Search for dissertations about: "data augmentation"
Showing result 1 - 5 of 59 swedish dissertations containing the words data augmentation.
-
1. Data-driven AI Techniques for Fashion and Apparel Retailing
Abstract : Digitalisation allows companies to develop many new ways of interacting with customers and other stakeholders. These digital interactions typically generate data that can be stored and later processed for different objectives. READ MORE
-
2. Improving Language Models Using Augmentation and Multi-Modality
Abstract : Language models have become a core component in modern Natural Language Processing (NLP) as they constitute a powerful base that is easily adaptable to many language processing tasks. Part of the strength lies in their ability to embed associations representing general world knowledge. READ MORE
-
3. Synthetic data for visual machine learning : A data-centric approach
Abstract : Deep learning allows computers to learn from observations, or else training data. Successful application development requires skills in neural network design, adequate computational resources, and a training data distribution that covers the application do-main. READ MORE
-
4. Resource efficient automatic segmentation of medical images
Abstract : Cancer is one of the leading causes of death worldwide. In 2020, there were around 10 million cancer deaths and nearly 20 million new cancer cases in the world. Radiation therapy is essential in cancer treatments because half of the cancer patients receive radiation therapy at some point. READ MORE
-
5. Unobtrusive Augmentation of Physical Environments : Interaction Techniques, Spatial Displays and Ubiquitous Sensing
Abstract : The fundamental idea of Augmented Reality (AR) is to improve and enhance our perception of the surroundings, through the use of sensing, computing and display systems that make it possible to augment the physical environment with virtual computer graphics. AR is, however, often associated with user-worn equipment, whose current complexity and lack of comfort limit its applicability in many scenarios. READ MORE