Current solutions to discriminative and generative tasks in computer vision exist separately and often lack interpretability and explainability. Using faces as our application domain, here we present an architecture that is based around two core ideas that address these issues: first, our framework learns an unsupervised, low-dimensional embedding of faces using an adversarial autoencoder that is able to synthesize high-quality face images. Second, a supervised disentanglement splits the low-dimensional embedding vector into four sub-vectors, each of which contains separated information about one of four major face attributes (pose, identity, expression, and style) that can be used both for discriminative tasks and for manipulating all four attributes in an explicit manner. The resulting architecture achieves state-of-the-art image quality, good discrimination and face retrieval results on each of the four attributes, and supports various face editing tasks using a face representation of only 99 dimensions. Finally, we apply the architecture's robust image synthesis capabilities to visually debug label-quality issues in an existing face dataset.
Biography: After graduating from the University of Stuttgart in 2009 with a M.Sc. in Computer Science, Björn Browatzki completed a Ph.D. in Computer Vision at the Max Planck Institute for Biological Cybernetics focusing on robotic vision applications. In 2014 he joined Wirewax Ltd., London, as a Computer Vision Engineer working on Face Identification in video. From 2016 to 2018 he held a research position at Reutlingen University of Applied Science. Since 2018 he is a Research
Professor at Korea University in Seoul. His main interests lie on the analysis of image and video data with a current focus on the understanding of human faces.