Search results for "Computer Vision and Pattern Recognition"

showing 10 items of 997 documents

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

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

On the Convergence of Tsetlin Machines for the IDENTITY- and NOT Operators

2020

The Tsetlin Machine (TM) is a recent machine learning algorithm with several distinct properties, such as interpretability, simplicity, and hardware-friendliness. Although numerous empirical evaluations report on its performance, the mathematical analysis of its convergence is still open. In this article, we analyze the convergence of the TM with only one clause involved for classification. More specifically, we examine two basic logical operators, namely, the "IDENTITY"- and "NOT" operators. Our analysis reveals that the TM, with just one clause, can converge correctly to the intended logical operator, learning from training data over an infinite time horizon. Besides, it can capture arbit…

FOS: Computer and information sciencesComputer Science - Machine LearningTraining setLearning automataComputer Science - Artificial IntelligenceComputer sciencebusiness.industryApplied MathematicsTime horizonPropositional calculusLogical connectiveMachine Learning (cs.LG)Artificial Intelligence (cs.AI)Operator (computer programming)Computational Theory and MathematicsArtificial IntelligencePattern recognition (psychology)Convergence (routing)Identity (object-oriented programming)Computer Vision and Pattern RecognitionArtificial intelligencebusinessSoftwareInterpretabilityIEEE Transactions on Pattern Analysis and Machine Intelligence
researchProduct

Extracting Deformation-Aware Local Features by Learning to Deform

2021

Despite the advances in extracting local features achieved by handcrafted and learning-based descriptors, they are still limited by the lack of invariance to non-rigid transformations. In this paper, we present a new approach to compute features from still images that are robust to non-rigid deformations to circumvent the problem of matching deformable surfaces and objects. Our deformation-aware local descriptor, named DEAL, leverages a polar sampling and a spatial transformer warping to provide invariance to rotation, scale, and image deformations. We train the model architecture end-to-end by applying isometric non-rigid deformations to objects in a simulated environment as guidance to pr…

FOS: Computer and information sciencesComputer Science - Machine Learning[INFO.INFO-CV] Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Computer Vision and Pattern Recognition (cs.CV)Computer Science::Computer Vision and Pattern RecognitionComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISIONComputer Science - Computer Vision and Pattern Recognition[INFO.INFO-CV]Computer Science [cs]/Computer Vision and Pattern Recognition [cs.CV]Machine Learning (cs.LG)ComputingMethodologies_COMPUTERGRAPHICS
researchProduct

Deep Non-Line-of-Sight Reconstruction

2020

The recent years have seen a surge of interest in methods for imaging beyond the direct line of sight. The most prominent techniques rely on time-resolved optical impulse responses, obtained by illuminating a diffuse wall with an ultrashort light pulse and observing multi-bounce indirect reflections with an ultrafast time-resolved imager. Reconstruction of geometry from such data, however, is a complex non-linear inverse problem that comes with substantial computational demands. In this paper, we employ convolutional feed-forward networks for solving the reconstruction problem efficiently while maintaining good reconstruction quality. Specifically, we devise a tailored autoencoder architect…

FOS: Computer and information sciencesComputer Science - Machine Learningbusiness.industryComputer scienceComputer Vision and Pattern Recognition (cs.CV)Image and Video Processing (eess.IV)Computer Science - Computer Vision and Pattern RecognitionNonlinear optics020207 software engineering02 engineering and technologyIterative reconstructionInverse problemElectrical Engineering and Systems Science - Image and Video ProcessingAutoencoderRendering (computer graphics)Machine Learning (cs.LG)Non-line-of-sight propagation0202 electrical engineering electronic engineering information engineeringFOS: Electrical engineering electronic engineering information engineering020201 artificial intelligence & image processingComputer visionArtificial intelligencebusiness
researchProduct

