Master Thesis in Emergent Width-Adaptive Representations via Spatially-Gated Channel Routing

Interested in exploring new approaches in deep learning and computer vision? Join our research team and help shape the future of autonomous perception systems – apply now! • You will develop and implement a novel and efficient transformer architecture for autonomous driving perception that adaptively adjusts its computational depth and width. • As part of evaluating the approach, you will design and conduct experiments to assess model performance and efficiency for key perception tasks such as semantic segmentation and object detection, while comparing the results with several baseline models. • Through detailed investigations, you will analyze emergent network properties, including the way computational resources are allocated to different image regions and how internal feature representations become organized. • In addition, you will contribute to cutting-edge research at the intersection of deep learning, computer vision, and autonomous driving, with the objective of creating safer and more scalable perception systems. • Education: master studies in the field of Informatics, Engineering, Natural Sciences or comparable with good grades • Experience and Knowledge: knowledge of deep learning concepts; familiarity with PyTorch; programming in Python • Personality and Working Practice: you are creative, enjoy a hands-on approach, and adapt quickly to new situations • Work Routine: your on-site presence is required • Languages: very good in English Start: according to prior agreement Duration: 3 - 6 months Requirement for this thesis is the enrollment at university. Please attach your CV, transcript of records, examination regulations and if indicated a valid work and residence permit. Diversity and inclusion are not just trends for us but are firmly anchored in our corporate culture. Therefore, we welcome all applications, regardless of gender, age, disability, religion, ethnic origin or sexual identity. Need further information about the job? Michael Ulrich (Functional Department) Work #LikeABosch starts here: Apply now! #LI-DNI