GANPOP uses deep learning to estimate optical properties from single images, improving accuracy over existing methods.
problem Estimating optical properties from single wide-field images.
method Conditional generative adversarial networks trained on paired images and optical property maps.
result GANPOP estimates optical properties with 58% higher accuracy than single-snapshot optical property technique in human gastrointestinal specimens.
Study formalizes properties of deep neural networks for image recognition.
problem Understanding why deep neural networks classify images.
method Formalized properties of eight state-of-the-art deep neural networks.
result Deep neural networks can be deceived with a fooling ratio of 88%.
Self-guidance controls image generation by extracting properties from diffusion model representations.
problem Generating images from text descriptions is challenging due to the complexity of visual details.
method Self-guidance uses internal representations of diffusion models to control image generation.
result Properties like object shape, location, and appearance can be extracted and used to steer image generation.
Machine learning and complexity-entropy methods estimate liquid crystal properties from textures.
problem Extracting physical properties from liquid crystal textures.
method Combining permutation entropy, statistical complexity, and machine learning.
result Significant precision in predicting physical properties of liquid crystals.
Total variation denoising improves image quality adaptively.
problem Improving image quality from noisy data.
method Total variation regularization for image denoising.
result Denoised images converge to true images at a parametric rate.
The study examines properties of digital images using various adjacencies.
problem Properties of Cartesian products of digital images.
method Various adjacencies used to study digital images.
result Properties of digital images studied using adjacencies.
New algorithms extract features from light waveforms, improving image quality.
problem Extracting features from digital images efficiently and accurately.
method Dispersive propagation of light followed by phase detection.
result Superior dynamic range and energy efficiency compared to conventional methods.
C2G-Net improves image classification of similar objects like cells.
problem Classifying images with many similar objects efficiently and interpretably.
method Combines image compression and a CNN with reduced parameters.
result C2G-Net achieves similar accuracy to conventional CNNs but with reduced training time and improved interpretability.
Cartesian neural network models learn soft tissue mechanical properties without shape assumptions.
problem Model-based methods limit elastography to imaging linear-elastic parameters.
method Data-driven neural network constitutive models (NNCMs) learn stress-strain relationships from force-displacement data.
result NNCMs can characterize mechanical properties and their spatial distribution without prior shape knowledge.
Examines how irreducibility and rigidity affect digital images.
problem Understanding interactions between irreducibility and rigidity in digital images.
method Analyzes Cartesian products, wedges, and cold and freezing sets.
result Interactions between irreducibility and rigidity in digital images.
Study convexity and AFPP in digital images.
problem Relationship between convexity and AFPP in digital images.
method Examined in Z^2 digital images.
result Relationship between convexity and AFPP in digital images.
We present a new, fully generative model of optical telescope image sets, along with a variational procedure for inference. Each pixel intensity is treated as a Poisson random variable, with a rate parameter dependent on latent properties of stars and galaxies. Key latent properties are themselves random, with scientif…
Enhances image memorability and scaryness using deep learning.
problem Improving subjective visual properties like memorability and scaryness.
method Combines deep style transfer and generative adversarial networks to modify image attributes.
result Demonstrates effectiveness in enhancing image memorability and generating scary pictures.
Bayesian algorithm detects image matches and fraud.
problem Detecting identity matches and fraud in image databases.
method Generative model of image graph trained with matching algorithm.
result Bayesian approach improves detection accuracy.
Digital trees have approximate fixed point property, and conditions for products are explored.
problem Conditions for the approximate fixed point property in digital tree products.
method Analyzes digital trees and their products, explores conditions for the AFPP.
result Conditions are found for the AFPP in digital tree products.
The paper explores how neural networks generalize differently from natural and medical images.
problem Discrepancies in generalization error between natural and medical images.
method Established and empirically validated a generalization scaling law with respect to intrinsic dataset properties.
result Higher intrinsic 'label sharpness' of medical images leads to higher adversarial vulnerability.
Paper proposes a method to extract disentangled features for multi-task learning in medical images.
problem Indiscriminate mixing of image properties leads to poor generalization in deep learning.
method Uses deep neural networks and adversarial regularization to disentangle features.
result Demonstrates improved performance on images with new properties like artifacts.
