CHAIR Partner Seminar: Domain adaptation and deep learning across different industries

Each seminar includes a networking session to promote exchange of ideas, not only from presenter to listener, but between all participants. 
Our ambition is to support a collaborative environment between CHAIR and our core partners, and learn from each other.

Moderator: Fredrik Johansson, CHAIR.

Agenda 12 November:

10:00-10:20

Training-free guidance for plug-and-play score-based generative models in medical image-to-image translation

Jennifer Alvén, Chalmers, researches deep learning of medical images, including translating images between domains or classes. An application could be between healthy and sick, or between woman and man, to find patterns and causal relationships. Her research can be used to translate from an area with a lot of data to one with little data while taking into account the differences between the various data sources. 

In addition to healthcare, the research could be applied to image translation to recognize a specific road under different weather conditions. She is interested in plug-and-play scenarios within foundation models. 

10:20-10:40

Domain Adaptation for Network Performance Modeling with and without Labeled Data

Hannes Larsson is a Senior Researcher at Ericsson Research where he has been since 2019. His main focus is on distributed learning, transfer learning and domain adaptation for network operations and management.  Further, he is the co-inventor of multiple patent applications and co-author of several papers. He received his MSc degree in engineering physics in 2018 from Uppsala University. 

10:40-11:00

TBA

11:00-11:30

Networking session with coffee

11:30-12:00

Discussion: Domain adaptation and deep learning across different industries, talks and reflections on the presentations.