Related papers: UMATO: Bridging Local and Global Structures for Re…

As estimators of location parameters, univariate trimmed means are well known for their robustness and efficiency. They can serve as robust alternatives to the sample mean while possessing high efficiencies at normal as well as heavy-tailed…

In autonomous driving, robust place recognition is critical for global localization and loop closure detection. While inter-modality fusion of camera and LiDAR data in multimodal place recognition (MPR) has shown promise in overcoming the…

In recent advancements in medical image analysis, Convolutional Neural Networks (CNN) and Vision Transformers (ViT) have set significant benchmarks. While the former excels in capturing local features through its convolution operations, the…

A fundamental challenge in image editing lies in preserving spatial locality: edits should improve targeted content without inadvertently altering surrounding regions. However, most optimization-based editing approaches treat images as…

Molecular dynamics (MD) simulations present a data-mining challenge, given that they can generate a considerable amount of data but often rely on limited or biased human interpretation to examine their information content. By not asking the…

Deep learning has substantially advanced pansharpening, achieving impressive fusion quality. However, a prevalent limitation is that conventional deep learning models, which typically rely on training datasets, often exhibit suboptimal…

Constructing uncertainty sets as unions of multiple subsets has emerged as an effective approach for creating compact and flexible uncertainty representations in data-driven robust optimization (RO). This paper focuses on two separate…

Unsupervised domain adaptation (UDA) for semantic segmentation is a promising task freeing people from heavy annotation work. However, domain discrepancies in low-level image statistics and high-level contexts compromise the segmentation…

MR imaging is a valuable diagnostic tool allowing to non-invasively visualize patient anatomy and pathology with high soft-tissue contrast. However, MRI acquisition is typically time-consuming, leading to patient discomfort and increased…

We propose a novel distance-based regularization method for deep metric learning called Multi-level Distance Regularization (MDR). MDR explicitly disturbs a learning procedure by regularizing pairwise distances between embedding vectors…

Low-rank gradient-based optimization methods have significantly improved memory efficiency during the training of large language models (LLMs), enabling operations within constrained hardware without sacrificing performance. However, these…

Traditional problems in computational geometry involve aspects that are both discrete and continuous. One such example is nearest-neighbor searching, where the input is discrete, but the result depends on distances, which vary continuously.…

Semantic segmentation of crops and weeds is crucial for site-specific farm management; however, most existing methods depend on labor intensive pixel-level annotations. A further challenge arises when models trained on one field (source…

Data visualization is the process by which data of any size or dimensionality is processed to produce an understandable set of data in a lower dimensionality, allowing it to be manipulated and understood more easily by people. The goal of…

Modern computational science and engineering applications are being improved by the advances in scientific machine learning. Data-driven methods such as Dynamic Mode Decomposition (DMD) can extract coherent structures from spatio-temporal…

The estimation of uncertainty in robotic vision, such as 3D object detection, is an essential component in developing safe autonomous systems aware of their own performance. However, the deployment of current uncertainty estimation methods…

Vision Mamba models have been extensively researched in various fields, which address the limitations of previous models by effectively managing long-range dependencies with a linear-time overhead. Several prospective studies have further…

For the task of metal artifact reduction (MAR), although deep learning (DL)-based methods have achieved promising performances, most of them suffer from two problems: 1) the CT imaging geometry constraint is not fully embedded into the…

Ensemble learning has had many successes in supervised learning, but it has been rare in unsupervised learning and dimensionality reduction. This study explores dimensionality reduction ensembles, using principal component analysis and…

This report concerns the problem of dimensionality reduction through information geometric methods on statistical manifolds. While there has been considerable work recently presented regarding dimensionality reduction for the purposes of…