Related papers: Breaking Scale Anchoring: Frequency Representation…

Conventional reinforcement learning (RL) algorithms exhibit broad generality in their theoretical formulation and high performance on several challenging domains when combined with powerful function approximation. However, developing RL…

For nonlinear inverse problems that are prevalent in imaging science, symmetries in the forward model are common. When data-driven deep learning approaches are used to solve such problems, these intrinsic symmetries can cause substantial…

A core challenge in scientific machine learning, and scientific computing more generally, is modeling continuous phenomena which (in practice) are represented discretely. Machine-learned operators (MLOs) have been introduced as a means to…

Few-shot Relation Extraction (FSRE) aims to extract relational facts from a sparse set of labeled corpora. Recent studies have shown promising results in FSRE by employing Pre-trained Language Models (PLMs) within the framework of…

Although large scale models achieve significant improvements in performance, the overfitting challenge still frequently undermines their generalization ability. In super resolution tasks on images, diffusion models as representatives of…

A fundamental problem faced by object recognition systems is that objects and their features can appear in different locations, scales and orientations. Current deep learning methods attempt to achieve invariance to local translations via…

Diffusion magnetic resonance imaging (dMRI) often suffers from low spatial and angular resolution due to inherent limitations in imaging hardware and system noise, adversely affecting the accurate estimation of microstructural parameters…

Although deep learning has significantly improved Face Recognition (FR), dramatic performance deterioration may occur when processing Low Resolution (LR) faces. To alleviate this, approaches based on unified feature space are proposed with…

Despite the large research effort devoted to learning dependencies between time series, the state of the art still faces a major limitation: existing methods learn partial correlations but fail to discriminate across distinct frequency…

When a very fast dynamic event is recorded with a low-framerate camera, the resulting video suffers from severe motion blur (due to exposure time) and motion aliasing (due to low sampling rate in time). True Temporal Super-Resolution (TSR)…

The success of deep neural networks greatly relies on the availability of large amounts of high-quality annotated data, which however are difficult or expensive to obtain. The resulting labels may be class imbalanced, noisy or human biased.…

Angle encoding has emerged as a popular feature map for embedding classical data into quantum models, naturally generating truncated Fourier series with universal function approximation capabilities. Despite this expressive capability,…

Super-resolution suffers from an innate ill-posed problem that a single low-resolution (LR) image can be from multiple high-resolution (HR) images. Recent studies on the flow-based algorithm solve this ill-posedness by learning the…

Numerous lines of aim to control $\textit{model disagreement}$ -- the extent to which two machine learning models disagree in their predictions. We adopt a simple and standard notion of model disagreement in real-valued prediction problems,…

Convolution neural networks have achieved remarkable performance in many tasks of computing vision. However, CNN tends to bias to low frequency components. They prioritize capturing low frequency patterns which lead them fail when suffering…

Recent deep-learning based Super-Resolution (SR) methods have achieved remarkable performance on images with known degradation. However, these methods always fail in real-world scene, since the Low-Resolution (LR) images after the ideal…

Time series forecasting is critical in numerous real-world applications, requiring accurate predictions of future values based on observed patterns. While traditional forecasting techniques work well in in-domain scenarios with ample data,…

Deep neural networks have gained tremendous success in a broad range of machine learning tasks due to its remarkable capability to learn semantic-rich features from high-dimensional data. However, they often require large-scale labelled…

In this study, the problem of computing a sparse representation of multi-dimensional visual data is considered. In general, such data e.g., hyperspectral images, color images or video data consists of signals that exhibit strong local…

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior…