Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 105 for “"feature map"”.

  1. Active perception in visual simultaneous localization and mapping by feature / map point selection

    Made available in DSpace on 2020-03-02T22:15:17Z (GMT). No. of bitstreams: 3 SHANGGUAN-THESIS-2019.pdf: 2228824 bytes, checksum: 5b85d2af527e7f9f5ccd86676233811f (MD5) ZhengheShangguan_Thesis-Master.docx: 3626082 bytes, checksum: d163037c82f5c7bd6cd1d7b6167c7684 (MD5) LICENSE.txt: 4214 bytes, …

    uiuc Repository record for Active perception in visual simultaneous localization and mapping by feature / map point selection (opens in a new tab)

  2. A Novel Feature Maps Covariance Minimization Approach for Advancing Convolutional Neural Network Performance

    … (CNN) by reducing the covariance between the feature maps of the convolutional layers. In a CNN, the units of a hidden layer are segmented into the feature/activation maps. The units within a feature map share the weight matrix (filter), or in simple terms look for the same feature. A feature …

    unlv Repository record for A Novel Feature Maps Covariance Minimization Approach for Advancing Convolutional Neural Network Performance (opens in a new tab) Download PDF for A Novel Feature Maps Covariance Minimization Approach for Advancing Convolutional Neural Network Performance (opens in a new tab)

  3. Improving Visual Embeddings using Attention and Geometry Constraints

    … image, video, or language) to a discriminative feature embedding space is considered a fundamental problem in the learning community. In such embedding spaces, the data with similar semantic meaning are clustered, while the data with dissimilar semantic meaning are separated. A number of …

    anu Repository record for Improving Visual Embeddings using Attention and Geometry Constraints (opens in a new tab)

  4. Deep Learning for Accelerated Magnetic Resonance Imaging

    … image. In this section, we propose a specific feature map based on the MRI knee dataset for GAN to reconstruct high perceptual quality MR knee images. We demonstrate that the MRI-based feature map is superior to the pre-trained feature map for GAN-based reconstruction. However, these networks …

    buffalo Repository record for Deep Learning for Accelerated Magnetic Resonance Imaging (opens in a new tab)

  5. DELINEATION OF RESTING STATE FUNCTIONAL MRI INTRINSIC BRAIN NETWORKS

    … the most common method to achieve functional mapping, but it has limitations. There is a need for non-invasive methods like fMRI that measure the functional connectivity of brain regions with high spatial and temporal resolution. However, fMRI independent components (ICs) must be manually …

    jhu Repository record for DELINEATION OF RESTING STATE FUNCTIONAL MRI INTRINSIC BRAIN NETWORKS (opens in a new tab)

  6. Direct estimation of the knee flexion angle from a monocular image during walking

    … model built with a ResNet backbone enhanced with feature map constraints to directly estimate lower limb anatomical landmarks, specifically knee flexion angles; by enforcing spatial consistency through internal feature map supervision; from monocular RGB images of defined functional movement …

    ets-quebec Download PDF for Direct estimation of the knee flexion angle from a monocular image during walking (opens in a new tab)

  7. Monocular Vision based Particle Filter Localization in Urban Environments

    … that uses aerial orthoimagery as a reference map. The topics of perception and localization are reviewed along with their modeling using a probabilistic framework. Computer vision techniques used to create the feature map and to extract features from camera images are discussed. Localization …

    waterloo Repository record for Monocular Vision based Particle Filter Localization in Urban Environments (opens in a new tab)

  8. Improving deep image feature matching

    … steps, where the high-dimensional local image features are first extracted across images and correspondences are established based on features' similarities. Image matching can be categorized into two sub-domains: geometric and semantic matching, where the former matches pixels describing the …

    oxford Repository record for Improving deep image feature matching (opens in a new tab)

  9. Semi-supervised universal yolov3-spp with GIoU loss for autonomous driving object detection under sunny and foggy weather

    … built with a universal adapter that consists a “feature map”-based attention module and a weather-based attention module. The “feature map”-based attention module has a parallel of Squeeze-and-Excitation (SE) adapters, where each SE adapter extracts different features from each channel. The …

    uiuc Repository record for Semi-supervised universal yolov3-spp with GIoU loss for autonomous driving object detection under sunny and foggy weather (opens in a new tab)

  10. Target Detection Using a Wavelet-Based Fractal Scheme

    … SAR imagery. Recently, a wavelet-based fractal feature set, similar to the proposed one, was compared with the EF feature for a general texture classification problem. The wavelet-based technique yielded a lower classification error than EF, which motivated the comparison between the two …

    uno Repository record for Target Detection Using a Wavelet-Based Fractal Scheme (opens in a new tab)

