesh. Their generative modeling has great potential in real-world applications such as material design and graphics synthesis. Classical…
Problems such as predicting a new shading field (Y) for an image (X) are ambiguous: many very distinct solutions are good. Representing this ambiguity requires building a conditional model P(Y|X) of the prediction, conditioned on the image.…
We present a new scheme, $\it{galtag}$, for refining the photometric redshift measurements of faint galaxies by probabilistically tagging them to observed galaxy groups constructed from a brighter, magnitude-limited spectroscopy survey.…
Auto-encoders are perhaps the best-known non-probabilistic methods for representation learning. They are conceptually simple and easy to train. Recent theoretical work has shed light on their ability to capture manifold structure, and drawn…
The future astronomical imaging surveys are set to provide precise constraints on cosmological parameters, such as dark energy. However, production of synthetic data for these surveys, to test and validate analysis methods, suffers from a…
The cosmological redshift of a galaxy's light is inferable from its observable properties in images. Because imaging is much easier to acquire than spectroscopic observations that would allow the identification of distinct line features,…
This study explores the application of Convolutional Autoencoders (CAEs) for analyzing and reconstructing Scanning Tunneling Microscopy (STM) images of various crystalline lattice structures. We developed two distinct CAE architectures to…
Large Language Models (LLMs) encode factual knowledge within hidden parametric spaces that are difficult to inspect or control. While Sparse Autoencoders (SAEs) can decompose hidden activations into more fine-grained, interpretable…
Cellular Automata (CA) theory is a discrete model that represents the state of each of its cells from a finite set of possible values which evolve in time according to a pre-defined set of transition rules. CA have been applied to a number…
We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output of a VAE, which ensures the VAE's output to preserve the…
Explainable Artificial Intelligence (XAI) models have recently attracted a great deal of interest from a variety of application sectors. Despite significant developments in this area, there are still no standardized methods or approaches…
Self-supervised learning guided by masked image modelling, such as Masked AutoEncoder (MAE), has attracted wide attention for pretraining vision transformers in remote sensing. However, MAE tends to excessively focus on pixel details,…
We introduce a new galaxy image decomposition tool, GALPHAT (GALaxy PHotometric ATtributes), to provide full posterior probability distributions and reliable confidence intervals for all model parameters. GALPHAT is designed to yield a high…
Graph autoencoders (AE) and variational autoencoders (VAE) are powerful node embedding methods, but suffer from scalability issues. In this paper, we introduce FastGAE, a general framework to scale graph AE and VAE to large graphs with…
To understand the fundamental parameters of galaxy evolution, we investigated the minimum set of parameters that explain the observed galaxy spectra in the local Universe. We identified four latent variables that efficiently represent the…