Search Results for author: Pia Hanfeld

Found 4 papers, 4 papers with code

Ensuring Topological Data-Structure Preservation under Autoencoder Compression due to Latent Space Regularization in Gauss--Legendre nodes

1 code implementation15 Sep 2023 Chethan Krishnamurthy Ramanaik, Juan-Esteban Suarez Cardona, Anna Willmann, Pia Hanfeld, Nico Hoffmann, Michael Hecht

Revisiting this classic enables to prove that regularised autoencoders ensure a one-to-one re-embedding of the initial data manifold to its latent representation.

Kidnapping Deep Learning-based Multirotors using Optimized Flying Adversarial Patches

1 code implementation1 Aug 2023 Pia Hanfeld, Khaled Wahba, Marina M. -C. Höhne, Michael Bussmann, Wolfgang Hönig

We introduce flying adversarial patches, where multiple images are mounted on at least one other flying robot and therefore can be placed anywhere in the field of view of a victim multirotor.

Pose Estimation Real-World Adversarial Attack +1

Flying Adversarial Patches: Manipulating the Behavior of Deep Learning-based Autonomous Multirotors

1 code implementation22 May 2023 Pia Hanfeld, Marina M. -C. Höhne, Michael Bussmann, Wolfgang Hönig

We introduce flying adversarial patches, where an image is mounted on another flying robot and therefore can be placed anywhere in the field of view of a victim multirotor.

Position

InFlow: Robust outlier detection utilizing Normalizing Flows

1 code implementation10 Jun 2021 Nishant Kumar, Pia Hanfeld, Michael Hecht, Michael Bussmann, Stefan Gumhold, Nico Hoffmann

Normalizing flows are prominent deep generative models that provide tractable probability distributions and efficient density estimation.

Density Estimation Outlier Detection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.