The first one of these open guest lectures (at 13:15-14:00) will be available in the lecture hall, or by Zoom. The other ones will only be available in the lecture hall.
Deep Generative Models, Stable Diffusion, and the Revolution in Visual Synthesis.
Speaker: Björn Ommer.
Recently, deep generative modeling
has become the most prominent paradigm for learning powerful
representations of our (visual) world and for generating novel samples
thereof. Consequently, they have already become the main building block
for numerous algorithms and practical applications. This talk will
contrast the most commonly used generative models to date with a
particular focus on denoising diffusion probabilistic models, the core
of the currently leading approaches to visual synthesis. Despite their
enormous potential, these models come with their own specific
limitations. We will then discuss a solution, latent diffusion models
a.k.a. "Stable Diffusion", that significantly improves the efficiency of
diffusion models. Now billions of training samples can be summarized in
compact representations of just a few gigabyte so that the approach
runs on even consumer GPUs. Time permitting, the talk will conclude with
an outlook on current extensions and future work.
Ommer is a full professor at the University of Munich where he is
heading the Machine Vision and Learning Group. Before he was a full
professor in the department of mathematics and computer science at
Heidelberg University. 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.
serves as an associate editor for IEEE T-PAMI and previously for Pattern
Recognition Letters. His research interests include semantic scene
understanding, visual synthesis and retrieval, self-supervised metric
and representation learning, and explainable AI. Moreover, he is
applying this basic research in interdisciplinary projects within the
digital humanities and the life sciences.
The rest of the lectures, available in the lecture hall only:
- 14.15-14.30, Ericsson: AI/ML for future cellular networks. Speakers: Dr Jingya Li, and Dr Sven Jacobsson
- 14.30-14.45, Astra Zeneca: Deep Learning and AI at Astra Zeneca. Speaker: Dr Emil Gustavsson
- 14.45-15.00, Zenseact: Deep learning for autonomous driving. Speaker: Dr. Christoffer Petersson
This seminar is given as part of the course SSY340 Deep machine learning.
If you have any questions, please contact Lennart Svensson.
Welcome to join!
Seminar; Lecture; Public lecture
HB4, lecture hall, Hörsalar HB, Campus Johanneberg
12 October, 2022, 13:15
12 October, 2022, 15:00