arXiv research

GANs improve medical image analysis through de-noising, segmentation, and data synthesis.

New method improves estimation of neural network aleatoric uncertainty.

Beta-SOD detects and corrects noisy object re-identification using cosine similarity and Beta mixtures.

This paper develops optimal transport methods on the roto-translation group SE2.

ECNNs improve stock market predictions by correcting errors from previous steps.

New method recovers clean data from corrupted samples.

Using integration by parts on Gaussian space we construct a Stein Unbiased Risk Estimator (SURE) for the drift of Gaussian processes using their local and occupation times. By almost-sure minimization of the SURE risk of shrinkage estimators we derive an estimation and de-noising procedure for an input signal perturbed…

The paper bounds the mean absolute error in DNN vector-to-vector regression.

In Deep Learning, Stochastic Gradient Descent (SGD) is usually selected as a training method because of its efficiency; however, recently, a problem in SGD gains research interest: sharp minima in Deep Neural Networks (DNNs) have poor generalization; especially, large-batch SGD tends to converge to sharp minima. It bec…

A deep learning model improves seismic noise reduction.

The study examines backward compatibility issues in ML systems, especially with noisy data.

We present a robust generalization of the synthetic control method for comparative case studies. Like the classical method, we present an algorithm to estimate the unobservable counterfactual of a treatment unit. A distinguishing feature of our algorithm is that of de-noising the data matrix via singular value threshol…

Method preserves Hamiltonian structure for unknown systems from noisy data.

ML reduces high-dimensional data to reveal its underlying structure.

Analytic method for Gaussian Process State-Space Models reduces inference time to linear complexity.

High signal to noise ratio (SNR) consistency of model selection criteria in linear regression models has attracted a lot of attention recently. However, most of the existing literature on high SNR consistency deals with model order selection. Further, the limited literature available on the high SNR consistency of subs…

Noise statistics oblivious algorithm improves robust regression with sparse outliers.

New method calibrates complex ODEs from noisy data using neural networks.

A common analytical problem in neuroscience is the interpretation of neural activity with respect to sensory input or behavioral output. This is typically achieved by regressing measured neural activity against known stimuli or behavioral variables to produce a "tuning function" for each neuron. Unfortunately, because …

Paper develops a new weighted low-rank matrix approximation technique.

A guide to using low-pass graph filters for network data.

Research on manifold learning within a density ridge estimation framework has shown great potential in recent work for both estimation and de-noising of manifolds, building on the intuitive and well-defined notion of principal curves and surfaces. However, the problem of unwrapping or unfolding manifolds has received r…

Improved averaging method for noisy observations converges strongly.

Random projection (RP) is a classical technique for reducing storage and computational costs. We analyze RP-based approximations of convex programs, in which the original optimization problem is approximated by the solution of a lower-dimensional problem. Such dimensionality reduction is essential in computation-limite…

Enhances financial data signal-to-noise ratio using auto-encoders and mutual regularization.

Orthogonal matching pursuit (OMP) is a widely used compressive sensing (CS) algorithm for recovering sparse signals in noisy linear regression models. The performance of OMP depends on its stopping criteria (SC). SC for OMP discussed in literature typically assumes knowledge of either the sparsity of the signal to be e…

A new model finds patterns enriched in target datasets.

New GAN design uses conditional independence graphs to improve model-based GANs.

Paper tackles learning mixture of RUMs from partial data.

Paper proposes MTL for weakly labelled SED, improving performance with 2-step attention.

Paper recovers lattice signal partitions efficiently.

The main goal of this study is to extract a set of brain networks in multiple time-resolutions to analyze the connectivity patterns among the anatomic regions for a given cognitive task. We suggest a deep architecture which learns the natural groupings of the connectivity patterns of human brain in multiple time-resolu…

We propose an algorithm to impute and forecast a time series by transforming the observed time series into a matrix, utilizing matrix estimation to recover missing values and de-noise observed entries, and performing linear regression to make predictions. At the core of our analysis is a representation result, which st…

We show that given an estimate $\widehat{A}$ that is close to a general high-rank positive semi-definite (PSD) matrix $A$ in spectral norm (i.e., $\|\widehat{A}-A\|_2 \leq δ$), the simple truncated SVD of $\widehat{A}$ produces a multiplicative approximation of $A$ in Frobenius norm. This observation leads to many inte…

CatSIM measures image similarity robustly to small changes.

Develops statistical guarantees for image-to-image regression models.

AugurOne trains single image generators without GANs using image warps.

Paper analyzes learning from ghost imaging without reconstruction bottleneck.

Total variation denoising improves image quality adaptively.

Improves text-to-image generation with bidirectional capabilities.

Transmission imaging, as an important imaging technique widely used in astronomy, medical diagnosis, and biology science, has been shown in [49] quite different from reflection imaging used in our everyday life. Understanding the structures of images (the prior information) is important for designing, testing, and choo…

A new metric FRD improves comparing medical images.

This study investigates how much knowledge from natural images can be transferred to pathology images.

Generates high-resolution images from low-resolution inputs.

Few-shot unsupervised image-to-image translation model learns from a few examples.

Generates synthetic laparoscopic images for training deep neural networks.

Content based image retrieval, a technique which uses visual contents of image to search images from large scale image databases according to users' interests. This paper provides a comprehensive survey on recent technology used in the area of content based face image retrieval. Nowadays digital devices and photo shari…

Generative Adversarial Networks optimize model parameters for image matching.