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.

169,291 papers · 148 categories

Trend · papers per month

77154230307 · Jun 202019922001200920182026
48 results for image regions

Paper develops SKPD framework for signal region detection in image regression.

problem Limited research on image region detection in high-resolution image regression.
method Sparse Kronecker Product Decomposition (SKPD) framework for matrices and tensors.
result Computed solutions converge to truth with guaranteed consistency.

This paper presents a new probabilistic generative model for image segmentation, i.e. the task of partitioning an image into homogeneous regions. Our model is grounded on a mid-level image representation, called a region tree, in which regions are recursively split into subregions until superpixels are reached. Given t…

2015-06-11abs ↗pdf ↗

Identification of regions of interest (ROI) associated with certain disease has a great impact on public health. Imposing sparsity of pixel values and extracting active regions simultaneously greatly complicate the image analysis. We address these challenges by introducing a novel region-selection penalty in the framew…

2016-05-27abs ↗pdf ↗

RGI improves robustness of GAN-inversion for image restoration and anomaly detection.

problem Robustness of GAN-inversion to unknown gross corruptions.
method Proposes RGI and R-RGI methods with provable robustness guarantees.
result Restored images and corrupted region masks converge to ground truth under mild assumptions.

Framework detects and classifies multi-label RBC images from microscopic images.

problem Challenges in separating touching or overlapping cells for classification.
method Region proposal model + CNN feature extraction + multi-label prediction networks.
result Framework achieves good performance in automatic cell detection and classification.

Simple regional perturbations maintain model transferability while reducing adversarial example distortion.

problem Comparing efficacy of regional adversarial attacks without complex methods.
method Developed a simple regional adversarial perturbation attack using cross-entropy sign.
result Localized adversarial examples require significantly less LpL_p norm distortion compared to non-local counterparts.

EBM uses high-dimensional imaging biomarkers to improve dementia progression estimation.

problem Current EBMs only use scalar biomarkers, limiting accuracy from cross-sectional data.
method Proposes nDEBM, a novel method using semi-supervised SVM on voxel-wise imaging biomarkers.
result nDEBM outperforms state-of-the-art EBM methods using regional volume biomarkers.

Improved object detection for scientific document images.

problem Current object detectors fail to accurately localize regions in scientific document images.
method Revised R-CNN model with region embedding for fine-grained proposals.
result 17% mAP improvement over standard object detection models.

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.

Model learns image-word associations from captions using contrastive learning.

problem Phrase grounding, associating image regions to caption words.
method Optimizing word-region attention to maximize mutual information, using language model guided word substitutions for negatives.
result Model achieves 76.7% accuracy on Flickr30K Entities benchmark, a 5.7% gain from weak supervision.

DNNs can approximate fractal functions with exponential linear regions.

problem Understanding neural network approximations of complex functions.
method Using Iterated Function Systems (IFS) and neural networks to generate fractal functions.
result DNNs can generate fractal functions with a number of linear regions exponential in the number of parameters.

PFE embeds images into sparse regions for better segmentation.

problem Image segmentation challenges with slowly varying signals and sparse region boundaries.
method Piecewise Flat Embedding (PFE) using sparse signal recovery theory, L1,p regularization, and Bregman iterations.
result PFE enhances image segmentation performance on multiple datasets.

Develops counterfactual visual explanations to show how images could change to classify differently.

problem Creating understandable explanations for vision system predictions.
method Selects a distractor image and identifies spatial regions to modify for different classification.
result Users trained with counterfactual explanations perform better in fine-grained bird classification.

The paper proposes a method to focus on discriminative regions for better unsupervised domain adaptation.

problem Unsupervised domain adaptation with limited target domain labels.
method Probabilistic certainty estimate of regions to focus on during classification.
result State-of-the-art results on various datasets compared to recent methods.

PaRCE estimates model confidence for CNNs across various uncertainties.

problem Limited holistic approach to estimating perception model confidence in CNNs.
method Probabilistic and reconstruction-based competency estimation.
result PaRCE best distinguishes between various types of samples and regions.

