Research
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.

169,051 papers · 148 categories

Trend · papers per month

8.3%16.7%25.0%33.3% · Jul 199219922001200920182026
48 results for image observations

A new method estimates target images directly from noisy observations in cryo-EM.

problem Estimating target images from noisy, rotated observations in cryo-EM.
method Estimates rotation-invariant features and then images from these features.
result Effectiveness demonstrated on synthetic cryo-EM datasets.

Adapts deep learning models trained on simulated images for use with real images.

problem Difficulty in training deep neural networks on large amounts of experimental data.
method Adversarial domain adaptation method to mitigate domain shift between simulated and experimental image data.
result Adversarial domain adaptation successfully mitigates domain shift and improves numerical observer performance.

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

problem Data assimilation challenges with partial observations.
method EnSF integrates image inpainting with diffusion models to predict unobserved states.
result EnSF successfully tracks SQG dynamics with partial observations.

SOLAR learns efficient representations for RL in complex image domains.

problem Efficient model-based reinforcement learning in domains with complex observations like images.
method Optimizes structured representations for inferring simple dynamics and cost models from data.
result Substantially better final performance than other model-based RL methods, more efficient than model-free RL.

A geometric account explains why 'The Dress' is ambiguous, predicting observable signatures in image processing.

problem Understanding and predicting ambiguity in image processing, particularly in intrinsic image decomposition.
method Geometric analysis of intrinsic image decomposition, focusing on the discontinuous switch in prior-mode sections.
result Predicted signatures in albedo Jacobian and Fernet curvature can be observed in various models and datasets.

Satellite imagery helps adjust for unobserved confounders in observational studies.

problem Adjusting for confounding factors in observational studies with non-tabular data like satellite imagery.
method Formalizing conditions for causal effect identification, estimation, and sensitivity analysis.
result Demonstrated the use of satellite imagery as a proxy for unobserved confounders in anti-poverty aid programs.

New approach predicts under latent shifts using high-dimensional images.

problem Prediction under latent subgroup shifts with high-dimensional observations.
method Recognition-parametrised model (RPM) for identifying causal latent structure.
result Successfully adapts predictions for high-dimensional image data.

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

problem Quantifying how much knowledge from natural images can be transferred to pathology images.
method Proposes a framework to quantify knowledge gain by a particular layer, conducts empirical investigation in pathology image centered transfer learning.
result Early layers of deep models can transfer knowledge to pathology image classification tasks.

Solves high-dimensional observation learning for control models.

problem Learning dynamics from high-dimensional images is challenging.
method Proposes a Beta DVBF approach to handle latent and observable space discrepancies.
result Demonstrates improved model learning from high-dimensional observations.

Generative model for high-dimensional categorical data using Gaussian-Dirichlet fields.

problem Efficiently modeling and predicting high-dimensional categorical data.
method Combines Dirichlet and Gaussian processes for spatio-temporal modeling.
result Model accurately approximates categorical data in unobserved locations.

This paper establishes the existence of observable footprints that reveal the "causal dispositions" of the object categories appearing in collections of images. We achieve this goal in two steps. First, we take a learning approach to observational causal discovery, and build a classifier that achieves state-of-the-art …

2016-05-26abs ↗pdf ↗

DEMUD-VIS detects novel image content and explains it visually.

problem Detecting and explaining novel image content in large datasets.
method Uses CNN for feature extraction, reconstruction error for novelty detection, and up-convolutional networks for image reconstruction.
result Demonstrates visual explanations of novel image content on diverse datasets.

We develop a method for user-controllable semantic image inpainting: Given an arbitrary set of observed pixels, the unobserved pixels can be imputed in a user-controllable range of possibilities, each of which is semantically coherent and locally consistent with the observed pixels. We achieve this using a deep generat…

2018-06-15abs ↗pdf ↗

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

problem Reconstructing medical images from partial measurements.
method Score-based generative models trained on medical images, then sampling to reconstruct images consistent with measurements and physical model.
result Comparable or better performance in CT and MRI tasks, with improved generalization to unknown measurement processes.

Improved image restoration using frequency-guided sampling.

problem Restoring high-quality images from degraded observations with known degradation processes.
method Proposed a frequency-guided sampling approach for diffusion-based image restoration, incorporating a time-varying low-pass filter.
result Significantly improved performance on challenging image restoration tasks, including motion deblurring and image dehazing.

Paper explores supervised learning methods to approximate ideal observer for joint signal detection and localization.

problem Optimizing medical imaging systems by assessing their performance using the Ideal Observer model.
method Uses supervised learning methods, specifically convolutional neural networks, to approximate the Ideal Observer for joint signal detection and localization tasks.
result Supervised learning-based methods can approximate the Ideal Observer for joint signal detection and localization tasks, as shown by comparisons to MCMC and analytical methods.

