Projects

Investigation and implementation of ensemble-based semantic segmentation methods while looking at performance, floating point operations, execution time, and out-of-distribution robustness.

Large national project with a consortium of both industry and academia. The focus lied on establishing a stringend and provable safety argumentation for AI-based functions.

Investigation of methods for creating realistically looking universal adversarial attacks for semantic segmentation on video data.

Investigation of methods for teacher-student networks performing semantic segmentation under the context of adversarial robustness.