NeLLoC improves image compression with parallel decoding.
problem Image compression with OOD generalization.
method Local autoregressive model with parallel decoding.
result Significant gains in compression runtime.
On-device research index
arXiv research
A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
168,742 papers · 148 categories
Trend · papers per month
48 results for “Parallel Imaging”
A parallel algorithm learns efficient Kronecker product dictionaries.
problem Sparse representation of 2D signals like images and hyperspectral data.
method Highly parallelizable algorithm for learning separable dictionaries.
result Competitive sparse representations at lower computational cost.
-net: Ensembled Iterative Deep Neural Networks for Accelerated Parallel MR Image Reconstructioneess.IV
Ensembled neural networks improve MRI image quality.
problem Accelerated parallel MR imaging with high SSIM scores.
method Ensembled -net combining parallel coil and sensitivity networks, trained with supervised and semi-supervised methods.
result Ensembling models achieves visually sharp and textured images with robust SSIM scores.
This study presents a new lossy image compression method that utilizes the multi-scale features of natural images. Our model consists of two networks: multi-scale lossy autoencoder and parallel multi-scale lossless coder. The multi-scale lossy autoencoder extracts the multi-scale image features to quantized variables a…
It Takes Two to Tango: Two Parallel Samplers Improve Quality in Diffusion Models for Limited Stepscs.CV
Two parallel samplers enhance image quality in limited denoising steps.
problem Limited denoising steps in diffusion models reduce image quality.
method Two parallel samplers denoise at successive times, integrating their information.
result Two parallel samplers improve image quality compared to a single sampler.
Quantum computers can speed up machine learning optimization problems.
problem Long computation times and high resource requirements for classical optimization algorithms in machine learning.
method Developed a mathematical model to leverage quantum parallelism for machine learning.
result Quantum machine learning applied to a 3D time-varying image demonstrated significant speedup.
New method solves blind inverse problems by optimizing both operator and image parameters.
problem Solving blind inverse problems with known forward operator.
method Parallel reverse diffusion guided by gradients from intermediate stages.
result State-of-the-art performance on blind deblurring and imaging through turbulence.
Real-time Ionospheric Imaging of S4 Scintillation from Limited Data with Parallel Kalman Filters and Smoothnessphysics.ao-ph
Real-time ionospheric images created from limited data using parallel Kalman filters.
problem Monitoring ionospheric irregularities using limited spatio-temporal observations.
method Bayesian framework with parallel Kalman filters and connectivity information.
result Real-time ionospheric images with high spatio-temporal resolution can be produced.
New algorithm speeds up diffusion model sampling 4-14 times.
problem Time-consuming sampling from diffusion models.
method Parallelizing autoregressive process through fixed-point iteration.
result ParaTAA reduces inference steps by 4-14 times.
SHVC improves image compression with fewer parameters.
problem Challenges in VAE compression, especially with bits-back coding.
method Introduces autoregressive sub-pixel convolution and autoregressive initial bits.
result Achieves state-of-the-art compression performance with fewer model parameters.
This paper proposes a multi-channel image reconstruction method, named DeepcomplexMRI, to accelerate parallel MR imaging with residual complex convolutional neural network. Different from most existing works which rely on the utilization of the coil sensitivities or prior information of predefined transforms, Deepcompl…
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…
Although voice conversion (VC) algorithms have achieved remarkable success along with the development of machine learning, superior performance is still difficult to achieve when using nonparallel data. In this paper, we propose using a cycle-consistent adversarial network (CycleGAN) for nonparallel data-based VC train…
We consider a general theory of curvatures of discrete surfaces equipped with edgewise parallel Gauss images, and where mean and Gaussian curvatures of faces are derived from the faces' areas and mixed areas. Remarkably these notions are capable of unifying notable previously defined classes of surfaces, such as discre…
We describe a simple, low-level approach for embedding probabilistic programming in a deep learning ecosystem. In particular, we distill probabilistic programming down to a single abstraction---the random variable. Our lightweight implementation in TensorFlow enables numerous applications: a model-parallel variational …
Convolutional neural networks (CNNs) attained a good performance in hyperspectral sensing image (HSI) classification, but CNNs consider spectra as orderless vectors. Therefore, considering the spectra as sequences, recurrent neural networks (RNNs) have been applied in HSI classification, for RNNs is skilled at dealing …
Deep-SLR reduces SLR complexity with CNN, enabling efficient parallel MRI.
problem High computational complexity in SLR matrix completion.
method Convolutional Neural Network (CNN) trained to estimate annihilation relations from imperfect k-space measurements.
result Significant reduction in runtime by three orders of magnitude compared to SLR schemes.
