相关论文: IsUMap: Manifold Learning and Data Visualization l…

Accelerating magnetic resonance imaging (MRI) remains challenging, particularly under realistic acquisition noise. While diffusion models have recently shown promise for reconstructing undersampled MRI data, many approaches lack an explicit…

Among all data augmentation techniques proposed so far, linear interpolation of training samples, also called Mixup, has found to be effective for a large panel of applications. Along with improved predictive performance, Mixup is also a…

In the last few years, many explanation methods based on the perturbations of input data have been introduced to improve our understanding of decisions made by black-box models. The goal of this work is to introduce a novel perturbation…

Dripping water from a faucet is a typical example exhibiting rich nonlinear phenomena. For such a system, the time stamps at which water drops separate from the faucet can be directly observed in real experiments, and the time series of…

Recent advances in diffusion-based generative modeling have demonstrated significant promise in tackling long-horizon, sparse-reward tasks by leveraging offline datasets. While these approaches have achieved promising results, their…

Deep neural networks excel at learning the training data, but often provide incorrect and confident predictions when evaluated on slightly different test examples. This includes distribution shifts, outliers, and adversarial examples. To…

Multimodal fusion of remote sensing images serves as a core technology for overcoming the limitations of single-source data and improving the accuracy of surface information extraction, which exhibits significant application value in fields…

Tabular data are central to biomedical research, from liquid biopsy and bulk and single-cell transcriptomics to electronic health records and phenotypic profiling. Unlike images or sequences, however, tabular datasets lack intrinsic spatial…

In this paper, we approach the problem of uncertainty quantification in deep learning through a predictive framework, which captures uncertainty in model parameters by specifying our assumptions about the predictive distribution of unseen…

Image reconstruction is an inverse problem that solves for a computational image based on sampled sensor measurement. Sparsely sampled image reconstruction poses addition challenges due to limited measurements. In this work, we propose an…

Recent advancements in multimodal pre-training models have significantly advanced computational pathology. However, current approaches predominantly rely on visual-language models, which may impose limitations from a molecular perspective…

This paper presents a novel visual feature based scene mapping method for underwater vehicle manipulator systems (UVMSs), with specific emphasis on robust mapping in natural seafloor environments. Our method uses GPU accelerated SIFT…

In the field of medical image analysis, image registration is a crucial technique. Despite the numerous registration models that have been proposed, existing methods still fall short in terms of accuracy and interpretability. In this paper,…

In this paper, we present a powerful differentiable surface fitting technique to derive a compact surface representation for a given dense point cloud or mesh, with application in the domains of graphics and CAD/CAM. We have chosen the Loop…

Manifold learning aims to discover and represent low-dimensional structures underlying high-dimensional data while preserving critical topological and geometric properties. Existing methods often fail to capture local details with global…

Current audio-visual representation learning can capture rough object categories (e.g., ``animals'' and ``instruments''), but it lacks the ability to recognize fine-grained details, such as specific categories like ``dogs'' and ``flutes''…

In image set classification, a considerable advance has been made by modeling the original image sets by second order statistics or linear subspace, which typically lie on the Riemannian manifold. Specifically, they are Symmetric Positive…

Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities. Moreover, increasingly heavier models, \textit{e}.\textit{g}., Transformers, have attracted the…

This paper introduces an innovative approach to Medical Vision-Language Pre-training (Med-VLP) area in the specialized context of radiograph representation learning. While conventional methods frequently merge textual annotations into…

Data mixing (e.g., Mixup, Cutmix, ResizeMix) is an essential component for advancing recognition models. In this paper, we focus on studying its effectiveness in the self-supervised setting. By noticing the mixed images that share the same…