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.

168,695 papers · 148 categories

Trend · papers per month

152305457609 · Jun 202019922001200920172026
48 results for bounded images

We give a combinatorial proof, using the hyperbolicity of the curve graphs, of the bounded geodesic image theorem of Masur and Minsky. Recently it has been shown that curve graphs are uniformly hyperbolic, thus a universal bound can be given for the diameter of the geodesic image. We also generalize the theorem for pro…

2013-01-25abs ↗pdf ↗

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.

Estimates convex hulls of smooth function images with error bounds.

problem Estimating the convex hull of the image of a smooth boundary set.
method Using submersion properties and sampling inputs, derive bounds on Hausdorff distance.
result New tighter and more general error bounds for geometric inference.

Extends L2-norm LDA to 2D inputs using Bhattacharyya bound.

problem L2-norm LDA loses useful image information for 2D inputs.
method 2DBLDA maximizes matrix-based between-class distance and minimizes within-class distance, optimizing Bhattacharyya error bound.
result 2DBLDA improves image recognition and face reconstruction.

Study on holomorphic isometries between complex domains, revealing geometric properties.

problem Characterizing holomorphic isometries between bounded symmetric domains.
method Analyzing holomorphic isometries between complex unit ball and other bounded symmetric domains, using classical results for complex-analytic subvarieties of Stein manifolds.
result Images of holomorphic isometries have specific geometric properties, including intersections with affine-linear subspaces.

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.

New method certifies images against transformations like rotations and translations.

problem Certifying robustness of images against transformations like rotations and translations.
method Randomized smoothing with three different kinds of defenses.
result Individual certificates can be obtained via statistical error bounds or efficient online inverse computation.

As deep neural networks become more adept at traditional tasks, many of the most exciting new challenges concern multimodality---observations that combine diverse types, such as image and text. In this paper, we introduce a family of multimodal deep generative models derived from variational bounds on the evidence (dat…

2019-12-11abs ↗pdf ↗

This work proves intrinsic robustness bounds for natural image distributions.

problem Understanding the robustness of natural image distributions against adversarial attacks.
method Assumes natural image distributions are captured by conditional generative models and proves robustness bounds for classifiers.
result Shows a large gap between theoretical robustness limits and current state-of-the-art adversarial robustness.

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…

2005-12-15abs ↗pdf ↗

The paper establishes lower bounds on Yang-Mills functionals for fibrations.

problem Analyzing the stability and nefness of direct image sheaves in fibrations.
method Generalizing mean curvature and Harder-Narasimhan filtrations to arbitrary polarized fibrations.
result Optimal lower bounds on fibered Yang-Mills functionals in terms of direct image sheaves.

We improve image perturbation defenses using a better-defined Wasserstein threat model.

problem Real-world image perturbations are not pixel-independent, unlike p\ell_p threat models.
method We rectify flaws in the Wasserstein threat model and explore stronger attacks and defenses.
result Current Wasserstein-robust models are ineffective against real-world perturbations.

We describe an approach for incorporating prior knowledge into machine learning algorithms. We aim at applications in physics and signal processing in which we know that certain operations must be embedded into the algorithm. Any operation that allows computation of a gradient or sub-gradient towards its inputs is suit…

2019-07-03abs ↗pdf ↗

Paper proposes an efficient method for bounding box annotation in object detection.

problem Manual annotation of bounding boxes is tedious and resource-intensive.
method Iterative training of object detector on small batches of labeled images, with human annotator correcting errors.
result Significant reduction in human annotation effort, up to 75%.

Deep convolutional neural networks have recently achieved state-of-the-art performance on a number of image recognition benchmarks, including the ImageNet Large-Scale Visual Recognition Challenge (ILSVRC-2012). The winning model on the localization sub-task was a network that predicts a single bounding box and a confid…

2013-12-08abs ↗pdf ↗

Study improves confidence measures in medical imaging pipelines by addressing bias.

problem Bias in metric-based imaging pipelines compromises the efficiency of prediction intervals.
method Formalized symmetric and asymmetric CP formulations, analyzed bias effects, and validated empirically.
result Symmetric intervals are inflated by bias, while asymmetric intervals remain unaffected.

The paper analyzes and proposes an algorithm for multi-modal nonlinear embeddings with theoretical performance bounds.

problem Generalizability of multi-modal nonlinear embeddings to unseen data.
method Theoretical analysis and a multi-modal nonlinear representation learning algorithm motivated by performance bounds.
result The proposed algorithm yields promising performance in multi-modal image classification and cross-modal image-text retrieval applications.

The paper studies volumes of direct images for high tensor powers of ample bundles.

problem Understanding asymptotics of Monge-Ampère volumes for high tensor powers of ample line bundles.
method Analyzes the leading term of asymptotics and classifies bundles saturating a topological bound.
result Provides a characterization of bundles admitting projectively flat Hermitian structures in the case of high symmetric powers of ample vector bundles.

The paper evaluates and improves uncertainty estimates in neural networks for safety-critical applications.

problem Quantifying uncertainty in neural networks for safety-critical systems.
method Proposes a statistical test for evaluating uncertainty realism in neural networks and transfers a classification architecture to image-to-image tasks.
result The variational U-Net architecture significantly improves uncertainty realism in image-to-image tasks compared to a plain model.

In this paper we present some bounds of Hausdorff measures of objects definable in o-minimal structures: sets, fibers of maps, inverse images of curves of maps, etc. Moreover, we also give some explicit bounds for semi-algebraic or semi-Pfaffian cases, which depend only on the combinatoric data representing the objects…

2012-04-25abs ↗pdf ↗

High-quality image synthesis with diffusion models, achieving state-of-the-art FID score.

problem Generating high-quality images from latent variables.
method Training diffusion probabilistic models with a weighted variational bound, inspired by denoising score matching and Langevin dynamics.
result State-of-the-art FID score of 3.17 on CIFAR10 dataset.

Study improves pollen detection in optical and holographic images using deep learning.

problem Improving pollen detection accuracy in holographic microscopy images.
method Used YOLOv8s for detection and MobileNetV3L for classification, addressing performance gaps through dataset expansion and automated labeling.
result Significant improvement in detection and classification performance on holographic images.

The Generative Adversarial Network (GAN) has recently been applied to generate synthetic images from text. Despite significant advances, most current state-of-the-art algorithms are regular-grid region based; when attention is used, it is mainly applied between individual regular-grid regions and a word. These approach…

2019-02-04abs ↗pdf ↗

Convolutional neural networks converge quickly with gradient descent.

problem Learning efficient image classifiers with over-parameterized networks.
method Gradient descent for training over-parametrized CNNs with global average-pooling.
result Gradient descent quickly reduces the misclassification risk of CNNs.

Improved visual representation learning with conditional negative sampling.

problem Learning strong unsupervised visual representations using contrastive learning.
method Introduce a family of mutual information estimators that sample negatives conditionally.
result Improves accuracy by 2-5% points on four standard image datasets.

AI enhances pollen recognition in veterinary imaging using holographic microscopy.

problem Challenges in recognizing pollen in holographic images due to speckle noise and artifacts.
method Training YOLOv8s and MobileNetV3L on dual-modality dataset, employing WGAN-SN for synthetic data augmentation.
result GAN-based augmentation improves object detection and classification in holographic images, closing the performance gap.