Sökning: "CycleGAN"

Visar resultat 6 - 10 av 23 uppsatser innehållade ordet CycleGAN.

1. 6. LiDAR Point Cloud De-noising for Adverse Weather

   Master-uppsats, Högskolan i Halmstad/Akademin för informationsteknologi

   Författare :Johan Bergius; Jesper Holmblad; [2022]
   Nyckelord :Semantic Segmentation; Lidar point cloud; CNN; GAN; CycleGAN; Unsupervised; LiOR; DSOR; DROR; WADS;

   Sammanfattning : Light Detection And Ranging (LiDAR) is a hot topic today primarily because of its vast importance within autonomous vehicles. LiDAR sensors are capable of capturing and identifying objects in the 3D environment. However, a drawback of LiDAR is that they perform poorly under adverse weather conditions. LÄS MER

3. 7. Gaze tracking using Recurrent Neural Networks : Hardware agnostic gaze estimation using temporal features, synthetic data and a geometric model

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Fredrik Malmberg; [2022]
   Nyckelord :Gaze Tracking; Eye Tracking; Computer Vision; Transfer Learning; Synthetic Data; Domain Adaptation; Sequential Models; Blickspårning; Ögonspårning; Datorseende; Transfer Learning; Syntetisk Data; Domain Adaptation; Sekventiella Modeller;

   Sammanfattning : Vision is an important tool for us humans and significant effort has been put into creating solutions that let us measure how we use it. Most common among the techniques to measure gaze direction is to use specialised hardware such as infrared eye trackers. LÄS MER

4. 8. Enhancing Simulated Sonar Images With CycleGAN for Deep Learning in Autonomous Underwater Vehicles

   Master-uppsats, KTH/Matematisk statistik

   Författare :Aron Norén; [2021]
   Nyckelord :Deep Learning; Machine Learning; Sonar; Simulation; GAN; cycleGAN; YOLO-v4; Data Sparsity; Uncertainty Estimations; Djupinlärning; maskininlärning; sonar; simulering; GAN; cycleGAN; YOLO-v4; gles data; osäkerhetsanalys;

   Sammanfattning : This thesis addresses the issues of data sparsity in the sonar domain. A data pipeline is set up to generate and enhance sonar data. The possibilities and limitations of using cycleGAN as a tool to enhance simulated sonar images for the purpose of training neural networks for detection and classification is studied. LÄS MER

5. 9. Data Synthesis in Deep Learning for Object Detection

   Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

   Författare :Josef Haddad; [2021]
   Nyckelord :Deep Learning; Computer vision; Object detection; Synthetic data; Domain Adaptation; Machine Learning; Djupinlärning; Datorseende; Objektdetektion; Syntetiskt data; Domänadaption; Maskininlärning;

   Sammanfattning : Deep neural networks typically require large amounts of labeled data for training, but a problem is that collecting data can be expensive. Our study aims at revealing insights into how training with synthetic data affects performance in real-world object detection tasks. LÄS MER

7. 10. Image Synthesis Using CycleGAN to Augment Imbalanced Data for Multi-class Weather Classification

   Master-uppsats, Linköpings universitet/Medie- och Informationsteknik; Linköpings universitet/Tekniska fakulteten

   Författare :Marcus Gladh; Daniel Sahlin; [2021]
   Nyckelord :;

   Sammanfattning : In the last decade, convolutional neural networks have been used to a large extent for image classification and recognition tasks in a number of fields. For image weather classification, data can be both sparse and unevenly distributed amongst labels in the training set. LÄS MER