相关论文: Disentangled Representation Learning for Astronomi…
In the era of industrial Galactic astronomy and multi-object spectroscopic stellar surveys, the sample sizes and the number of available stellar chemical abundances have reached dimensions in which it has become difficult to process all the…
In this third paper in a series, we investigate the need of spectra denoising for the derivation of stellar parameters. We have used two distinct datasets for this work. The first one contains spectra in the range of 4450-5400 {\AA} at a…
Disentangled representation learning remains challenging as the underlying factors of variation in the data do not naturally exist. The inherent complexity of real-world data makes it unfeasible to exhaustively enumerate and encapsulate all…
Achieving high accuracy and precision in stellar parameter and chemical composition determinations is challenging in massive star spectroscopy. On one hand, the target selection for an unbiased sample build-up is complicated by several…
The idea behind the \emph{unsupervised} learning of \emph{disentangled} representations is that real-world data is generated by a few explanatory factors of variation which can be recovered by unsupervised learning algorithms. In this…
Face images are subject to many different factors of variation, especially in unconstrained in-the-wild scenarios. For most tasks involving such images, e.g. expression recognition from video streams, having enough labeled data is…
The possibility of identifying co-natal stars that have dispersed into the Galactic disc based on chemistry only is called strong chemical tagging. Its feasibility has been debated for a long time, with the promise of reconstructing the…
Scene text images contain not only style information (font, background) but also content information (character, texture). Different scene text tasks need different information, but previous representation learning methods use tightly…
Materials with bespoke properties have long been identified by computational searches, and their experimental realisation is now coming within reach through autonomous laboratories. Scattering experiments are central to verifying the atomic…
The detection and subsequent characterisation of exoplanets are intimately linked to the characteristics of their host star. Therefore, it is necessary to study the star in detail in order to understand the formation history and…
Stellar abundances for a large number of stars are key information for the study of Galactic formation history. Large spectroscopic surveys such as DESI and LAMOST take median-to-low resolution ($R\lesssim5000$) spectra in the full optical…
Disentangled representation learning offers useful properties such as dimension reduction and interpretability, which are essential to modern deep learning approaches. Although deep learning techniques have been widely applied to…
To study stellar populations, it is common to combine chemical abundances from different spectroscopic surveys/studies where different setups were used. These inhomogeneities can lead us to inaccurate scientific conclusions. In this work,…
Neural operators (NOs) excel at learning mappings between function spaces, serving as efficient forward solution approximators for PDE-governed systems. However, as black-box solvers, they offer limited insight into the underlying physical…
The ability to learn disentangled representations that split underlying sources of variation in high dimensional, unstructured data is important for data efficient and robust use of neural networks. While various approaches aiming towards…
Disentanglement is the task of learning representations that identify and separate factors that explain the variation observed in data. Disentangled representations are useful to increase the generalizability, explainability, and fairness…
We propose a framework to analyze how multivariate representations disentangle ground-truth generative factors. A quantitative analysis of disentanglement has been based on metrics designed to compare how one variable explains each…
We construct an unsupervised learning model that achieves nonlinear disentanglement of underlying factors of variation in naturalistic videos. Previous work suggests that representations can be disentangled if all but a few factors in the…
Recent disentangled representation learning (DRL) methods heavily rely on factor specific strategies-either learning objectives for attributes or model architectures for objects-to embed inductive biases. Such divergent approaches result in…
Sequential scientific data span many resolutions and domains, and unifying them into a common representation is a key step toward developing foundation models for the sciences. Astronomical spectra exemplify this challenge: massive surveys…