arXiv research

This research uses Siamese networks to identify partial mouse brain images from the Allen atlas.

Paper explores VRM for PSMLC with partially labeled medical images.

Topic models (e.g., pLSA, LDA, SLDA) have been widely used for segmenting imagery. These models are confined to crisp segmentation. Yet, there are many images in which some regions cannot be assigned a crisp label (e.g., transition regions between a foggy sky and the ground or between sand and water at a beach). In the…

EnSF uses image inpainting to handle partial observations in data assimilation.

Neural DEs improve single image super-resolution.

Let $π:\mathcal{X}\to M$ be a holomorphic fibration with compact fibers and $L$ a relatively ample line bundle over $\mathcal{X}$. We obtain the asymptotic of the curvature of $L^2$-metric and Qullien metric on the direct image bundle $π_*(L^k\otimes K_{\mathcal{X}/M})$ up to the lower order terms than $k^{n-1}$ for la…

PFDL improves deep learning models' OOD generalization by decorrelating feature embeddings.

Paper proposes efficient method for evaluating Bayesian models in imaging.

Topic models (e.g., pLSA, LDA, sLDA) have been widely used for segmenting imagery. However, these models are confined to crisp segmentation, forcing a visual word (i.e., an image patch) to belong to one and only one topic. Yet, there are many images in which some regions cannot be assigned a crisp categorical label (e.…

In this work, we propose a simple yet effective solution to the problem of connectome inference in calcium imaging data. The proposed algorithm consists of two steps. First, processing the raw signals to detect neural peak activities. Second, inferring the degree of association between neurons from partial correlation …

Compressed sensing is a powerful tool in applications such as magnetic resonance imaging (MRI). It enables accurate recovery of images from highly undersampled measurements by exploiting the sparsity of the images or image patches in a transform domain or dictionary. In this work, we focus on blind compressed sensing (…

Computer-aided diagnosis system for diffuse lung diseases (DLDs) is necessary for the objective assessment of the lung diseases. In this paper, we develop semantic segmentation model for 5 kinds of DLDs. DLDs considered in this work are consolidation, ground glass opacity, honeycombing, emphysema, and normal. Convoluti…

Deep neural networks trained to inpaint partially occluded images show a deep understanding of image composition and have even been shown to remove objects from images convincingly. In this work, we investigate how this implicit knowledge of image composition can be leveraged for fully self-supervised instance separati…

Defense against small image patches using occlusions.

Natural signals and images are well-known to be approximately sparse in transform domains such as Wavelets and DCT. This property has been heavily exploited in various applications in image processing and medical imaging. Compressed sensing exploits the sparsity of images or image patches in a transform domain or synth…

Partial differential equations (PDEs) are indispensable for modeling many physical phenomena and also commonly used for solving image processing tasks. In the latter area, PDE-based approaches interpret image data as discretizations of multivariate functions and the output of image processing algorithms as solutions to…

We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment. The objective is to classify an image over a finite time horizon. We propose a network architecture on how agents should form a local belief, take local actions, an…

Traditional classifiers can generate high-quality images comparable to generative models.

In Ahlfors' covering surface theory, it is well known that there exists a positive constant $h$ such that for any nonconstant holomorphic mapping $f:$ if $f(Δ)\cap \{0,1,\infty \}=\emptyset ,$ then% A(f,Δ)\leq hL(f,\partial Δ),% where $Δ$ is the disk $|z|<1$ in $\mathbb{C},$ $S$ is the unit Riemann sphere,…

Research on unique continuation principles in medical and seismic imaging.

A method for self-supervised representation learning in partially observable environments.

Framework learns image dynamics between time steps using latent variables.

Paper proves direct image sheaf positivity for certain Kähler fibrations.

We consider the relative canonical line bundle $K_{\mathcal{X}/\mathcal{T}}$ and a relatively ample line bundle $(L, e^{-φ})$ over the total space $\mathcal{X}\to \mathcal{T}$ of fibration over the Teichmüller space by Riemann surfaces. We consider the case when the induced metric $\sqrt{-1}\partial\bar{\partial}φ|_{\…

In reinforcement learning, we can learn a model of future observations and rewards, and use it to plan the agent's next actions. However, jointly modeling future observations can be computationally expensive or even intractable if the observations are high-dimensional (e.g. images). For this reason, previous works have…

We show that the notion of $3$-hyperconvexity on oriented flag manifolds defines a partial cyclic order. Using the notion of interval given by this partial cyclic order, we construct Schottky groups and show that they correspond to images of positive representations in the sense of Fock and Goncharov. We construct poly…

We propose a solution to the image deconvolution problem where the convolution kernel or point spread function (PSF) is assumed to be only partially known. Small perturbations generated from the model are exploited to produce a few principal components explaining the PSF uncertainty in a high dimensional space. Unlike …

A novel capsule network model improves surrogate modeling and uncertainty quantification from sparse data.

Study character varieties of tangles to map immersed curves in the pillowcase.

New method denoises and fills in missing image data without clean training data.

Study controllability of diffeomorphisms of simple polytopes.

Any knot group is the image of the group of a prime knot by a homomorphism that preserves peripheral structure. In fact, there are infinitely many such prime knots. A related partial order on knots is defined, and its properties are discussed.

Improved person detection in occluded conditions with AOS images.

DiffATD efficiently discovers targets in partially observable environments using diffusion dynamics.

New methods for graph completion improve image annotation and neuroimaging.

Multi-echo magnetic resonance (MR) images are acquired by changing the echo times (for T2 weighted) or relaxation times (for T1 weighted) of scans. The resulting (multi-echo) images are usually used for quantitative MR imaging. Acquiring MR images is a slow process and acquiring multi scans of the same cross section fo…

We present a variational Bayesian method of joint image reconstruction and point spread function (PSF) estimation when the PSF of the imaging device is only partially known. To solve this semi-blind deconvolution problem, prior distributions are specified for the PSF and the 3D image. Joint image reconstruction and PSF…

Improved persistence spheres map measures to functions, stable under partial transport.

We prove that every function $f:\mathbb{R}^n\to \mathbb{R}$ satisfies that the image of the set of critical points at which the function $f$ has Taylor expansions of order $n-1$ and non-empty subdifferentials of order $n$ is a Lebesgue-null set. As a by-product of our proof, for the proximal subdifferential $\partial_{…

In this paper, we confront the problem of deep learning's big labeled data requirements, offer a rule based strategy for extreme augmentation of small data sets and apply that strategy with the image to image translation model by Isola et al. (2016) to automate cel style cartoon coloring with very limited training data…

R-PLS improves analysis of brain functional connectivity matrices.

A method to prevent image representation collapse through data-dependent augmentation.

Many real world network problems often concern multivariate nodal attributes such as image, textual, and multi-view feature vectors on nodes, rather than simple univariate nodal attributes. The existing graph estimation methods built on Gaussian graphical models and covariance selection algorithms can not handle such d…

Expands weak supervision by allowing partial labels from multiple noisy sources.

Proves curvature positivity of invariant direct images in complex geometry.

Paper offers robust recovery for 1-bit sensing with partial Gaussian circulant matrices.

Generative models solve medical imaging inverse problems without needing paired data.

New method for partial matching of shapes with Varifolds.