Search results for " Vision"

showing 10 items of 2709 documents

Group Importance Sampling for particle filtering and MCMC

2018

Bayesian methods and their implementations by means of sophisticated Monte Carlo techniques have become very popular in signal processing over the last years. Importance Sampling (IS) is a well-known Monte Carlo technique that approximates integrals involving a posterior distribution by means of weighted samples. In this work, we study the assignation of a single weighted sample which compresses the information contained in a population of weighted samples. Part of the theory that we present as Group Importance Sampling (GIS) has been employed implicitly in different works in the literature. The provided analysis yields several theoretical and practical consequences. For instance, we discus…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer sciencePosterior probabilityMonte Carlo methodMachine Learning (stat.ML)02 engineering and technologyMultiple-try MetropolisStatistics - Computation01 natural sciencesMachine Learning (cs.LG)Computational Engineering Finance and Science (cs.CE)Methodology (stat.ME)010104 statistics & probabilitysymbols.namesake[INFO.INFO-TS]Computer Science [cs]/Signal and Image ProcessingStatistics - Machine LearningArtificial IntelligenceResampling0202 electrical engineering electronic engineering information engineering0101 mathematicsElectrical and Electronic EngineeringComputer Science - Computational Engineering Finance and ScienceStatistics - MethodologyComputation (stat.CO)ComputingMilieux_MISCELLANEOUSMarkov chainApplied Mathematics020206 networking & telecommunicationsMarkov chain Monte CarloStatistics::ComputationComputational Theory and MathematicsSignal ProcessingsymbolsComputer Vision and Pattern RecognitionStatistics Probability and UncertaintyParticle filter[SPI.SIGNAL]Engineering Sciences [physics]/Signal and Image processingAlgorithmImportance samplingDigital Signal Processing
researchProduct

Deep Learning Based Cardiac MRI Segmentation: Do We Need Experts?

2021

Deep learning methods are the de facto solutions to a multitude of medical image analysis tasks. Cardiac MRI segmentation is one such application, which, like many others, requires a large number of annotated data so that a trained network can generalize well. Unfortunately, the process of having a large number of manually curated images by medical experts is both slow and utterly expensive. In this paper, we set out to explore whether expert knowledge is a strict requirement for the creation of annotated data sets on which machine learning can successfully be trained. To do so, we gauged the performance of three segmentation models, namely U-Net, Attention U-Net, and ENet, trained with dif…

FOS: Computer and information sciencesComputer Science - Machine LearningComputer scienceProcess (engineering)GeneralizationIndustrial engineering. Management engineeringComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern Recognitionheartannotated data setT55.4-60.8Machine learningcomputer.software_genre030218 nuclear medicine & medical imagingTheoretical Computer ScienceMachine Learning (cs.LG)Set (abstract data type)03 medical and health sciences0302 clinical medicineFOS: Electrical engineering electronic engineering information engineeringSegmentationNumerical AnalysisArtificial neural networkbusiness.industryDeep learningsegmentationImage and Video Processing (eess.IV)deep learningQA75.5-76.95Electrical Engineering and Systems Science - Image and Video ProcessingComputational MathematicsHausdorff distanceComputational Theory and MathematicsIndex (publishing)Electronic computers. Computer scienceArtificial intelligencebusinesscomputer030217 neurology & neurosurgeryMRI
researchProduct

Warped Gaussian Processes in Remote Sensing Parameter Estimation and Causal Inference

2018

This letter introduces warped Gaussian process (WGP) regression in remote sensing applications. WGP models output observations as a parametric nonlinear transformation of a GP. The parameters of such a prior model are then learned via standard maximum likelihood. We show the good performance of the proposed model for the estimation of oceanic chlorophyll content from multispectral data, vegetation parameters (chlorophyll, leaf area index, and fractional vegetation cover) from hyperspectral data, and in the detection of the causal direction in a collection of 28 bivariate geoscience and remote sensing causal problems. The model consistently performs better than the standard GP and the more a…

FOS: Computer and information sciencesComputer Science - Machine LearningHeteroscedasticityRemote sensing applicationComputer scienceComputer Vision and Pattern Recognition (cs.CV)Maximum likelihoodComputer Science - Computer Vision and Pattern Recognition0211 other engineering and technologies02 engineering and technologyBivariate analysis010501 environmental sciences01 natural sciencesMachine Learning (cs.LG)Data modelingsymbols.namesakeElectrical and Electronic EngineeringGaussian process021101 geological & geomatics engineering0105 earth and related environmental sciencesRemote sensingParametric statisticsEstimation theoryHyperspectral imagingGeotechnical Engineering and Engineering GeologyConfidence intervalCausal inferencesymbolsIEEE Geoscience and Remote Sensing Letters
researchProduct

