Essays about: "Disentangled Representation"
Showing result 1 - 5 of 6 essays containing the words Disentangled Representation.
-
1. Text-Driven Fashion Image Manipulation with GANs : A case study in full-body human image manipulation in fashion
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Language-based fashion image editing has promising applications in design, sustainability, and art. However, it is considered a challenging problem in computer vision and graphics. The diversity of human poses and the complexity of clothing shapes and textures make the editing problem difficult. READ MORE
-
2. Introducing Sparsity into the Current Landscape of Disentangled Representation Learning
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : In many scenarios it is natural to assume that a set of data is generated given a set of latent factors. If we consider some high-dimensional data, there might only be a few degrees of variability which are essential to the generation of such data. READ MORE
-
3. Modelling approach and avoidance behaviour : A deep learning approach to understand the human olfactory system
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : In this thesis we examine the question whether it is possible to model approach and avoidance behaviour with probabilistic machine learning. The results from this project will primarily aid in our collective understanding of human existence. READ MORE
-
4. On the effectiveness of ß-VAEs for imageclassification and clustering : Using a disentangled representation for Transfer Learning and Semi-Supervised Learning
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : Data labeling is a critical and costly process, thus accessing large amounts of labeled data is not always feasible. Transfer Learning (TL) and Semi-Supervised Learning (SSL) are two promising approaches to leverage both labeled and unlabeled samples. READ MORE
-
5. Unsupervised Learning of Useful and Interpretable Representations from Image Data
University essay from KTH/Skolan för elektroteknik och datavetenskap (EECS)Abstract : This master thesis tackles the problem of unsupervised learning of useful and interpretable representations from image data using deep Convolutional Neural Networks (CNN). Recent years have seen remarkable success from using deep learning technologies to tackle computer vision problems. READ MORE