Topic models (e.g., pLSA, LDA, SLDA) have been widely used for segmenting imagery. These models are confined to crisp segmentation. Yet, there are many images in which some regions cannot be assigned a crisp label (e.g., transition regions between a foggy sky and the ground or between sand and water at a beach). In the…

2015-11-09abs ↗pdf ↗

We present a novel approach to automatically segment magnetic resonance (MR) images of the human brain into anatomical regions. Our methodology is based on a deep artificial neural network that assigns each voxel in an MR image of the brain to its corresponding anatomical region. The inputs of the network capture infor…

2015-02-09abs ↗pdf ↗

Novel graph-based framework for hyperspectral image classification using superpixels.

problem High classification accuracy with limited labelled data in hyperspectral images.
method Superpixel method for defining local regions, spectral and spatial features extraction, contracted graph representation, semi-supervised classifier.
result Our approach produces accurate classifications with minimal labelled data, outperforming state-of-the-art techniques.

MDGCN improves hyperspectral image classification by dynamically updating graphs.

problem Traditional CNNs struggle with irregular image regions and class boundaries.
method MDGCN uses dynamic graph convolution on hyperspectral images, adapting to local regions.
result MDGCN outperforms state-of-the-art methods on benchmark datasets.

Applying convolutional neural networks to large images is computationally expensive because the amount of computation scales linearly with the number of image pixels. We present a novel recurrent neural network model that is capable of extracting information from an image or video by adaptively selecting a sequence of …

2014-06-24abs ↗pdf ↗

OLALA automates document layout annotation by selecting ambiguous regions for labeling.

problem Efficiently annotating complex document layouts with limited resources.
method Object-Level Active Learning framework that selects ambiguous regions for labeling and uses semi-automatic correction.
result OLALA significantly boosts model performance and improves annotation efficiency.

A new method classifies hyperspectral images using dynamic graph convolutional networks.

problem Complex spatial context in HSI classification leads to inaccurate results.
method Develops a GCN-based method that captures long-range contextual relations and refines graph edges.
result Significant improvement in HSI classification performance compared to state-of-the-art methods.

SaliencyMix augments images with salient patches to improve model generalization.

problem Improving deep learning model generalization through better data augmentation.
method Carefully selects salient patches from images and mixes them with the target image.
result Achieves state-of-the-art top-1 error rates and robustness against adversarial attacks.

Improved breast cancer screening with a fast, memory-efficient model.

problem Classifying high-resolution breast cancer screening images.
method Extends globally-aware multiple instance classifier to handle image-level labels.
result Achieves AUC of 0.93 in classifying malignant findings, outperforming existing methods.

New method reduces false positives in weakly supervised pixel-level localization.

problem Reduces false positives in weakly supervised pixel-level localization.
method Proposes a deep learning method using conditional entropy to constrain the localizer.
result Significant improvements in image-level classification and pixel-level localization.

Project aims to diagnose and track IPF disease using deep learning.

problem Diagnosing and tracking IPF disease in lung images.
method Developed a deep learning model for identifying honeycombing and ground glass patterns in HRCT lung images.
result Deep learning model achieved high accuracy in identifying specific lung regions.

DBNet improves natural language image localization and detection.

problem Natural language-based visual entity localization with limited accuracy.
method Discriminative bimodal neural network (DBNet) trained with extensive negative samples.
result Significantly outperforms previous methods on Visual Genome dataset.

We study surface knots in 4-space by using generic planar projections. These projections have fold points and cusps as their singularities and the image of the singular point set divides the plane into several regions. The width (or the total width) of a surface knot is a numerical invariant related to the number of po…

2009-05-21abs ↗pdf ↗

Enhanced deep learning model improves tumor segmentation in ultrasound images.

problem Challenges in integrating patient-specific medical priors into deep learning models.
method Integrates visual saliency into a U-Net architecture with attention blocks.
result Achieved a Dice similarity coefficient of 90.5 percent on a dataset of 510 images.

Framework improves agent's ability to learn from noisy images.

problem Agents tend to focus on distracting regions in unsupervised image-based goal exploration.
method Proposes a novel framework combining absolute Learning Progress with unsupervised image-based goal exploration.
result Agents successfully identify and ignore distracting regions, improving overall performance.

Framework automates microstructure image analysis for materials science.

problem Complex microstructures in materials require automated analysis.
method Combines unsupervised and supervised learning for classification and segmentation.
result Framework can automatically segment and classify micrographs.