Kolloquium SoSe 2019

Image and video understanding is a difficult inverse problem. It requires learning a metric in image space that reflects object relations in real world. This metric learning problem calls for large volumes of training data. While images and videos are easily available, labels are not, thus motivating self-supervised metric and representation learning. Furthermore, I will present a widely applicable strategy based on deep reinforcement learning to improve the surrogate tasks underlying self-supervision. Thereafter, the talk will cover the learning of disentangled representations that explicitly separate different object characteristics by following an analysis-by-synthesis paradigm. I will discuss a variety of applications of this research ranging from behavior analysis in neuroscience to visual analytics in the digital humanities.

Bio

Björn Ommer is a professor in the Department of Mathematics and Computer Science at Heidelberg University and heading the Computer Vision Group. He received his diploma in Computer Science from University of Bonn and his PhD from ETH Zurich. Thereafter, he was a postdoc in the vision group of Jitendra Malik at UC Berkeley.

Björn serves as an associate editor for IEEE T-PAMI and previously for Pattern Recognition Letters. He is a co-director of the Interdisciplinary Center for Scientific Computing (IWR) and the Heidelberg Collaboratory for Image Processing. His research interests include semantic scene understanding, self-supervised visual metric and representation learning, object recognition in images and videos, and behavior analysis. He is applying this basic research in interdisciplinary projects with neuroscience and the digital humanities for which he also received an additional cooptation in the department of philosophy.