This paper describes neural-fortran, a parallel Fortran framework for neural networks and deep learning. It features a simple interface to construct feed-forward neural networks of arbitrary structure and size, several activation functions, and stochastic gradient descent as the default optimization algorithm. Neural-f…
Accelerated magnetic resonance (MR) scan acquisition with compressed sensing (CS) and parallel imaging is a powerful method to reduce MR imaging scan time. However, many reconstruction algorithms have high computational costs. To address this, we investigate deep residual learning networks to remove aliasing artifacts …
Geometric quantization often produces not one Hilbert space to represent the quantum states of a classical system but a whole family of Hilbert spaces, and the question arises if the spaces are canonically isomorphic. [ADW] and [Hi] suggest to view as fibers of a Hilbert bundle , introduce a connec…
In real world industrial applications of topic modeling, the ability to capture gigantic conceptual space by learning an ultra-high dimensional topical representation, i.e., the so-called "big model", is becoming the next desideratum after enthusiasms on "big data", especially for fine-grained downstream tasks such as …
A fast deep learning method for parallel MRI without calibration.
problem Calibration issues in parallel MRI reconstruction.
method Model-based deep learning, self-learning non-linear annihilation filters, Fourier domain pre-learning.
result Significantly faster than SLR methods (3 orders of magnitude), improved performance with spatial domain prior.
Faster Training of Diffusion Models and Improved Density Estimation via Parallel Score Matchingcs.LG
Parallel score matching accelerates DPM training and improves density estimation.
problem Extended training periods and limited modeling flexibility in DPMs.
method Partitioning the learning task into independent time sub-intervals and modeling the score at each time point separately.
result Significant acceleration of training process and improved density estimation performance.
On weakly reflective submanifolds in compact isotropy irreducible Riemannian homogeneous spacesmath.DG
Study extends reflective submanifold theory to compact homogeneous spaces.
problem Characterize reflective submanifolds in compact isotropy irreducible spaces.
method Extend previous results to infinite-dimensional Hilbert spaces.
result Inverse image of reflective submanifolds is also reflective.
We propose JECL, a method for clustering image-caption pairs by training parallel encoders with regularized clustering and alignment objectives, simultaneously learning both representations and cluster assignments. These image-caption pairs arise frequently in high-value applications where structured training data is e…
Study adapts AI research methods to analyze image augmentation impacts on neural network operations.
problem Understanding how image augmentation affects neural network performance and sensitivity.
method Adapted treatment-control paradigm, uses variance decomposition, Sobol indices, and Shapley values for sensitivity analysis.
result Visualizes and quantifies sensitivity to different image augmentation parameters.
We examine the relationships between the differential invariants of objects and of their images under a surjective map. We analyze both the case when the underlying transformation group is projectable and hence induces an action on the image, and the case when only a proper subgroup of the entire group acts projectably…
Light pillars over rippled water appear parallel due to projection geometry.
problem Light pillars over rippled water appear parallel.
method Developing a geometric optics model
result The phenomenon is explained using the specular reflection rule, projection geometry, and physics of surface slopes.
We consider learning problems over training sets in which both, the number of training examples and the dimension of the feature vectors, are large. To solve these problems we propose the random parallel stochastic algorithm (RAPSA). We call the algorithm random parallel because it utilizes multiple parallel processors…
Deep autoregressive sequence-to-sequence models have demonstrated impressive performance across a wide variety of tasks in recent years. While common architecture classes such as recurrent, convolutional, and self-attention networks make different trade-offs between the amount of computation needed per layer and the le…
New data-driven Cartan connection tracks complex vascular structures.
problem Tracking complex vascular structures in multi-orientation images.
method Formulated a data-driven Cartan connection on for geodesic tracking.
result Improved geodesic tracking of vascular trees with globally optimal curves.
Localized curvature bounds ensure harmonic maps are constant.
problem Ensuring harmonic maps are constant under localized curvature constraints.
method Localized Bochner-type rigidity theorem for harmonic maps with image-dependent curvature bounds.
result Harmonic maps are constant if minimal Ricci curvature dominates image-dependent curvature bounds.