Deep learning models can predict chemical properties without needing advanced chemistry knowledge.
problem How much chemistry does a deep neural network need to know to make accurate predictions?
method Systematically removing and adding localized domain-specific information to image channels of training data.
result An augmented Chemception (AugChemception) outperforms the original model in predicting toxicity, activity, and solvation free energy.
ADS explains object differences by quantifying and removing underlying properties.
problem Explaining differences between two object images.
method Align-Deform-Subtract (ADS) framework that uses semantic alignments and iterative quantification/removal of differences.
result ADS provides disentangled error measures explaining object differences in terms of underlying properties.
CURL uses neural curves to enhance global image properties.
problem Global image enhancement using neural networks.
method CURL is a multi-colour space neural retouching block trained in HSV, CIELab, and RGB color spaces.
result CURL produces state-of-the-art image quality in RGB-to-RGB and RAW-to-RGB transformations.
Analyzes properties of stiffness tensors for elastic wave imaging.
problem Characterizing stiffness tensor fields for elastic wave imaging.
method Finsler-geometric methods applied to anisotropic stiffness tensor fields.
result Conditions for Finsler-geometric methods to be applicable.
The paper studies properties of image Milnor number and stability of germs.
problem Understanding the stability and properties of isolated instability germs.
method Analyzes three properties of image Milnor number for germs with isolated instability.
result Establishes the conservation of image Milnor number and proves weak Mond's conjecture.
New properties of weighted Hilbert transform derived, useful for imaging applications.
problem Properties of weighted Hilbert transform in L2 spaces.
method Derivation of Plancherel-like equations, coerciveness, iterative sequences.
result Iterative sequences for inversion are applicable to specific cases.
ProAGAN stabilizes GANs for learning SOMs from noisy medical imaging data.
problem Learning stochastic object models from noisy and indirect medical imaging measurements.
method Developed Progressive Growing of AmbientGANs (ProAGAN) to stabilize GANs training.
result Signal detection performance improved using ProAGAN-generated images.
Untrained neural networks can recover natural images from few measurements.
problem Recovering natural images from a small number of measurements.
method Gradient descent on un-trained convolutional neural networks.
result Untrained neural networks can approximate reconstruct signals/images from a near minimal number of random measurements.
New model constructs astronomical catalogs from images efficiently.
problem Building accurate catalogs from large image datasets.
method Generative model with MCMC and VI for inference.
result Variational inference is 1000x faster with similar accuracy.
Study on cold and freezing sets in digital images.
problem Properties of cold sets in digital images.
method Analysis of properties and relationships between cold and freezing sets.
result Examined relationships between cold and freezing sets.
Study shows dataset properties impact adversarial machine learning robustness.
problem Vulnerability of DNNs to adversarial attacks.
method Examined five datasets, analyzed input size and contrast effects.
result Input size and contrast significantly influence adversarial success.
Study MAP estimation for PnP priors with SGD, proving convergence and demonstrating practical applications.
problem Theoretical analysis and practical implementation of PnP priors for Bayesian imaging problems.
method Maximum-a-posteriori estimation with Plug & Play priors and stochastic gradient descent.
result Convergence proof for MAP computation by PnP-SGD under realistic assumptions on the denoiser.
We study the mean curvature flow of complete space-like submanifolds in pseudo-Euclidean space with bounded Gauss image, as well as that of complete submanifolds in Euclidean space with convex Gauss image. By using the confinable property of the Gauss image under the mean curvature flow we prove the long time existence…
A machine learning method predicts rock permeability from 3D images.
problem Efficiently predict permeability of heterogeneous rocks for planetary and robotic applications.
method Machine learning guided 3D properties recognition of rock morphology from 3D micro CT and MRI images.
result The morphology decoder method accurately predicts permeability from 3D images.
Polarimetric images enhance object detection in adverse weather conditions.
problem Object detection in road scenes is challenging in adverse weather conditions.
method Combining polarimetric imaging and deep learning.
result Polarimetry improves object detection by 20% to 50% compared to conventional RGB images.
