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 17 of 17 for “"Image-to-image translation"”.
-
Text-Guided Image-to-Image Translation for Converting RGB Maps to Tactile Images
… blind and visually impaired individuals access to visual information through touch, aiding navigation, education, and social interaction. However, manual tactile design is costly, time-intensive, and difficult to scale. This thesis proposes a novel approach to generate tactile maps from RGB maps …
-
Learning to map between domains
… everyone's cell phone has a camera. The photos taken by these cameras are shared massively and rapidly on the internet. However, there is an asymmetry: Each individual can consume only limited visual content in his limited lifetime, such that only a chosen few are talented enough to both …
-
Synthesizing Realistic Data for Vision Based Drone-to-Drone Detection
… drone detection is the limited amount of drone images for training. To address this issue, we used Generative Adversarial Networks, CycleGAN to be precise, for the generation of realistic looking fake images which were indistinguishable from real data. CycleGAN is a classic example of Image to …
-
Unsupervised Domain Adaptation per la rilevazione di oggetti e riconoscimento di azioni
… la rilevazione degli oggetti e il riconoscimento delle azioni. UDA è una tecnica di machine learning che mira a ridurre le differenze di distribuzione tra un dominio di origine (con dati etichettati) e un dominio di destinazione (con dati non etichettati). L'obiettivo principale è sviluppare …
-
Meta-Learning and Self-Supervised Pretraining for Few-shot Image Translation
… of these improvements are however constrained to problems with large-scale curated data-sets which require a lot of human labor to gather. Additionally, these models tend to generalize poorly under both slight distributional shifts and low-data regimes. In recent years, emerging fields such as …
-
Representations for intelligent navigation in unfamiliar environments
The way an agent chooses to represent the world around it is fundamental to its ability to effectively interact with it. The work presented in this thesis is centered around the development of new representations that enable embodied agents to better understand the impact of their actions, so that …
-
Robustifying Machine Learning based Security Applications
… the inputs (i.e., adversarial examples) to cause machine learning models to make a mistake, and it's very challenging to obtain a large amount of attackers' data. These make applying machine learning in security-critical applications difficult. In this dissertation, we present several …
-
Towards Learning the Geometry of Data: From Diffusion Models to Riemannian Geometry
… a conditional normalising flow that improves image-to-image translation by hierarchically modelling image distributions across scales. In chapter 4, we introduce non-uniform diffusion models, which apply faster diffusion speed to high-frequency information and slower diffusion speed to …
-
Capsule Networks: Framework and Application to Disentanglement for Generative Models
… of applications in various domains such as image-to-image translation, video prediction, and generating synthetic data where accessing real data is expensive, unethical, or compromising privacy. One of the main challenges in designing a generative model is creating a disentangled …
-
Toward reliable localization: exploring infrared fiducial markers and multi-imu fusion as alternative sensor modalities
… remains a fundamental challenge for autonomous systems operating in environments where traditional sensors underperform. This dissertation explores two alternative sensor modalities: infrared fiducial markers and multi-IMU integration, as means to enhance localization robustness in …
-
Dynamic image crowd representations for improved anomaly detection using generative adversarial networks
… information source, some of which contain images of crowds of high density. However, relying on the typical manual surveillance systems for detecting anomalies (any behaviour outlying from established normalcy) in crowds presents complications concerning accuracy and computation power. This …
-
Novel time resolved optical and machine learning methods for label free biomedical imaging
Recent advances in multiphoton microscopy are paving the way for better visualization and understanding of intracellular organisms, leading to powerful non-invasive methods for cell and tissue diagnosis. Mitochondrial disorder is a type of disorder that affects the cell's mitochondria and impacts …
-
Analysis of loss functions in XVAE-GAN: A novel two-view image generation network
DSpace SAF Submission Ingestion Package generated from Vireo submission #14457 on 2020-02-28 at 17:35:35
-
Controllable Visual Synthesis
… over the past years. It has shown remarkable image generation improvement from low-quality, pixelated images with limited details to highly realistic images with fine details that can often be mistaken for real images. However, the traditional pipeline of rendering an image in computer …
-
A Deep Learning Approach to Predict Full-Field Stress Distribution in Composite Materials
This thesis proposes a deep learning approach to predict stress at various stages of mechanical loading in 2-D representations of fiber-reinforced composites. More specifically, the full-field stress distribution at elastic and at an early stage of damage initiation is predicted based on the …
-
Computer Vision Algorithms for Yield Mapping in Specialty Farms
… and phenotyping technologies have the potential to drastically transform the agricultural landscape. For commodity crops such as maize, wheat and soy recurring farming tasks such as seeding, weeding, irrigation, fertilization, application of pesticides, harvesting, and storage are in the process …
-
Democratizing Deep Learning methods by means of AutoML tools
… técnicas de Inteligencia Artificial, y en concreto de aprendizaje profundo, o en inglés \emph{Deep Learning}, se han convertido en el estado del arte para lidiar con problemas de Visión por Computador en casi cualquier ámbito. Este crecimiento se debe a la gran cantidad de imágenes que se …