Data consistency networks for (calibration-less) accelerated parallel MR image reconstructioneess.IV
We present simple reconstruction networks for multi-coil data by extending deep cascade of CNN's and exploiting the data consistency layer. In particular, we propose two variants, where one is inspired by POCSENSE and the other is calibration-less. We show that the proposed approaches are competitive relative to the st…
The paper proves properties of Finsler submanifolds and analytic maps.
problem Analyzing properties of Finsler submanifolds and their analytic maps.
method Proving properties of regular fibers of analytic maps and Finsler submersions.
result Regular fibers of an analytic map are equifocal under certain conditions.
A Bernstein theorem for complete spacelike constant mean curvature hypersurfaces in Minkowski spacemath.DG
We obtain a gradient estimate for the Gauss maps from complete spacelike constant mean curvature hypersurfaces in Minkowski space into the hyperbolic space. As applications, we prove a Bernstein theorem which says that if the image of the Gauss map is bounded from one side, then the spacelike constant mean curvature hy…
Recent progress on automatic generation of image captions has shown that it is possible to describe the most salient information conveyed by images with accurate and meaningful sentences. In this paper, we propose an image caption system that exploits the parallel structures between images and sentences. In our model, …
TQFTs and quantum computingquant-ph
Program connects quantum computing and topological field theories.
problem Connecting quantum computing and topological field theories.
method Formalizes the connection using cobordisms and parallel transport.
result Realizes quantum circuits as cobordisms in a double category.
The Earth Mover's Distance (EMD) is a state-of-the art metric for comparing discrete probability distributions, but its high distinguishability comes at a high cost in computational complexity. Even though linear-complexity approximation algorithms have been proposed to improve its scalability, these algorithms are eit…
Distributed data-parallel algorithms aim to accelerate the training of deep neural networks by parallelizing the computation of large mini-batch gradient updates across multiple nodes. Approaches that synchronize nodes using exact distributed averaging (e.g., via AllReduce) are sensitive to stragglers and communication…
Tensor completion estimates missing components by exploiting the low-rank structure of multi-way data. The recently proposed methods based on tensor train (TT) and tensor ring (TR) show better performance in image recovery than classical ones. Compared with TT and TR, the projected entangled pair state (PEPS), which is…
Paper develops Riemannian geometry for SPSD matrices with DA applications.
problem Riemannian geometry of SPSD matrices for DA.
method Closed-form expressions, approximations of geodesic path, PT, canonical representation.
result Proposes an algorithm for DA with improved performance.
Many powerful machine learning models are based on the composition of multiple processing layers, such as deep nets, which gives rise to nonconvex objective functions. A general, recent approach to optimise such "nested" functions is the method of auxiliary coordinates (MAC). MAC introduces an auxiliary coordinate for …
We characterize the Dirac structures that are parallel with respect to Gualtieri's canonical connection of a generalized Riemannian metric. On the other hand, we discuss Dirac structures that are images of generalized tangent structures. These structures turn out to be Dirac structures that, if seen as Lie algebroids, …
This paper addresses the morphing of manifold-valued images based on the time discrete geodesic paths model of Berkels, Effland and Rumpf 2015. Although for our manifold-valued setting such an interpretation of the energy functional is not available so far, the model is interesting on its own. We prove the existence of…
New solver MPLP++ outperforms existing solvers for dense graph models.
problem Efficiently solving dense, discrete Graphical Models with pairwise potentials.
method Dual Block-Coordinate Ascent with MPLP++ modification.
result MPLP++ significantly outperforms existing solvers, including TRWS.
Deep neural network image classifiers are reported to be susceptible to adversarial evasion attacks, which use carefully crafted images created to mislead a classifier. Recently, various kinds of adversarial attack methods have been proposed, most of which focus on adding small perturbations to input images. Despite th…
LA-VDM accelerates VDM using landmarks to improve data analysis.
problem Efficiently analyzing complex datasets with nonuniform sampling densities.
method Landmark-constrained two-stage normalization to accelerate VDM.
result LA-VDM accurately recovers parallel transport and converges to the connection Laplacian.
New method speeds up diffusion models inference to sub-linear time.
problem Efficient inference of diffusion models for high-dimensional data.
method Parallel sampling with Picard iterations within blocks.
result Achieves sub-linear time complexity of .