  11. Analysis of photogeologic fracture traces and lineaments in the northern portion of the Wartburg Basin, Tennessee

    <p>Photogeologic fracture trace and lineament mapping and analysis in the Wartburg Basin reveals important new information on the nature of fracturing in this area.</p> <p>Fracture traces and lineaments were mapped on ASCS black and white panchromatic aerial photographs and NASA high altitude color …

    ut-knoxville Repository record for Analysis of photogeologic fracture traces and lineaments in the northern portion of the Wartburg Basin, Tennessee (opens in a new tab)

  12. Clustering Epileptiform Discharges in the Interictal Electroencephalogram with Topography Preserving Maps

    Topography preserving maps have proved useful in the clustering of paroxysmal events in the Electroencephalogram (EEG) - in particular epileptiform events (EEvs) and artefacts. With the aim of enhancing performance of pre-existing systems, a novel variant of Kohonen’s Self Organising Feature Map …

    aston Repository record for Clustering Epileptiform Discharges in the Interictal Electroencephalogram with Topography Preserving Maps (opens in a new tab) Download PDF for Clustering Epileptiform Discharges in the Interictal Electroencephalogram with Topography Preserving Maps (opens in a new tab)

  13. Analysis and Explanation of Internet Search Engine Results Using Artificial Neural Networks and Fuzzy Logic

    … and show their similarities in a two dimensional map. This thesis is organized into four parts. First, there are brief reviews of the basic ideas and concepts of Artificial Neural Networks (ANNs) and Fuzzy Logic (FL) technologies. Then, we present a method that combines ANNs and FL to categorize …

    marquette Repository record for Analysis and Explanation of Internet Search Engine Results Using Artificial Neural Networks and Fuzzy Logic (opens in a new tab)

  14. Designing Efficient Deep Learning Models for Computer-Aided Medical Diagnosis

    … method for learning the inter-class mapping between under-represented class samples and over-represented samples in a bid to generate under-represented class samples using unpaired image-to-image translation. These synthetic images are then used as additional training data in the task …

    concordia Download PDF for Designing Efficient Deep Learning Models for Computer-Aided Medical Diagnosis (opens in a new tab)

  15. Interpreting intermediate feature representations of raw-waveform deep CNNs by sonification

    … sonification, a method to interpret intermediate feature representations of sound event recognition (SER) 1D-convolutional neural networks (1D-CNNs) trained on raw waveforms by mapping these representations back into the discrete-time input signal domain, highlighting substructures in the input …

    glasgow Repository record for Interpreting intermediate feature representations of raw-waveform deep CNNs by sonification (opens in a new tab) Download PDF for Interpreting intermediate feature representations of raw-waveform deep CNNs by sonification (opens in a new tab)

  16. Robotic Barrier Construction through Weaved, Inflatable Tubes

    … that are weaved around existing environmental features. These extruded tubes are based on everted vine robots, and we introduce a new method to steer their growth. The mechanism is characterized in terms of accuracy, resilience, and the ability of the tubes to withstand distributed loads. This …

    cornell Repository record for Robotic Barrier Construction through Weaved, Inflatable Tubes (opens in a new tab)

  17. Self-organizing neural networks for sequence representation and classification : application to the SCSS nuclear database

    … System. This methodology uses a Self-organizing Feature Map (SOFM) to perform an unsupervised classification of the events. Because events are sequences of occurrences of variable length and occurrences are sequences of an arbitrary number of letters, the classification of events with a SOFM …

    utk-theses Repository record for Self-organizing neural networks for sequence representation and classification : application to the SCSS nuclear database (opens in a new tab)

  18. A neural network approach to multisensor data fusion for vessel traffic services

    … identify the type of input data and other system features that are suitable for fusion. This is followed by a brief study of the various neural networks to evaluate their suitability for data fusion applications. The Kohonen's self-organizing feature map (SOFM) was identified as the most suitable …

    nps Repository record for A neural network approach to multisensor data fusion for vessel traffic services (opens in a new tab)

  19. Object recognition using self-organizing neural networks

    … and classifier layers. The first layer maps a digitized grey level image into a two dimensional array of nodes which contains the extracted features of the original image. This array is called a self-organizing feature map, and its interconnections with the input are reinforced during …

    ut-knoxville Repository record for Object recognition using self-organizing neural networks (opens in a new tab)

  20. Joint spatial and layer attention for convolutional networks

    … Neural Networks (CNN) layers (i.e., “what” feature abstraction to attend to) and different spatial locations of the selected feature map (i.e., “where”) to perform the task at hand. Specifically, at each Recurrent Neural Network (RNN) step, both a CNN layer and localized spatial region …

    uoit Repository record for Joint spatial and layer attention for convolutional networks (opens in a new tab)

Page 1 of 6