Related papers: Multiview Hessian Regularization for Image Annotat…
The success of many machine learning (ML) methods depends crucially on having large amounts of labeled data. However, obtaining enough labeled data can be expensive, time-consuming, and subject to ethical constraints for many applications.…
We propose a new constrained optimization approach to hyperspectral (HS) image restoration. Most existing methods restore a desirable HS image by solving some optimization problem, which consists of a regularization term(s) and a…
The performance of deep learning models in remote sensing (RS) strongly depends on the availability of high-quality labeled data. However, collecting large-scale annotations is costly and time-consuming, while vast amounts of unlabeled…
Few-shot learning (FSL) based on manifold regularization aims to improve the recognition capacity of novel objects with limited training samples by mixing two samples from different categories with a blending factor. However, this mixing…
Current Large Multimodal Models (LMMs) struggle with high-resolution visual inputs during the reasoning process, as the number of image tokens increases quadratically with resolution, introducing substantial redundancy and irrelevant…
Automated segmentation of the fetal head in ultrasound images is critical for prenatal monitoring. However, achieving robust segmentation remains challenging due to the poor quality of ultrasound images and the lack of annotated data.…
Accurate segmentation of blood vessels in brain magnetic resonance angiography (MRA) is essential for successful surgical procedures, such as aneurysm repair or bypass surgery. Currently, annotation is primarily performed through manual…
Methods based on convolutional neural network (CNN) have demonstrated tremendous improvements on single image super-resolution. However, the previous methods mainly restore images from one single area in the low resolution (LR) input, which…
Scenes reconstructed by 3D Gaussian Splatting (3DGS) trained on low-resolution (LR) images are unsuitable for high-resolution (HR) rendering. Consequently, a 3DGS super-resolution (SR) method is needed to bridge LR inputs and HR rendering.…
We present a method for tracking Maximally Stable Homogeneous Regions (MSHR) in images with an arbitrary number of channels. MSHR are conceptionally very similar to Maximally Stable Extremal Regions (MSER) and Maximally Stable Color Regions…
Self-Supervised Learning (SSL) methods harness the concept of semantic invariance by utilizing data augmentation strategies to produce similar representations for different deformations of the same input. Essentially, the model captures the…
Low-rank structures play important role in recent advances of many problems in image science and data science. As a natural extension of low-rank structures for data with nonlinear structures, the concept of the low-dimensional manifold…
Designing learning-based no-reference (NR) video quality assessment (VQA) algorithms for camera-captured videos is cumbersome due to the requirement of a large number of human annotations of quality. In this work, we propose a…
We propose two generic methods for improving semi-supervised learning (SSL). The first integrates weight perturbation (WP) into existing "consistency regularization" (CR) based methods. We implement WP by leveraging variational Bayesian…
The increase in the observed volume in cosmological surveys imposes various challenges on simulation preparations. Firstly, the volume of the simulations required increases proportionally to the observations. However, large-volume…
We establish a family of subspace-based learning method for multi-view learning using the least squares as the fundamental basis. Specifically, we investigate orthonormalized partial least squares (OPLS) and study its important properties…
Scene text image super-resolution (STISR) is an important pre-processing technique for text recognition from low-resolution scene images. Nowadays, various methods have been proposed to extract text-specific information from high-resolution…
While the harmonic function solution performs well in many semi-supervised learning (SSL) tasks, it is known to scale poorly with the number of samples. Recent successful and scalable methods, such as the eigenfunction method focus on…
Hyperspectral image (HSI) with narrow spectral bands can capture rich spectral information, but it sacrifices its spatial resolution in the process. Many machine-learning-based HSI super-resolution (SR) algorithms have been proposed…
Hyperspectral images (HSI) contain a wealth of information over hundreds of contiguous spectral bands, making it possible to classify materials through subtle spectral discrepancies. However, the classification of this rich spectral…