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.

168,932 papers · 148 categories

Trend · papers per month

8.3%16.7%25.0%33.3% · Jan 199319922001200920172026
48 results for image inference

Bayesian variational inference improves medical image segmentation confidence.

problem Improving interpretability and confidence in deep learning models for medical image segmentation.
method Encoder-decoder architecture based on variational inference for segmenting brain tumor images.
result The model segments brain tumors with both aleatoric and epistemic uncertainty.

NIFTy.re accelerates imaging models and expands Gaussian processes and variational inference.

problem Slow performance and limited inference strategies in NIFTy.
method Rewritten NIFTy with new modeling principles, inference strategies, and JAX integration.
result Dramatic acceleration of models and new inference capabilities.

Bayesian method improves star location and flux estimation from coadded images.

problem Statistical analysis of coadded astronomical images is complicated by pixel dependence.
method Bayesian approach that implicitly marginalizes single-exposure pixel intensities.
result Method outperforms single-exposure image training for star parameter estimation.

Improved neural spike inference from calcium imaging data.

problem Neural spike inference from calcium imaging data.
method Importance weighted adversarial variational autoencoders (IWAE) with adversarial training.
result Adversarial IWAE methods outperform VAEs in inferring neural spikes.

Latent feature models are attractive for image modeling, since images generally contain multiple objects. However, many latent feature models ignore that objects can appear at different locations or require pre-segmentation of images. While the transformed Indian buffet process (tIBP) provides a method for modeling tra…

2012-06-27abs ↗pdf ↗

Proposes a model to generate 3D-aware images from 2D images.

problem Generating 3D-aware images from 2D images.
method Likelihood-based top-down model using Neural Radiance Fields and energy-based latent variables.
result Model can infer 3D object structures from 2D images and generate novel views.

Collage-CNN reduces cloud inference latency by 1.47X with 9X reduced latency variation.

problem Reducing latency variance in cloud machine learning inference.
method Proposes a novel Collage-CNN model that combines multiple images for classification, providing redundancy and cost efficiency.
result Significant reduction in 99th percentile tail latency and variation in inference latency.

Image super-resolution (SR) is an underdetermined inverse problem, where a large number of plausible high-resolution images can explain the same downsampled image. Most current single image SR methods use empirical risk minimisation, often with a pixel-wise mean squared error (MSE) loss. However, the outputs from such …

2016-10-14abs ↗pdf ↗

Learn object dynamics from unlabeled images.

problem Unsupervised learning of multiple object dynamics from unlabeled video sequences.
method Probabilistic model generating noisy positions, followed by non-linear rendering. Efficient inference method for querying the model.
result Efficient inference of object dynamics from unlabeled images.

We introduce a novel generative autoencoder network model that learns to encode and reconstruct images with high quality and resolution, and supports smooth random sampling from the latent space of the encoder. Generative adversarial networks (GANs) are known for their ability to simulate random high-quality images, bu…

2018-07-09abs ↗pdf ↗

The deep image prior was recently introduced as a prior for natural images. It represents images as the output of a convolutional network with random inputs. For "inference", gradient descent is performed to adjust network parameters to make the output match observations. This approach yields good performance on a rang…

2019-04-16abs ↗pdf ↗

Stem uses diffusion models to infer gene expression from H&E images.

problem Inference of gene expression from H&E stained images is time-consuming and expensive.
method Conditional diffusion generative model to infer gene expression.
result Stem achieves state-of-the-art performance in spatial gene expression prediction.

Paper tackles Bayesian image restoration in low-photon Poisson imaging problems.

problem Bayesian inference in challenging low-photon Poisson imaging problems.
method Plug-and-play (PnP) Langevin sampling strategies with accelerated methods and mirror sampling.
result Effective PnP Langevin sampling methods for low-photon Poisson imaging problems.

Machine learning methods for computational imaging require uncertainty estimation to be reliable in real settings. While Bayesian models offer a computationally tractable way of recovering uncertainty, they need large data volumes to be trained, which in imaging applications implicates prohibitively expensive collectio…

2019-04-12abs ↗pdf ↗

Bayesian deep learning improves seismic imaging uncertainty.

problem Uncertainty in seismic imaging due to data noise and linearization errors.
method Combines Bayesian inference and deep neural networks to quantify uncertainty in horizon tracking.
result Uncertainty in automatically tracked horizons can be quantified and visualized.

A key goal of computer vision is to recover the underlying 3D structure from 2D observations of the world. In this paper we learn strong deep generative models of 3D structures, and recover these structures from 3D and 2D images via probabilistic inference. We demonstrate high-quality samples and report log-likelihoods…

2016-07-03abs ↗pdf ↗

BLISS detects and separates astronomical sources quickly and accurately.

problem Detecting and separating overlapping astronomical sources in large images.
method Bayesian Light Source Separator (BLISS) using deep generative models and variational inference.
result BLISS can process megapixel images in seconds and produce highly accurate catalogs.

Generative Score Inference improves uncertainty quantification for multimodal data.

problem Accurate uncertainty quantification in multimodal learning tasks.
method Generative Score Inference (GSI) uses synthetic samples to approximate conditional score distributions.
result GSI achieves state-of-the-art performance in hallucination detection and image captioning uncertainty estimation.

A new method learns latent space normalizing flow for approximate inference in generator models.

problem Approximate inference in generator models with complex posterior distributions.
method Jointly learns latent space normalizing flow and generator model using MCMC-based maximum likelihood.
result The short-run Langevin flow approximates the posterior and aligns with the normalizing flow prior.

Scattering representations simplify SBI for images without extra compression.

problem Efficiently performing simulation-based inference on images with limited data.
method Use scattering representations for compression and learning, combined with spatial averaging and expressive density estimators.
result Scattering representations provide more information than traditional methods, without requiring additional simulations.

New method recovers relative rates in spatial compositional data from IMS.

problem Challenges in analyzing spatial data from IMS due to competitive sampling.
method Hierarchical Variational Graph Fused Lasso using heavy-tailed graphical lasso prior and automatic differentiation variational inference.
result Our method outperforms state-of-the-practice point estimate methodologies in IMS and has superior posterior coverage.

End-to-end meta-learned system for image compression.

problem Reducing the gap between training and inference conditions in image compression.
method Model-Agnostic Meta-learning approach for latent tensor overfitting and updating encoder and decoder networks.
result Meta-learned system achieves better compression performance compared to traditional methods.

New method learns fusion rules from few images using granular ball priors.

problem Challenges in supervised learning for image fusion with limited data.
method Introduces incomplete priors and Granular Ball Pixel Computation (GBPC) algorithm.
result Lightweight neural network learns effective fusion rules from few images.

Image classification with deep neural networks is typically restricted to images of small dimensionality such as 224 x 244 in Resnet models [24]. This limitation excludes the 4000 x 3000 dimensional images that are taken by modern smartphone cameras and smart devices. In this work, we aim to mitigate the prohibitive in…

2018-12-08abs ↗pdf ↗

Unified framework DDNs for multi-label classification, improving inference efficiency.

problem Efficient inference for multi-label classification with dependency networks.
method Combining dependency networks and deep learning, proposing novel inference schemes.
result Novel inference schemes outperform basic neural architectures and Markov networks.

The paper tackles video prediction by estimating conditional densities implicitly.

problem Temporal prediction uncertainty and high-dimensional probabilistic inference in natural scenes.
method Score-based conditional density estimation using sequence-to-image networks trained on a resilience-to-noise objective.
result The method handles occlusion boundaries and weights predictive evidence by reliability.