Understanding and Improving Robustness and Uncertainty Estimation in Deep Learning.
Saarland University & Max Planck Institute for Informatics, July 2022.
Advisors: Prof. Bernt Schiele, Prof. Matthias Hein
Committee: Dr. Pawan Kumar, Prof. Mario Fritz, Prof. Eddy Ilg, Dr. Jan Eric Lenssen
[PDF, Project Page]
In March this year I finally submitted my PhD thesis and successfully defended in July. Now, more than 6 months later, my thesis is finally available in the university’s library. During my PhD, I worked on various topics surrounding robustness and uncertainty in deep learning, including adversarial robustness, robustness to bit errors, out-of-distribution detection and conformal prediction. In this article, I want to share my thesis and give an overview of its contents.
In July this year I finally defended my PhD which mainly focused on (adversarial) robustness and uncertainty estimation in deep learning. In my case, the defense consisted of a (public) 30 minute talk about my work, followed by questions from the thesis committee and audience. In this article, I want to share the slides and some lessons learned in preparing for my defense.
My master thesis, written at the Autonomous Vision Group of Max Planck Institute for Intelligent Systems under the supervision of Prof. Andreas Geiger, addresses the problem of 3D shape completion of sparse point clouds under weak supervision. Specifically, based on a learned shape prior it is possible to learn 3D shape completion without access to ground truth shapes, as shown on KITTI. This article briefly introduces the problem and the main contributions and offers the thesis as download.
Part of my master thesis at the Max Planck Institute for Intelligent Systems was an initial proposal — outlining the general idea and the current state-of-the-art. Specifically, I worked on learning 3D shape completion on KITTI using 3D bounding boxes only. In this article, I want to present this proposal.
My bachelor thesis, written at the Computer Vision Group at RWTH Aachen University, discusses superpixel segmentation utilizing depth information. Based on our own implementation of SEEDS , we examine the influence of depth information on the performance and compare several variants to other state-of-the-art approaches to superpixel segmentation.