Projects
Heterogeneity in post-stroke attention: a computational approach to capture individual differences, their impact on daily life and lesion neuroanatomy KU Leuven
Hemispatial neglect, a syndrome characterized by spatial and non-spatial attention deficits is a common sequela after stroke. Research has revealed a detrimental impact of hemispatial neglect on independence in daily life and has failed to identify a critical lesion site underlying neglect. Most studies relied on pen-and-paper tests which are unable to dissociate spatial from non-spatial deficits. For this reason, studies have likely included ...
Particle and Power Exhaust Studies in the EAST Fusion Tokamak and Computational Analysis Using Coupled Fluid-Kinetic Plasma Codes KU Leuven
This PhD aims contributing in finding a solution for the particle and power exhaust problem in tokamak operation. Because the combination of a double null magnetic configuration and neon seeding seems promising in full-carbon experiments, the main focus is on exploring this potential in metallic devices.
This thesis is done in the EU-CN collaboration framework of EUROfusion and experiments are performed at the EAST tokamak, located at ...
Quantifying earlier indicators of disease in group housed pigs using computer vision KU Leuven
Introduction Diseases in pigs cause negative impact on their wellbeing, increasing the cost of production in pig industry by the rate of weight loss and death observed in affected pigs and affects public health by the increased use of antimicrobials while the development of antimicrobial resistance. Early detection of health and welfare compromises in commercial piggeries is essential for timely intervention to enhance treatment success, ...
Tractable Approximations for Achieving Higher Model Efficiency in Computer Vision KU Leuven
The 2010s have seen the first large-scale successes of computer vision “in the wild”, paving the way for industrial applications. Thanks to the formidable increase of processing power in consumer electronics, convolutional neural networks have led the way in this revolution. With enough supervision, these models have proven able to surpass human accuracy on many vision tasks. However, rather than focusing exclusively on accuracy, it is ...
A modular consistent, disciminative framework for structured output learning in computer vision. KU Leuven
State of the art computer vision systems are fundamentally reliant on statistical learning to optimize performance on a specific application. Currently, statistical frameworks in computer vision are typically based on classification and regression, probabilistic graphical models, or discriminative structured prediction frameworks such as the Structured Output Support Vector Machine (SOSVM). Although some of the best performing ...
Exploring Unsupervised Learning for Computer Vision Tasks with Neural Networks KU Leuven
Traditional supervised learning algorithms for computer vision tasks usually rely on large extensively annotated datasets. However, this labeling process can be expensive, biased, and susceptible to ambiguity.
The thesis explores self-supervised or unsupervised learning as a viable alternative to overcome these obstacles.
Specifically, it tackles fundamental perception tasks via neural networks and aims to automatically discover ...
A Modular, Consistent, Discriminative Framework for Structured Output Learning in Computer Vision. KU Leuven
State of the art computer vision systems are fundamentally reliant on statistical learning to optimize performance on a specific application. Currently, statistical frameworks in computer vision are typically based on classification and regression, probabilistic graphical models, or discriminative structured prediction frameworks such as the Structured Output Support Vector Machine (SOSVM). Although some of the best performing computer vision ...
Designing High-Performing Networks for Multi-Scale Computer Vision KU Leuven
Since the emergence of deep learning, the computer vision field has flourished with models improving at a rapid pace on more and more complex tasks. We distinguish three main ways to improve a computer vision model: (1) improving the data aspect by for example training on a large, more diverse dataset, (2) improving the training aspect by for example designing a better optimizer, and (3) improving the network architecture (or network for ...
Spatially Adaptive Neural Networks for Computer Vision KU Leuven
Over the past decade, computer vision has seen remarkable progress due to the emergence of data-driven deep learning approaches. Convolutional neural networks (CNN) extract relevant features in an automated way by training on annotated data. As research advances, more complex architectures have more trainable parameters and require more computations. However, executing these models requires powerful hardware, which limits their applicability ...