Webinar: New advances in deep learning with applications in the monitoring of power lines
This talk describes novel deep learning methodological research conducted at the UiT Machine Learning Group in collaboration with the company eSmart Systems.
Register by following the link below:
Link to the webinar will be sent directly to your e-mail address an hour before the webinar starts.
The motivation for the work is an industrial project where the aim is to monitor power lines from UAV images using specially developed deep convolutional neural networks. The talk describes a proposed neural network called the LS-Net for segmenting out line structures corresponding to power lines. Furthermore, inspired by the power line monitoring problem, the talk describes new basic research within so-called few-shot learning, proposing a new similarity measure to regularize such systems for better performance.
About Robert Jenssen
Robert Jenssen is Professor and Head of the UiT Machine Learning Group http://machine-learning.uit.no at UiT - The Arctic University of Norway. Jenssen received the Honorable Mention for the 2003 Pattern Recognition Journal Best Paper Award, the 2005 IEEE ICASSP Outstanding Student Paper Award, the 2007 UiT Young Investigator Award, the 2013 IEEE Geoscience and Remote Sensing Society Letters Best Paper Award, the 2017 International Medical Informatics Association (IMIA Yearbook) Best Paper Award, and the 2017 Scandinavian Conference on Image Analysis Best Student Paper Award (as supervisor). His paper, “Kernel Entropy Component Analysis,” was a featured paper of the IEEE Transactions on Pattern Analysis and Machine Intelligence. Jenssen is an adjunct professor with the Norwegian Computing Center in Oslo. He was previously a senior researcher (20%) at the Norwegian Center on E-Health Research. He has had long-term research stays at the Technical University of Denmark, Kongens Lyngby, Denmark, from 2012 to 2013, with the Technical University of Berlin, Berlin, Germany, from 2008 to 2009, and with the University of Florida, Gainesville, FL, USA, spring 2018, spring 2004, and from Sept. 2002 to July 2003. Jenssen serves on the IEEE Technical Committee on Machine Learning for Signal Processing and he is an Associate Editor for the journal Pattern Recognition. Until recently he was the chair of the Norwegian Association on Image Analysis and Pattern Recognition (NOBIM). Jenssen is the General Chair of the annual Northern Lights Deep Learning Workshop - NLDL, and has been General Chair of the Scandinavian Conference on Image Analysis.