Related papers: PhDLspec: physical-prior embedded deep learning me…
Accurate estimation of stellar parameters -- stellar age, lifetime, and evolutionary stage -- remains a fundamental challenge in astrophysics. We introduce a hybrid deep learning architecture combining multimodal spectroscopic and…
High precision differential astrometry assesses the positions, distances, and motions of celestial objects in relation to the stars. The focal plane of such space telescope must be calibrated with a precision down to the level of 1e-5 pixel…
We present a novel technique to overcome the limitations of the applicability of Principal Component Analysis to typical real-life data sets, especially astronomical spectra. Our new approach addresses the issues of outliers, missing…
Diffusion Probabilistic Models (DPMs) have demonstrated significant potential in 3D medical image segmentation tasks. However, their high computational cost and inability to fully capture global 3D contextual information limit their…
A key algorithm for understanding the world is material segmentation, which assigns a label (metal, glass, etc.) to each pixel. We find that a model trained on existing data underperforms in some settings and propose to address this with a…
One of the long-standing problems in materials science is how to predict a material's structure and then its properties given only its composition. Experimental characterization of crystal structures has been widely used for structure…
Real-world large-scale datasets are heteroskedastic and imbalanced -- labels have varying levels of uncertainty and label distributions are long-tailed. Heteroskedasticity and imbalance challenge deep learning algorithms due to the…
Deep models have achieved impressive progress in solving partial differential equations (PDEs). A burgeoning paradigm is learning neural operators to approximate the input-output mappings of PDEs. While previous deep models have explored…
In modern-day astronomy, near-infrared, optical, and ultraviolet spectroscopy are indispensable for studying a wide range of phenomena, from measuring black hole masses to analyzing chemical abundances in stellar atmospheres. However,…
The concept of Label Distribution Learning (LDL) is a technique to stabilize classification and regression problems with ambiguous and/or imbalanced labels. A prototypical use-case of LDL is human age estimation based on profile images.…
The distinction between stars and galaxies is a fundamental problem in the field of celestial classification. This issue has become challenging for these ongoing and upcoming digital surveys, which will produce terabytes and even petabytes…
While deep learning (DL)-based methods have achieved remarkable success in continuous wireless resource allocation, efficient solutions for problems involving discrete variables remain challenging. This is primarily due to the zero-gradient…
Deep learning-based segmentation techniques have shown remarkable performance in brain segmentation, yet their success hinges on the availability of extensive labeled training data. Acquiring such vast datasets, however, poses a significant…
Diffusion MRI (dMRI) is the primary imaging modality used to study brain microstructure in vivo. Reliable and computationally efficient parameter inference for common dMRI biophysical models is a challenging inverse problem, due to factors…
Limited labeled data makes it hard to train models from scratch in medical domain, and an important paradigm is pre-training and then fine-tuning. Large pre-trained models contain rich representations, which can be adapted to downstream…
The article proposes formulating and codifying a set of applied numerical methods, coined as Deep Learning Discrete Calculus (DLDC), that uses the knowledge from discrete numerical methods to interpret the deep learning algorithms through…
Deep learning has achieved significant breakthroughs in medical imaging, but these advancements are often dependent on large, well-annotated datasets. However, obtaining such datasets poses a significant challenge, as it requires…
Higher-order spectra (Brillinger's polyspectra) offer powerful methods for solving critical problems in signal processing and data analysis. Despite their significant potential, their practical use has remained limited due to unresolved…
Accurate multi-slice reconstruction from limited measurement data is crucial to speed up the acquisition process in medical and scientific imaging. However, it remains challenging due to the ill-posed nature of the problem and the high…
In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consists of multiple relevant labels and other noisy labels. Existing PML methods typically design…