Sökning: "3D training"

Visar resultat 21 - 25 av 169 uppsatser innehållade orden 3D training.

1. 21. Exploring Normalizing Flow Modifications for Improved Model Expressivity

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

   Författare :Marcel Juschak; [2023]
   Nyckelord :Normalizing Flows; Motion Synthesis; Invertible Neural Networks; Glow; MoGlow; Maximum Likelihood Estimation; Generative models; normaliserande flöden; rörelsesyntes; inverterbara neurala nätverk; Glow; MoGlow; maximum likelihood-skattning generativa modeller;

   Sammanfattning : Normalizing flows represent a class of generative models that exhibit a number of attractive properties, but do not always achieve state-of-the-art performance when it comes to perceived naturalness of generated samples. To improve the quality of generated samples, this thesis examines methods to enhance the expressivity of discrete-time normalizing flow models and thus their ability to capture different aspects of the data. LÄS MER

3. 22. Evaluation of Computer Tomography based Cancer Diagnostics with the help of 3D Printed Phantoms and Deep Learning

   Kandidat-uppsats, KTH/Skolan för teknikvetenskap (SCI)

   Författare :Alex Back; Pontus Pandurevic; [2023]
   Nyckelord :Machine Learning; Deep Learning; Convolutional Neural Networks; Perception Loss; CNN; DL; ML; Computer Tomography; CT; Cancer Diagnostics; Evaluation of Image Reconstruction; Radiomics; Tumors; 3D Printed Phantoms; 3D Printing; PLA;

   Sammanfattning : Computed x-ray tomography is one of the most common medical imaging modalities andas such ways of improving the images are of high relevance. Applying deep learningmethods to denoise CT images has been of particular interest in recent years. LÄS MER

4. 23. Self-supervised pre-training of an attention-based model for 3D medical image segmentation

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

   Författare :Albert Sund Aillet; [2023]
   Nyckelord :Computer vision; Deep learning; 3D Medical image segmentation; Self-supervised learning; Datorseende; Djupinlärning; 3D Medicinsk bildsegmentering; Självövervakad träning;

   Sammanfattning : Accurate segmentation of anatomical structures is crucial for radiation therapy in cancer treatment. Deep learning methods have been demonstrated effective for segmentation of 3D medical images, establishing the current standard. However, they require large amounts of labelled data and suffer from reduced performance on domain shift. LÄS MER

5. 24. Uncertainty Estimation in Volumetric Image Segmentation

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

   Författare :Donggyun Park; [2023]
   Nyckelord :Uncertainty Estimation; Uncertainty Quantification UQ ; Volumetric Image Segmentation; 3D U-Net; test-time data augmentation; Deep ensemble;

   Sammanfattning : The performance of deep neural networks and estimations of their robustness has been rapidly developed. In contrast, despite the broad usage of deep convolutional neural networks (CNNs)[1] for medical image segmentation, research on their uncertainty estimations is being far less conducted. LÄS MER

7. 25. Unsupervised Domain Adaptation for 3D Object Detection Using Adversarial Adaptation : Learning Transferable LiDAR Features for a Delivery Robot

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

   Författare :Mattias Hansson; [2023]
   Nyckelord :Unsupervised Domain Adaptation; 3D Object Detection; Mobile Robotics; Adversarial Adaptation; Computer Vision; Oövervakad Domänanpassning; 3D Objektigenkänning; Mobila Robotar; Motspelaranpassning; Datorseende;

   Sammanfattning : 3D object detection is the task of detecting the full 3D pose of objects relative to an autonomous platform. It is an important perception system that can be used to plan actions according to the behavior of other dynamic objects in an environment. LÄS MER