Improved self-supervised learning for document images.
problem Performance of self-supervised pre-training on document images is poor.
method Proposed context-aware alternatives and a novel multi-modal method.
result Novel method outperforms other self-supervised methods on document image classification.
Two-layer model sparsifies image residuals for CT image reconstruction.
problem Image reconstruction from limited and corrupted data.
method Pre-learning a two-layer sparsifying transform model with block coordinate descent optimization.
result Preliminary experiments show the two-layer model improves CT image reconstruction from low-dose measurements.
SUPER learning combines supervised and unsupervised methods for LDCT image reconstruction.
problem Low-dose CT image reconstruction challenges.
method Combines supervised and unsupervised learning methods.
result SUPER learning dramatically outperforms constituent methods.
DAEs can generate images without additional loss terms, inheriting VAE properties.
problem Difficulty in using VAEs for practical generative modelling.
method Empirical exploration of DAEs for image generation without novel methods.
result DAEs can generate images successfully without additional loss terms.
We consider projective varieties with degenerate Gauss image whose focal hypersurfaces are non-reduced schemes. Examples of this situation are provided by the secant varieties of Severi and Scorza varieties. The Severi varieties are moreover characterized by a uniqueness property.
A new image representation method using hypernetworks.
problem Representing images in a way that allows for continuous manipulation and analysis.
method Constructing a hypernetwork that maps pixel positions to colors, allowing for continuous image manipulation.
result Comparable image super-resolution results to existing methods using a single model.
IAGAN method improves medical image reconstruction by incorporating adaptive GAN priors.
problem Reconstructing high-fidelity medical images from incomplete data.
method Image-adaptive GAN-based reconstruction method (IAGAN).
result IAGAN can recover fine structures relevant for medical diagnosis.
New method proves exact recovery for tensor decomposition under reshuffling.
problem Numerical defects limit practical applications of tensor decomposition.
method Proves exact-recovery property for latent convex tensor decomposition using reshuffling.
result Generalized LCTD achieves exact recovery under reshuffling.
New Fourier metrics equivalent to Wasserstein distances in image processing.
problem Equivalence of Fourier-based and Wasserstein metrics in imaging problems.
method Extensions of Fourier-based metrics to handle different centers of mass and discrete measures, showing equivalence to Wasserstein distances.
result New Fourier metrics are equivalent to Wasserstein distances with explicit constants, improving runtime in image processing.
Study uses deep learning to quickly estimate tissue properties for personalized radio-frequency dosimetry.
problem Time-consuming tissue segmentation limits personalized radio-frequency dosimetry.
method Developed a learning-based approach using Convolutional Neural Networks (CNN) for magnetic resonance images.
result Smooth distribution of dielectric properties improves SAR distribution consistency.
Satellite imagery improves house price prediction models.
problem Improving accuracy of housing price estimation models.
method Transfer learning from ImageNet-pretrained Inception-v3 model to satellite images.
result Achieved a 10% improvement in R-squared score.
Most content-based image retrieval systems consider either one single query, or multiple queries that include the same object or represent the same semantic information. In this paper we consider the content-based image retrieval problem for multiple query images corresponding to different image semantics. We propose a…
New k-means method clusters radar image sequences using SPD matrices.
problem Clustering radar image sequences efficiently.
method Developed k-means on SPD matrices for non-Euclidean data. result Effective clustering of radar image sequences via SPD matrices.
This article is a survey on Lorenz knots. We describe the original construction, prove several classical properties, in particular the fact that the closure of a positive braid is a fibered knot, and describe Ghys'correspondance between modular knots and Lorenz knots. We also prove two new properties, namely that follo…
Paper introduces PSGAN for texture synthesis with manifold properties.
problem Texture synthesis with limited ability to handle diverse data.
method Generative adversarial networks (GAN) with extended noise tensor structure.
result PSGAN can smoothly interpolate and generate novel textures.
The paper analyzes deep neural network classification regions and their decision boundaries.
problem Understanding the geometric properties of deep neural network classifiers.
method Empirical investigation of deep neural networks' classification regions and decision boundaries.
result Deep neural networks learn connected classification regions with flat decision boundaries.