Graph Embedding via High Dimensional Model Representation for Hyperspectral Images

2021

Learning the manifold structure of remote sensing images is of paramount relevance for modeling and understanding processes, as well as to encapsulate the high dimensionality in a reduced set of informative features for subsequent classification, regression, or unmixing. Manifold learning methods have shown excellent performance to deal with hyperspectral image (HSI) analysis but, unless specifically designed, they cannot provide an explicit embedding map readily applicable to out-of-sample data. A common assumption to deal with the problem is that the transformation between the high-dimensional input space and the (typically low) latent space is linear. This is a particularly strong assump…

FOS: Computer and information sciencesComputer Science - Machine LearningI.5.2Computer Vision and Pattern Recognition (cs.CV)G.1.6I.5.4Image and Video Processing (eess.IV)0211 other engineering and technologiesComputer Science - Computer Vision and Pattern RecognitionI.4.702 engineering and technologyElectrical Engineering and Systems Science - Image and Video ProcessingI.4.10; I.5.2; G.1.6; I.4.7; I.5.4I.4.10Machine Learning (cs.LG)FOS: Electrical engineering electronic engineering information engineeringGeneral Earth and Planetary SciencesElectrical and Electronic Engineering021101 geological & geomatics engineering
researchProduct

Deep Importance Sampling based on Regression for Model Inversion and Emulation

2021

Understanding systems by forward and inverse modeling is a recurrent topic of research in many domains of science and engineering. In this context, Monte Carlo methods have been widely used as powerful tools for numerical inference and optimization. They require the choice of a suitable proposal density that is crucial for their performance. For this reason, several adaptive importance sampling (AIS) schemes have been proposed in the literature. We here present an AIS framework called Regression-based Adaptive Deep Importance Sampling (RADIS). In RADIS, the key idea is the adaptive construction via regression of a non-parametric proposal density (i.e., an emulator), which mimics the posteri…

FOS: Computer and information sciencesComputer Science - Machine LearningImportance samplingComputer scienceMonte Carlo methodPosterior probabilityBayesian inferenceInferenceContext (language use)Machine Learning (stat.ML)02 engineering and technologyEstadísticaStatistics - ComputationMachine Learning (cs.LG)symbols.namesakeSurrogate modelStatistics - Machine LearningArtificial Intelligence0202 electrical engineering electronic engineering information engineeringAdaptive regressionEmulationElectrical and Electronic EngineeringModel inversionGaussian processComputation (stat.CO)EmulationApplied Mathematics020206 networking & telecommunicationsRemote sensingComputational Theory and MathematicsSignal Processingsymbols020201 artificial intelligence & image processingComputer Vision and Pattern RecognitionStatistics Probability and UncertaintyAlgorithmImportance sampling
researchProduct

Brima: Low-Overhead Browser-Only Image Annotation Tool (Preprint)

2021

Image annotation and large annotated datasets are crucial parts within the Computer Vision and Artificial Intelligence this http URL the same time, it is well-known and acknowledged by the research community that the image annotation process is challenging, time-consuming and hard to scale. Therefore, the researchers and practitioners are always seeking ways to perform the annotations easier, faster, and at higher quality. Even though several widely used tools exist and the tools' landscape evolved considerably, most of the tools still require intricate technical setups and high levels of technical savviness from its operators and crowdsource contributors. In order to address such challenge…

FOS: Computer and information sciencesComputer Science - Machine LearningLow overheadProcess (engineering)Computer scienceComputer Vision and Pattern Recognition (cs.CV)Scale (chemistry)media_common.quotation_subjectComputer Science - Computer Vision and Pattern RecognitionMachine Learning (cs.LG)World Wide WebCrowdsourceAutomatic image annotationResearch communityQuality (business)Preprintmedia_common2021 IEEE International Conference on Image Processing (ICIP)
researchProduct

Unsupervised Anomaly and Change Detection With Multivariate Gaussianization

2022

Anomaly detection (AD) is a field of intense research in remote sensing (RS) image processing. Identifying low probability events in RS images is a challenging problem given the high dimensionality of the data, especially when no (or little) information about the anomaly is available a priori. While a plenty of methods are available, the vast majority of them do not scale well to large datasets and require the choice of some (very often critical) hyperparameters. Therefore, unsupervised and computationally efficient detection methods become strictly necessary, especially now with the data deluge problem. In this article, we propose an unsupervised method for detecting anomalies and changes …

