Bachelor's Thesis Deep Learning/computer - Berlin, Deutschland - Fraunhofer-Gesellschaft

Fraunhofer-Gesellschaft
Fraunhofer-Gesellschaft
Geprüftes Unternehmen
Berlin, Deutschland

vor 1 Monat

Lena Wagner

Geschrieben von:

Lena Wagner

beBee Recruiter
Beschreibung

Future. Discover. Together.


The Computer Vision & Graphics group of the Vision & Imaging Technologies (VIT) department is currently offering a bachelor thesis in the area of Unsupervised Domain Adaptation through Adaptation of Batch Norm Statistics.

Become a part of our team and join us on our journey of research and innovation


What you will do

  • The aim of the work is the detailed investigation of the applicability of the referenced methods on real data
  • For this purpose, suitable data sets are to be selected, in which the same scene was recorded under different weather conditions
  • Subsequently, a semantic segmentation is to be trained for a reference domain, which can then be applied to other weather conditions by adapting the batch norm parameters

What you bring to the table

  • Profound knowledge in deep learning and computer vision
  • Independent and structured way of working

What you can expect

  • Fascinating challenges in a scientific and entrepreneurial setting
  • Modern and excellently equipped workspace in central location
  • Great and cooperative working atmosphere in an international team


With its focus on developing key technologies that are vital for the future and enabling the commercial utilization of this work by business and industry, Fraunhofer plays a central role in the innovation process.

As a pioneer and catalyst for groundbreaking developments and scientific excellence, Fraunhofer helps shape society now and in the future.


For questions contact:
Anna Hilsmann

Johannes Künzel

Fraunhofer Institute for Telecommunications, Heinrich Hertz Institute HHI

Requisition Number: 64769
Application Deadline: 05/31/2023