Human experts vs. machines in taxa recognition

2020

The step of expert taxa recognition currently slows down the response time of many bioassessments. Shifting to quicker and cheaper state-of-the-art machine learning approaches is still met with expert scepticism towards the ability and logic of machines. In our study, we investigate both the differences in accuracy and in the identification logic of taxonomic experts and machines. We propose a systematic approach utilizing deep Convolutional Neural Nets with the transfer learning paradigm and extensively evaluate it over a multi-pose taxonomic dataset with hierarchical labels specifically created for this comparison. We also study the prediction accuracy on different ranks of taxonomic hier…

FOS: Computer and information sciencesComputer Science - Machine Learninghahmontunnistus (tietotekniikka)Computer scienceClassification approachTaxonomic expert02 engineering and technologyneuroverkotcomputer.software_genreConvolutional neural networkQuantitative Biology - Quantitative MethodsField (computer science)Machine Learning (cs.LG)Machine learning approachesStatistics - Machine LearningAutomated approachDeep neural networks0202 electrical engineering electronic engineering information engineeringTaxonomic rankQuantitative Methods (q-bio.QM)Classification (of information)Artificial neural networksystematiikka (biologia)Prediction accuracyIdentification (information)koneoppiminenMulti-image dataBenchmark (computing)020201 artificial intelligence & image processingConvolutional neural networksComputer Vision and Pattern RecognitionClassification errorsMachine Learning (stat.ML)Machine learningState of the artElectrical and Electronic EngineeringTaxonomySupport vector machinesLearning systemsbusiness.industryNode (networking)020206 networking & telecommunicationsComputer circuitsHierarchical classificationConvolutionSupport vector machineFOS: Biological sciencesTaxonomic hierarchySignal ProcessingBiomonitoringBenchmark datasetsArtificial intelligencebusinesscomputertaksonitSoftware
researchProduct

Ensemble of Hankel Matrices for Face Emotion Recognition

2015

In this paper, a face emotion is considered as the result of the composition of multiple concurrent signals, each corresponding to the movements of a specific facial muscle. These concurrent signals are represented by means of a set of multi-scale appearance features that might be correlated with one or more concurrent signals. The extraction of these appearance features from a sequence of face images yields to a set of time series. This paper proposes to use the dynamics regulating each appearance feature time series to recognize among different face emotions. To this purpose, an ensemble of Hankel matrices corresponding to the extracted time series is used for emotion classification withi…

FOS: Computer and information sciencesComputer Science - RoboticsComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern RecognitionComputer Science - Human-Computer InteractionRobotics (cs.RO)Human-Computer Interaction (cs.HC)
researchProduct

Multi-Grid Redundant Bounding Box Annotation for Accurate Object Detection

2021

Modern leading object detectors are either two-stage or one-stage networks repurposed from a deep CNN-based backbone classifier network. YOLOv3 is one such very-well known state-of-the-art one-shot detector that takes in an input image and divides it into an equal-sized grid matrix. The grid cell having the center of an object is the one responsible for detecting the particular object. This paper presents a new mathematical approach that assigns multiple grids per object for accurately tight-fit bounding box prediction. We also propose an effective offline copy-paste data augmentation for object detection. Our proposed method significantly outperforms some current state-of-the-art object de…

FOS: Computer and information sciencesComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern Recognition
researchProduct

Eigen-Distortions of Hierarchical Representations

2017

We develop a method for comparing hierarchical image representations in terms of their ability to explain perceptual sensitivity in humans. Specifically, we utilize Fisher information to establish a model-derived prediction of sensitivity to local perturbations of an image. For a given image, we compute the eigenvectors of the Fisher information matrix with largest and smallest eigenvalues, corresponding to the model-predicted most- and least-noticeable image distortions, respectively. For human subjects, we then measure the amount of each distortion that can be reliably detected when added to the image. We use this method to test the ability of a variety of representations to mimic human p…

FOS: Computer and information sciencesComputer Vision and Pattern Recognition (cs.CV)Computer Science - Computer Vision and Pattern Recognition
researchProduct