Related papers: $Lux$: A generative, multi-output, latent-variable…

Existing state-of-the-art 3D point clouds understanding methods only perform well in a fully supervised manner. To the best of our knowledge, there exists no unified framework which simultaneously solves the downstream high-level…

Training generative models that capture rich semantics of the data and interpreting the latent representations encoded by such models are very important problems in un-/self-supervised learning. In this work, we provide a simple algorithm…

Current deep learning paradigms largely benefit from the tremendous amount of annotated data. However, the quality of the annotations often varies among labelers. Multi-observer studies have been conducted to study these annotation…

Synthetic spectra are needed to determine fundamental stellar and wind parameters of all types of stars. They are also used for the construction of theoretical spectral libraries helpful for stellar population synthesis. Therefore, a…

Learning identifiable representations and models from low-level observations is helpful for an intelligent spacecraft to complete downstream tasks reliably. For temporal observations, to ensure that the data generating process is provably…

Generating high-quality labeled image datasets is crucial for training accurate and robust machine learning models in the field of computer vision. However, the process of manually labeling real images is often time-consuming and costly. To…

We present a novel approach to deriving stellar labels for stars observed in MUSE fields making use of data-driven machine learning methods. Taking advantage of the comparable spectral properties (resolution, wavelength coverage) of the…

The drastic increase of data quantity often brings the severe decrease of data quality, such as incorrect label annotations, which poses a great challenge for robustly training Deep Neural Networks (DNNs). Existing learning \mbox{methods}…

Automatic classification methods applied to sky surveys have revolutionized the astronomical target selection process. Most surveys generate a vast amount of time series, or \quotes{lightcurves}, that represent the brightness variability of…

Land Use Land Cover (LULC) mapping is a vital tool for urban and resource planning, playing a key role in the development of innovative and sustainable cities. This study introduces a semi-supervised segmentation model for LULC prediction…

Suppose we observe samples of a subset of a collection of random variables. No additional information is provided about the number of latent variables, nor of the relationship between the latent and observed variables. Is it possible to…

The prevalence of noisy-label samples poses a significant challenge in deep learning, inducing overfitting effects. This has, therefore, motivated the emergence of learning with noisy-label (LNL) techniques that focus on separating noisy-…

Machine learning (ML) models are only as good as the data they are trained on. But recent studies have found datasets widely used to train and evaluate ML models, e.g. ImageNet, to have pervasive labeling errors. Erroneous labels on the…

Learning with noisy labels (LNL) aims at designing strategies to improve model performance and generalization by mitigating the effects of model overfitting to noisy labels. The key success of LNL lies in identifying as many clean samples…

Modern generative models are roughly divided into two main categories: (1) models that can produce high-quality random samples, but cannot estimate the exact density of new data points and (2) those that provide exact density estimation, at…

Learning with noisy labels is a vital topic for practical deep learning as models should be robust to noisy open-world datasets in the wild. The state-of-the-art noisy label learning approach JoCoR fails when faced with a large ratio of…

Long-Tailed distributions are pervasive in remote sensing due to the inherently imbalanced occurrence of grounded objects. However, a critical challenge remains largely overlooked, i.e., disentangling hard tail data samples from noisy…

A simple, fully connected neural network with a single hidden layer is used to estimate stellar masses for star-forming galaxies. The model is trained on broad-band photometry - from far-ultraviolet to mid-infrared wavelengths - generated…

We present Learning to Explain (LTX), a model-agnostic framework designed for providing post-hoc explanations for vision models. The LTX framework introduces an "explainer" model that generates explanation maps, highlighting the crucial…

This work investigates whether large language models (LLMs) offer advantages over traditional neural networks for astronomical data processing, in regimes with non-Gaussian, non-stationary noise and limited labeled samples. Gravitational…