Related papers: HyperAid: Denoising in hyperbolic spaces for tree-…

We study finite-sum nonlinear programs with localized variable coupling encoded by a (hyper)graph. We introduce a graph-compliant decomposition framework that brings message passing into continuous optimization in a rigorous, implementable,…

Learning-based image reconstruction models, such as those based on the U-Net, require a large set of labeled images if good generalization is to be guaranteed. In some imaging domains, however, labeled data with pixel- or voxel-level label…

Sparse approximations using highly over-complete dictionaries is a state-of-the-art tool for many imaging applications including denoising, super-resolution, compressive sensing, light-field analysis, and object recognition. Unfortunately,…

We present an unsupervised data-driven approach for non-rigid shape matching. Shape matching identifies correspondences between two shapes and is a fundamental step in many computer vision and graphics applications. Our approach is designed…

Self-supervised denoising has attracted widespread attention due to its ability to train without clean images. However, noise in real-world scenarios is often spatially correlated, which causes many self-supervised algorithms that assume…

A decision tree is one of the most popular approaches in machine learning fields. However, it suffers from the problem of overfitting caused by overly deepened trees. Then, a meta-tree is recently proposed. It solves the problem of…

Deep metric learning algorithms have been utilized to learn discriminative and generalizable models which are effective for classifying unseen classes. In this paper, a novel noise tolerant deep metric learning algorithm is proposed. The…

The increasing deployment of wearable sensors and implantable devices is shifting AI processing demands to the extreme edge, necessitating ultra-low power for continuous operation. Inspired by the brain, emerging memristive devices promise…

LiDAR place recognition approaches based on deep learning suffer from significant performance degradation when there is a shift between the distribution of training and test datasets, often requiring re-training the networks to achieve peak…

Denoisers trained with synthetic data often fail to cope with the diversity of unknown noises, giving way to methods that can adapt to existing noise without knowing its ground truth. Previous image-based method leads to noise overfitting…

For many optimization problems it is possible to define a distance metric between problem variables that correlates with the likelihood and strength of interactions between the variables. For example, one may define a metric so that the…

Deep learning has been widely adopted to tackle various code-based tasks by building deep code models based on a large amount of code snippets. While these deep code models have achieved great success, even state-of-the-art models suffer…

Overfitting is one of the most critical challenges in deep neural networks, and there are various types of regularization methods to improve generalization performance. Injecting noises to hidden units during training, e.g., dropout, is…

A significant research problem of recent interest is the localization of targets like vessels, surgical needles, and tumors in photoacoustic (PA) images. To achieve accurate localization, a high photoacoustic signal-to-noise ratio (SNR) is…

Parameterized algorithms have been subject to extensive research of recent years and allow to solve hard problems by exploiting a parameter of the corresponding problem instances. There, one goal is to devise algorithms, where the runtime…

In the tasks of image aesthetic quality evaluation, it is difficult to reach both the high score area and low score area due to the normal distribution of aesthetic datasets. To reduce the error in labeling and solve the problem of normal…

Several recent works discussed application-driven image restoration neural networks, which are capable of not only removing noise in images but also preserving their semantic-aware details, making them suitable for various high-level…

Learned denoisers play a fundamental role in various signal generation (e.g., diffusion models) and reconstruction (e.g., compressed sensing) architectures, whose success derives from their ability to leverage low-dimensional structure in…

Optimal transport provides a metric which quantifies the dissimilarity between probability measures. For measures supported in discrete metric spaces, finding the optimal transport distance has cubic time complexity in the size of the…

Recently, the task of distantly supervised (DS) ultra-fine entity typing has received significant attention. However, DS data is noisy and often suffers from missing or wrong labeling issues resulting in low precision and low recall. This…