FOS: Computer and information sciencesComputer Science - Machine LearningMultivariate statisticsComputer sciencebusiness.industryComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionFOS: Physical sciencesImage processingPattern recognitionMultivariate normal distributionComputational Physics (physics.comp-ph)Machine Learning (cs.LG)Methodology (stat.ME)Transformation (function)Robustness (computer science)General Earth and Planetary SciencesAnomaly detectionArtificial intelligenceElectrical and Electronic EngineeringbusinessPhysics - Computational PhysicsStatistics - MethodologyChange detectionCurse of dimensionalityIEEE Transactions on Geoscience and Remote Sensing
researchProduct

Environment Sound Classification using Multiple Feature Channels and Attention based Deep Convolutional Neural Network

2020

In this paper, we propose a model for the Environment Sound Classification Task (ESC) that consists of multiple feature channels given as input to a Deep Convolutional Neural Network (CNN) with Attention mechanism. The novelty of the paper lies in using multiple feature channels consisting of Mel-Frequency Cepstral Coefficients (MFCC), Gammatone Frequency Cepstral Coefficients (GFCC), the Constant Q-transform (CQT) and Chromagram. Such multiple features have never been used before for signal or audio processing. And, we employ a deeper CNN (DCNN) compared to previous models, consisting of spatially separable convolutions working on time and feature domain separately. Alongside, we use atten…

FOS: Computer and information sciencesComputer Science - Machine LearningSound (cs.SD)Computer science020209 energyMachine Learning (stat.ML)02 engineering and technologycomputer.software_genreConvolutional neural networkComputer Science - SoundDomain (software engineering)Machine Learning (cs.LG)Statistics - Machine LearningAudio and Speech Processing (eess.AS)0202 electrical engineering electronic engineering information engineeringFOS: Electrical engineering electronic engineering information engineeringAudio signal processingVDP::Teknologi: 500::Informasjons- og kommunikasjonsteknologi: 550business.industrySIGNAL (programming language)Pattern recognitionFeature (computer vision)Benchmark (computing)020201 artificial intelligence & image processingArtificial intelligenceMel-frequency cepstrumbusinesscomputerElectrical Engineering and Systems Science - Audio and Speech ProcessingCommunication channel
researchProduct

An Open-set Recognition and Few-Shot Learning Dataset for Audio Event Classification in Domestic Environments

2020

The problem of training with a small set of positive samples is known as few-shot learning (FSL). It is widely known that traditional deep learning (DL) algorithms usually show very good performance when trained with large datasets. However, in many applications, it is not possible to obtain such a high number of samples. In the image domain, typical FSL applications include those related to face recognition. In the audio domain, music fraud or speaker recognition can be clearly benefited from FSL methods. This paper deals with the application of FSL to the detection of specific and intentional acoustic events given by different types of sound alarms, such as door bells or fire alarms, usin…

FOS: Computer and information sciencesComputer Science - Machine LearningSound (cs.SD)sound processingaudio datasetmachine listeningUNESCO::CIENCIAS TECNOLÓGICASComputer Science - SoundMachine Learning (cs.LG)classificationArtificial IntelligenceAudio and Speech Processing (eess.AS)Signal ProcessingFOS: Electrical engineering electronic engineering information engineeringfew-shot learningopen-set recognitionComputer Vision and Pattern RecognitionSoftwareElectrical Engineering and Systems Science - Audio and Speech Processing
researchProduct

Kernel dependence regularizers and Gaussian processes with applications to algorithmic fairness

2019

Current adoption of machine learning in industrial, societal and economical activities has raised concerns about the fairness, equity and ethics of automated decisions. Predictive models are often developed using biased datasets and thus retain or even exacerbate biases in their decisions and recommendations. Removing the sensitive covariates, such as gender or race, is insufficient to remedy this issue since the biases may be retained due to other related covariates. We present a regularization approach to this problem that trades off predictive accuracy of the learned models (with respect to biased labels) for the fairness in terms of statistical parity, i.e. independence of the decisions…

FOS: Computer and information sciencesComputer Science - Machine LearningStatistics - Machine LearningArtificial IntelligenceSignal ProcessingMachine Learning (stat.ML)Computer Vision and Pattern RecognitionSoftwareMachine Learning (cs.LG)Pattern Recognition
researchProduct