Sökning: "generative adversarial learning"

Visar resultat 1 - 5 av 7 uppsatser innehållade orden generative adversarial learning.

  1. 1. Object Detection using deep learning and synthetic data

    Master-uppsats, Linköpings universitet/Medie- och InformationsteknikLinköpings universitet/Tekniska fakulteten

    Författare :Love Lidberg; [2018]
    Nyckelord :Deep Learning; Convolutional Neural Networks; Generative Adversarial Networks; Synthetic; Object Detection; Classification;

    Sammanfattning : This thesis investigates how synthetic data can be utilized when training convolutional neural networks to detect flags with threatening symbols. The synthetic data used in this thesis consisted of rendered 3D flags with different textures and flags cut out from real images. LÄS MER

  2. 2. Generation of Synthetic Images with Generative Adversarial Networks

    Master-uppsats, Blekinge Tekniska Högskola/Institutionen för datalogi och datorsystemteknik

    Författare :Mousa Zeid Baker; [2018]
    Nyckelord :classification; deep learning; generative adversarial network; machine learning;

    Sammanfattning : Machine Learning is a fast growing area that revolutionizes computer programs by providing systems with the ability to automatically learn and improve from experience. In most cases, the training process begins with extracting patterns from data. The data is a key factor for machine learning algorithms, without data the algorithms will not work. LÄS MER

  3. 3. Cell Image Transformation Using Deep Learning

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :Emmy Sjöstrand; Jesper Jönsson; [2018]
    Nyckelord :Mathematics and Statistics;

    Sammanfattning : This thesis was written at CellaVision who sells digital microscope systems, mainly used for blood analysis. Blood tests are an important part of modern health care and today digital microscopes are widely used to replace conventional microscopy. LÄS MER

  4. 4. Generation of Artificial Training Data for Deep Learning

    Master-uppsats, Lunds universitet/Matematik LTH

    Författare :David Wessman; Pontus Andersson; [2018]
    Nyckelord :Artificial training data; deep learning; generative adversarial networks; large scale image generation; person re-identification.; Technology and Engineering;

    Sammanfattning : Can artificial training data be used for deep learning applications in computer vision? We investigated this by building a framework that uses computer graphics to generate large quantities of images portraying humans. Generative Adversarial Networks (GANs) were used to bridge the gap in appearance between the generated and real images. LÄS MER

  5. 5. Automotive 3D Object Detection Without Target Domain Annotations

    Master-uppsats, Linköpings universitet/Datorseende; Linköpings universitet/Datorseende

    Författare :Fredrik Gustafsson; Erik Linder-Norén; [2018]
    Nyckelord :Object Detection; 3D Object Detection; Domain Adaptation; Generative Adversarial Networks; Computer Vision; Deep Learning; Machine Learning; Autonomous Driving;

    Sammanfattning : In this thesis we study a perception problem in the context of autonomous driving. Specifically, we study the computer vision problem of 3D object detection, in which objects should be detected from various sensor data and their position in the 3D world should be estimated. LÄS MER