ContraBAR uses contrastive learning to learn Bayes-optimal policies in RL.

problem Learning optimal policies for unknown tasks sampled from a known distribution.
method Proposes ContraBAR, a meta RL algorithm using contrastive predictive coding (CPC) for belief inference.
result ContraBAR achieves comparable performance to state-of-the-art methods and is computationally efficient.

Mobile agents classify images via reinforcement learning and consensus.

problem Image classification using multiple mobile agents.
method Proposed network architecture for local belief formation and feature extraction. Decentralized consensus protocol using reinforcement learning.
result Effectiveness of the proposed framework demonstrated on MNIST dataset.

Improves model accuracy in medical imaging with small datasets using transfer learning.

problem Challenges in training neural networks on small medical imaging datasets.
method Comparison of current techniques, proposing one cycle training, discriminative learning rates, gradual freezing, and parameter modification.
result Transfer learning is crucial for small datasets, especially when images from the same part of the body are available.

Develops a new method to create object models from medical images.

problem Variability in anatomical structures and textures limits observer performance.
method Progressive Growing AmbientGAN (ProAmGAN) for creating stochastic object models from medical imaging measurements.
result Demonstrates the effectiveness of ProAmGAN in creating realistic object models.

Automated detection of new, interesting, unusual, or anomalous images within large data sets has great value for applications from surveillance (e.g., airport security) to science (observations that don't fit a given theory can lead to new discoveries). Many image data analysis systems are turning to convolutional neur…

2018-06-21abs ↗pdf ↗

When training a deep neural network for image classification, one can broadly distinguish between two types of latent features of images that will drive the classification. We can divide latent features into (i) "core" or "conditionally invariant" features XcoreX^\text{core} whose distribution XcoreYX^\text{core}\vert Y, cond…

2017-10-31abs ↗pdf ↗

Paper proposes a method to estimate intra-observer variability in echocardiography quality assessment.

problem Intra-observer variability in echocardiography quality assessment impacts deep neural network reliability.
method Modeling intra-observer variability as aleatoric uncertainty in a regression problem.
result The proposed method reduces error from 0.11 to 0.09, improving test accuracy by 5.7%.

This study uses CNN-IOs to estimate MRI image reconstruction performance bounds.

problem Estimating task-based performance limits for MRI image reconstruction methods.
method Utilized stylized multi-coil SENSE MRI systems and deep-generated stochastic models to estimate IO performance.
result Estimation of IO performance provides guidance for designing under-sampled MRI systems.

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.

In image deconvolution problems, the diagonalization of the underlying operators by means of the FFT usually yields very large speedups. When there are incomplete observations (e.g., in the case of unknown boundaries), standard deconvolution techniques normally involve non-diagonalizable operators, resulting in rather …

2016-02-03abs ↗pdf ↗

SLAC learns latent representations for image-based RL tasks.

problem Challenges in learning policies from high-dimensional image observations.
method SLAC separates representation learning and task learning, using a latent variable model.
result SLAC outperforms model-free and model-based methods in image-based control tasks.

We apply basic statistical reasoning to signal reconstruction by machine learning -- learning to map corrupted observations to clean signals -- with a simple and powerful conclusion: it is possible to learn to restore images by only looking at corrupted examples, at performance at and sometimes exceeding training using…

2018-03-12abs ↗pdf ↗

DI-sNMF uses data imputation to separate circumstellar signals in high contrast imaging.

problem Separating circumstellar signals from non-circumstellar signals in high contrast imaging.
method DI-sNMF converts the signal separation problem into a missing data problem, using non-negative matrix factorization to attribute PSF signals to regions flagged as missing data.
result DI-sNMF can precisely measure circumstellar objects without altering them, as shown in simulations and real GPI observations.

VARENN visualizes climate data in 2D images for analysis.

problem Lack of integrated spatiotemporal data in climate models.
method VARENN uses convolutional neural networks to summarize monthly climate data into 2D color images.
result VARENN models accurately classify temperature and precipitation changes.

This research uses machine learning to approximate ideal and hotelling observer performance for binary signal detection.

problem Approximating the Ideal and Hotelling Observers for binary signal detection tasks.
method Supervised learning methods, including CNNs and SLNNs, are employed to approximate the IO and HO test statistics.
result The proposed supervised learning methods provide accurate approximations of the IO and HO test statistics.

New method learns useful disentangled representations from weakly labeled data.

problem Learning useful representations from weakly labeled data.
method Model pairs of non-i.i.d. images, learn disentangled representations without requiring annotation.
result Learn disentangled representations reliably from pairs of images without requiring group, individual factor, or number of changed factors annotation.