Related papers: VarRCWA: An Adaptive High-Order Rigorous Coupled W…
Medical ultrasound imaging is ubiquitous, but manual analysis struggles to keep pace. Automated segmentation can help but requires large labeled datasets, which are scarce. Semi-supervised learning leveraging both unlabeled and limited…
Methods for supervised principal component analysis (SPCA) aim to incorporate label information into principal component analysis (PCA), so that the extracted features are more useful for a prediction task of interest. Prior work on SPCA…
We propose a computationally efficient and high-performance classification algorithm by incorporating class structural information in analysis dictionary learning. To achieve more consistent classification, we associate a class…
Image-level weakly-supervised semantic segmentation (WSSS) reduces the usually vast data annotation cost by surrogate segmentation masks during training. The typical approach involves training an image classification network using global…
Most of existing detection pipelines treat object proposals independently and predict bounding box locations and classification scores over them separately. However, the important semantic and spatial layout correlations among proposals are…
In recent years, half precision floating-point arithmetic has gained wide support in hardware and software stack thanks to the advance of artificial intelligence and machine learning applications. Operating at half precision can…
Semi-supervised learning addresses the issue of limited annotations in medical images effectively, but its performance is often inadequate for complex backgrounds and challenging tasks. Multi-modal fusion methods can significantly improve…
Recent trends of ab initio studies and progress in methodologies for electronic structure calculations of strongly correlated electron systems are discussed. The interest for developing efficient methods is motivated by recent discoveries…
Although the preservation of shape continuity and physiological anatomy is a natural assumption in the segmentation of medical images, it is often neglected by deep learning methods that mostly aim for the statistical modeling of input data…
Optical approaches for wavefront shaping traditionally rely on phase modulation through holographic techniques. Shaping the phase determines a wave's diffraction and hence its intensity distribution in space. We instead show that shaping…
Analysing two-dimensional shallow water equations with idealised bottom topographies have many applications in the atmospheric and oceanic sciences; however, restrictive flow pattern assumptions have been made to achieve explicit solutions.…
This paper aims at developing new shape functions adapted to smooth vanishing coefficients for scalar wave equation. It proposes the numerical analysis of their interpolation properties. The interpolation is local but high order convergence…
Semantic segmentation is crucial in remote sensing, where high-resolution satellite images are segmented into meaningful regions. Recent advancements in deep learning have significantly improved satellite image segmentation. However, most…
Image-based crack detection algorithms are increasingly in demand in infrastructure monitoring, as early detection of cracks is of paramount importance for timely maintenance planning. While deep learning has significantly advanced crack…
Canonical correlation analysis investigates linear relationships between two sets of variables, but often works poorly on modern data sets due to high-dimensionality and mixed data types such as continuous, binary and zero-inflated. To…
This paper discusses lowest-order nonstandard finite element methods for space discretization and explicit and implicit schemes for time discretization of the biharmonic wave equation with clamped boundary conditions. A modified Ritz…
We consider the problem of establishing dense correspondences within a set of related shapes of strongly varying geometry. For such input, traditional shape matching approaches often produce unsatisfactory results. We propose an ensemble…
We present the efficiency of semi-orthogonal embedding for unsupervised anomaly segmentation. The multi-scale features from pre-trained CNNs are recently used for the localized Mahalanobis distances with significant performance. However,…
When working with large biological data sets, exploratory analysis is an important first step for understanding the latent structure and for generating hypotheses to be tested in subsequent analyses. However, when the number of variables is…
Self-consistent computations of the potential profile in complex semiconductor heterostructures can be successfully applied for comprehensive simulation of the gain and the absorption spectra, for the analysis of the capture, escape,…