6 papers
Structured Adversarial Camouflage via Voronoi Diagrams
Jens Bayer, Stefan Becker, David Münch +2
Pixel-wise adversarial patches are computationally heavy and often visually detectable, limiting utility in security-critical systems. We present adversarial Voronoi camouflage tha…
A Causally Grounded Taxonomy for Image Degradation Robustness Evaluation
Stefan Becker, Simon Weiss, Wolfgang Hübner +1
Image degradations can occur during acquisition, processing, and transmission, altering visual appearance and affecting downstream vision tasks. They are studied in several communi…
Self-Aware Object Detection via Degradation Manifolds
Stefan Becker, Simon Weiss, Wolfgang Hübner +1
Object detectors achieve strong performance under nominal imaging conditions but can fail silently when exposed to blur, noise, compression, adverse weather, or resolution changes.…
Higher-Order Adversarial Patches for Real-Time Object Detectors
Jens Bayer, Stefan Becker, David Münch +4
Higher-order adversarial attacks can directly be considered the result of a cat-and-mouse game -- an elaborate action involving constant pursuit, near captures, and repeated escape…
Traversing the Subspace of Adversarial Patches
Jens Bayer, Stefan Becker, David Münch +2
Despite ongoing research on the topic of adversarial examples in deep learning for computer vision, some fundamentals of the nature of these attacks remain unclear. As the manifold…
Strike the Balance: On-the-Fly Uncertainty based User Interactions for Long-Term Video Object Segmentation
Stéphane VujasinoviÄ, Stefan Becker, Sebastian Bullinger +3
In this paper, we introduce a variant of video object segmentation (VOS) that bridges interactive and semi-automatic approaches, termed Lazy Video Object Segmentation (ziVOS). In c…